US20180314729A9 - Semantic parsing engine - Google Patents

Semantic parsing engine Download PDF

Info

Publication number
US20180314729A9
US20180314729A9 US15/796,597 US201715796597A US2018314729A9 US 20180314729 A9 US20180314729 A9 US 20180314729A9 US 201715796597 A US201715796597 A US 201715796597A US 2018314729 A9 US2018314729 A9 US 2018314729A9
Authority
US
United States
Prior art keywords
query
graph
terms
graph query
elements
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US15/796,597
Other versions
US20180121500A1 (en
Inventor
Kevin Reschke
Ben Peloquin
Christopher Potts
Tharun Paul
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Roam Analytics Inc
Original Assignee
Roam Analytics Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Roam Analytics Inc filed Critical Roam Analytics Inc
Priority to US15/796,597 priority Critical patent/US20180314729A9/en
Assigned to ROAM ANALYTICS, INC. reassignment ROAM ANALYTICS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: PELOQUIN, Ben, PAUL, Tharun, POTTS, CHRISTOPHER, RESCHKE, Kevin
Publication of US20180121500A1 publication Critical patent/US20180121500A1/en
Publication of US20180314729A9 publication Critical patent/US20180314729A9/en
Priority to US17/012,319 priority patent/US11657044B2/en
Abandoned legal-status Critical Current

Links

Images

Classifications

    • G06F17/30401
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/242Query formulation
    • G06F16/243Natural language query formulation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/242Query formulation
    • G06F16/2428Query predicate definition using graphical user interfaces, including menus and forms
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/245Query processing
    • G06F16/2455Query execution
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/901Indexing; Data structures therefor; Storage structures
    • G06F16/9024Graphs; Linked lists
    • G06F17/30398
    • G06F17/30477
    • G06F17/30958
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0481Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
    • G06F3/0482Interaction with lists of selectable items, e.g. menus

Definitions

  • the subject matter disclosed herein generally relates to the technical field of special-purpose machines for dataset clustering and search engines that facilitate data set navigation and database queries, including software-configured computerized variants of such special-purpose machines and improvements to such variants, and to the technologies by which such special-purpose machines become improved compared to other special-purpose machines that facilitate generation of search results and relational links between discrete data sets using a canonical semantic layer.
  • data systems organize data into discrete sets and using standardized identifiers, categories, and characteristics. This organization enables easier and faster searching by organizing data published or consolidated by a single entity.
  • Data systems searching differing data sets, published across multiple entities encounter difficulties in correlating organizational structures. Further difficulties are encountered where data sets are provided in differing formats. While conventional data systems may be able to retrieve distinct documents or elements from multiple data sets, these data systems often provide the documents with no context or relation to other documents presented within the same or similar search results. As a result, conventional data systems attempting to draw inferences or determine links between data sets often present results with unacceptable degrees of uncertainty.
  • FIG. 1 is a block diagram illustrating a networked system, according to some example embodiments.
  • FIG. 2 is a block diagram of an example semantic parsing system, according to various embodiments.
  • FIG. 3 is a flowchart illustrating an example method of converting query structures for information retrieval from graph-based data structures using the semantic parsing system, according to various embodiments.
  • FIG. 4 is an example graphical user interface of the semantic parsing system, according to various embodiments.
  • FIG. 5 is a flowchart illustrating an example method of converting query structures for information retrieval from graph-based data structures using the semantic parsing system, according to various embodiments.
  • FIG. 6 is a flowchart illustrating an example method of converting query structures for information retrieval from graph-based data structures using the semantic parsing system, according to various embodiments.
  • FIG. 7 is an example graphical user interface of the semantic parsing system, according to various embodiments
  • FIG. 8 is a block diagram illustrating an example of a software architecture that may be installed on a machine, according to some example embodiments.
  • FIG. 9 illustrates a diagrammatic representation of a machine in the form of a computer system within which a set of instructions may be executed for causing the machine to perform any one or more of the methodologies discussed herein, according to an example embodiment.
  • Systems and method described herein define a semantic parsing system or semantic parsing engine for dataset graphs method for large scale knowledge graphs (e.g., health knowledge graphs) that is graph-backed in the sense that its grammar and semantic concepts are derived automatically from the graph schema.
  • the methods and systems also enable a superior search experience compared to raw database queries.
  • the systems and methods described herein are able to generate a connected knowledge graph by unifying any suitable data set, information, set of publications, or set of documents using semantic layers organizing or underlying the data sources and using machine learning techniques to generate models to incorporate new edges and relationships into the canonical layer.
  • the systems and methods disclosed herein present an approach to developing semantic parsers over large knowledge graphs, such as large health knowledge graphs (HKGs) derived from these public datasets.
  • These semantic parsers are graph-backed, such that the schema for the target graph is used to define the core space of entities, concepts, and relations; it provides the initial seed sets for defining the semantic lexicon; and it helps delimit the space of rules for syntactic and semantic combination.
  • very large and complex grammars are easily instantiated, addressing one of the major bottlenecks for semantic parsing at scale.
  • the result of the systems and methods disclosed herein is expanded access to public health information, so the semantic parser, in some example embodiments, is natural language search into health knowledge graphs. Natural language searching may differ from a database query language, which can be cumbersome even for experts and which puts most information out of reach for regular users. The promise of natural language search is that it removes these obstacles.
  • the present disclosure includes a usability study comparing the semantic parsing system with issuing raw graph query language statements. All participants were experts in the graph query language. As a group, they completed tasks faster and in fewer attempts with our system than with raw queries, and they preferred our system for everything except very complex queries.
  • a networked system 102 in the example forms of a network-based predictive modeling system, provides server-side functionality via a network 104 (e.g., the Internet or wide area network (WAN)) to one or more client devices 110 .
  • FIG. 1 illustrates, for example, a web client 112 (e.g., a browser, such as the INTERNET EXPLORER® browser developed by Microsoft® Corporation of Redmond. Washington State), an application 114 , and a programmatic client 116 executing on client device 110 .
  • a web client 112 e.g., a browser, such as the INTERNET EXPLORER® browser developed by Microsoft® Corporation of Redmond. Washington State
  • an application 114 e.g., a programmatic client 116 executing on client device 110 .
  • the client device 110 may comprise, but is not limited to, mobile phones, desktop computers, laptops, personal digital assistants (PDAs), smart phones, tablets, ultra books, netbooks, laptops, multi-processor systems, microprocessor-based or programmable consumer electronics, game consoles, set-top boxes, or any other communication device that a user may utilize to access the networked system 102 .
  • the client device 110 may comprise a display component (not shown) to display information (e.g., in the form of user interfaces).
  • the client device 110 may comprise one or more of a touch screens, accelerometers, gyroscopes, cameras, microphones, global positioning system (GPS) devices, and so forth.
  • GPS global positioning system
  • the client device 110 may be a device of a user that is used to perform a transaction involving object data and predictive models within the networked system 102 .
  • One or more users 106 may be a person, a machine, or other means of interacting with client device 110 .
  • the user 106 is not part of the network architecture 100 , but may interact with the network architecture 100 via client device 110 or another means.
  • one or more portions of network 104 may be an ad hoc network, an intranet, an extranet, a virtual private network (VPN), a local area network (LAN), a wireless LAN (WLAN), a WAN, a wireless WAN (WWAN), a metropolitan area network (MAN), a portion of the Internet, a portion of the Public Switched Telephone Network (PSTN), a cellular telephone network, a wireless network, a WiFi network, a WiMax network, another type of network, or a combination of two or more such networks.
  • Each of the client device 110 may include one or more applications (also referred to as “apps”) such as, but not limited to, a web browser, messaging application, electronic mail (email) application, and the like.
  • One or more users 106 may be a person, a machine, or other means of interacting with the client device 110 .
  • the user 106 is not part of the network architecture 100 , but may interact with the network architecture 100 via the client device 110 or other means.
  • the user provides input (e.g., touch screen input or alphanumeric input) to the client device 110 and the input is communicated to the networked system 102 via the network 104 .
  • the networked system 102 in response to receiving the input from the user, communicates information to the client device 110 via the network 104 to be presented to the user. In this way, the user can interact with the networked system 102 using the client device 110 .
  • An application program interface (API) server 120 and a web server 122 are coupled to, and provide programmatic and web interfaces respectively to, one or more application servers 140 .
  • the application servers 140 may host one or more publication systems 142 and a semantic parsing systems 150 , each of which may comprise one or more components or applications and each of which may be embodied as hardware, software, firmware, or any combination thereof.
  • the application servers 140 are, in turn, shown to be coupled to one or more database servers 124 that facilitate access to one or more information storage repositories or database(s) 126 .
  • the databases 126 are storage devices that store information to be posted (e.g., publications or listings) to the publication system 142 .
  • the databases 126 may also store object data, historical data, and predictive modeling data in accordance with example embodiments.
  • a third-party application 132 executing on third party server(s) 130 , is shown as having programmatic access to the networked system 102 via the programmatic interface provided by the API server 120 .
  • the third-party application 132 utilizing information retrieved from the networked system 102 , supports one or more features or functions on a website hosted by the third party.
  • the publication system 142 may provide a number of publication, archival, and data storage functions and services to users 106 that access the networked system 102 .
  • the publication system 142 may gather, publish, and store object data, historical data for one or more objects, sales data for one or more objects, revenue data for one or more objects, release data for one or more objects, competitor data for one or more objects, publicly distributed datasets for industries, datasets for users or practitioners associated with identified industries, census and other demographic data informing industry datasets, and taxonomy data sets comprising ontological descriptions of industry datasets.
  • the publication system 142 may publish the received or accessed datasets or may provide a consolidated database of the received or accessed datasets to an internal database or publicly available database to enable generation of predictive models and dataset network models based on the datasets.
  • the publication system 142 accesses one or more third party servers or databases (e.g., the third-party server 130 ) to retrieve, modify, and provision the object data within the database 126 .
  • the semantic parsing systems 150 may provide functionality operable to perform various dataset network model generation and predictive model generation and manipulation functions, as well as functions for generating graphical representations of datasets, dataset network models, and predictive models. For example, the semantic parsing systems 150 accesses datasets from the databases 126 , the third-party servers 130 , the publication system 142 , the client device 110 , and other sources. In some example embodiments, the semantic parsing systems 150 analyzes portions of the sets of object data to generate dataset network models and predictive models interpreting, drawing inferences from, and supplying search and result retrieval functionality for the accessed datasets.
  • the semantic parsing systems 150 communicates with the publication systems 142 to access the datasets and transmit queries received by the semantic parsing systems 150 to the publication system 142 .
  • the semantic parsing systems 150 may be a part of the publication system 142 .
  • client-server-based network architecture 100 shown in FIG. 1 employs a client-server architecture
  • present inventive subject matter is of course not limited to such an architecture, and could equally well find application in a distributed, or peer-to-peer, architecture system, for example.
  • the various publication system 142 and semantic parsing systems 150 could also be implemented as standalone software programs, which do not necessarily have networking capabilities.
  • the web client 112 may access the various publication and dataset network modeling systems 142 and 150 via the web interface supported by the web server 122 .
  • the programmatic client 116 accesses the various services and functions provided by the publication and dataset network modeling systems 142 and 150 via the programmatic interface provided by the API server 120 .
  • a third-party application(s) 128 executing on a third-party server(s) 130 , is shown as having programmatic access to the networked system 102 via the programmatic interface provided by the API server 114 .
  • the third-party application 128 utilizing information retrieved from the networked system 102 , may support one or more features or functions on a website hosted by the third party.
  • the third-party website may, for example, provide one or more promotional, marketplace, data repository, company interaction, or object tracking functions that are supported by the relevant applications of the networked system 102 .
  • FIG. 2 is a block diagram illustrating components of the semantic parsing systems 150 , according to some example embodiments.
  • the semantic parsing systems 150 is shown as including a receiver component 210 , a database component 220 , a semantic parsing component 230 , a modeling component 240 , and a presentation component 250 all configured to communicate with one another (e.g., via a bus, shared memory, or a switch).
  • Any one or more of the components described herein may be implemented using hardware (e.g., one or more processors of a machine) or a combination of hardware and software.
  • any component described herein may configure a processor (e.g., among one or more processors of a machine) to perform operations for which that component is designed.
  • any two or more of these components may be combined into a single component, and the functions described herein for a single component may be subdivided among multiple components.
  • components described herein as being implemented within a single machine, database(s) 126 , or device may be distributed across multiple machines, database(s) 126 , or devices.
  • FIG. 3 is a flowchart of operations of the semantic parsing system 150 in performing a method 300 of converting query structures for information retrieval from graph-based data structures using a semantic parsing system, according to some example embodiments. Operations of the method 300 may be performed by the semantic parsing system 150 , using components described herein.
  • the receiver component 210 receives a natural language query.
  • the natural language query may comprise a set of terms.
  • the natural language query may be transmitted to the semantic parsing system 150 to perform a search on one or more databases or datasets connected together in a knowledge graph.
  • the natural language query may include terms generated by a user associated with the query, such as by text entry.
  • the user may initially be presented with a text entry field 402 within a graphical user interface 400 .
  • the text entry field 402 may be configured to receive data entered by a user.
  • the natural language query 404 may be displayed within the text entry field 402 upon entry by the user.
  • the knowledge graph may be comprised of a plurality of subgraphs connected together.
  • the subgraphs may initially be isolated from one another, but connected by forming edges extending between related nodes of the isolated subgraphs in order to generate the knowledge graph.
  • the knowledge graph may be formed from public health datasets.
  • the public health datasets under consideration may not be released by a single entity using a consistent set of identifiers. Rather, each dataset presents a partial, potentially biased view of the world, the union of all the information in them is likely to be inconsistent, and establishing even simple links between entities often must be cast as a model-based inference under uncertainty.
  • the knowledge graph is formed from the distinct datasets in a manner producing a single connected graph with high confidence.
  • public datasets may be assembled into a connected graph, united thematically around common or related subjects, entities, or information.
  • An example of suitable public datasets may include datasets related to physicians and prescribing behavior.
  • Example public datasets may include, but are not limited to, National Provider Identifier, a registry of healthcare providers; CMS Physician Compare, data on physicians and their practices; CMS Open Payments Research, research support by manufacturers; Healthcare Taxonomy, three-level classification of medical specialties; CMS Prescriptions, information on prescriptions written under Medicare Part D; and FDA Drug Labels, information relating to drugs and their associated and regulated metadata.
  • the natural language queries, seeking to surface information from the knowledge graph may be formulated to take advantage of the structure of the knowledge graph.
  • Nodes and edges within the knowledge graph may be associated with types. Each type of node or edge may be associated with numerous attributes. For example, some edges may represent identity-relation edges and may be added based on identifiers, heuristic methods, and model-based inferences, with the direction chosen arbitrarily.
  • NPI identities connect NPI, CMS Physician Compare, and CMS Prescriptions via providers.
  • Taxonomy codes connect the NPI with the Healthcare Taxonomy. Brand and generic names connect CMS Prescriptions to FDA Drug Labels via drugs.
  • the CMS Open Payments Research dataset unlike CMS Prescriptions, may not contain NPI identifications, so the knowledge graph or models used to traverse the knowledge graph may be trained using a log-linear classifier and using a Dedupe package. Such training methodology may match nodes or attributes, characteristics, or metadata for nodes with high confidence.
  • the resulting graph may be instantiated in Neo4j.
  • the knowledge graph may comprise a plurality of nodes and edges, each numbering in the millions.
  • the semantic parsing component 230 generates an intermediate semantic representation of the set of terms of the natural language query.
  • the intermediate semantic representation may be a logical form representation.
  • the semantic parsing component 230 may automatically convert the natural language query to the logical form representation upon receipt of the natural language query from the text entry field 402 of the graphical user interface 400 depicted in FIG. 4 .
  • the semantic parsing component 230 includes PYTHON® code implemented at a webserver serving the graphical user interface 400 to a computing device of a user.
  • the semantic parsing component 230 may be an in-memory parser.
  • the semantic parsing component 230 and the modeling component 240 form a single component handling translation of the natural language query to a graph query, described below.
  • the semantic parsing component 230 comprises a graph-backed semantic parser.
  • the semantic parsing component 230 may configure, modify, or translate the natural language query through one or more operations to navigate around the challenges of distinct datasets incorporated into a single knowledge graph and resulting from inconsistencies among the distinct datasets.
  • the knowledge graph may be determined by the structure of the underlying databases.
  • the edges connecting discrete subgraphs may be added to connect these isolated subgraphs based on related attributes of individual nodes within the connected subgraphs.
  • the intermediate semantic representation is generated using one or more operations or sub-operations.
  • the semantic parsing component 230 may parse the set of terms of the natural language query to identify types of terms included in the natural language query.
  • the semantic parsing component 230 may identify types such as entities, actions, comparisons, nouns, verbs, adjectives, adverbs, and other suitable types.
  • the semantic parsing component 230 may then identify one or more relationships between the set of terms. The relationships may be based on proximity of the terms, syntactic or grammatical interactions of the terms, nature of the terms (e.g., comparative, superlative, etc.), intersecting relationships or terms, sorting relationships or terms, and any other suitable relationship.
  • the semantic parsing component 230 converts the set of terms to a logical form representation based on the one or more relationships.
  • the logical form representation is the intermediate semantic representation of the natural language query.
  • a grammar aspect of graph-backing, in the semantic parsing component 230 is employed in translating the natural language query into the intermediate semantic representation.
  • the semantic parsing component 230 may employ a graph schema of the knowledge graph to define at least a portion of the grammar rules of the semantic parsing component 230 . For example, where the schema contains Person-->WORKS_IN-->Location, the semantic parsing component 230 may create a syntax rule, such as “PERSON !
  • the semantic parsing component 230 may additionally allow bridging concept terms in the logical forms that have no syntactic realization but establish the desired semantic links, equivalently, graph paths.
  • a natural language query includes terms of “top JANUVIA® prescribers in New York,” the query involves three uses of an intersect operator as well as one use of a sorted operator. The sorted operator may be triggered by the superlative modifier “top.”
  • the semantic parsing component 230 may use one or more semantic or syntax rules associated with the CMS Prescriptions sub-graph, where that sub-graph uses internal ‘cms_drug’ nodes. Further, a bridging concept may be triggered to relate a provider to a drug based on expectations generated by relationships of nodes within the knowledge graph.
  • the modeling component 240 generates a graph query including graph terms corresponding to the set of terms of the natural language query.
  • the graph query may be represented within the graphical user interface 400 as a set of selectable user interface elements 406 .
  • generation of the graph query is based on the intermediate semantic representation.
  • the graph terms may be defined based on a graph-based database and the set of terms of the natural language query.
  • the graph query may comprise or be generated as a cypher query.
  • the modeling component 240 may map one or more of the natural language query and the intermediate semantic representation into a declarative query language cypher, such as an Neo4j query language Cypher.
  • the modeling component 240 interacts with the semantic parsing component 230 , receiving the intermediate semantic representation and converting the representation into the graph query.
  • the modeling component 240 may be an in-memory language model.
  • the modeling component 240 uses a language model, an entity index, a lexical resource, and grammar or syntax rules associated with the knowledge graph to transform the natural language query or the intermediate semantic representation into the graph query with the graph terms.
  • the modeling component 240 and the resulting graph query may be defined by the underlying knowledge graph.
  • the language models used for entity detection may be trained on name-type attributes of nodes.
  • the language models, incorporated in the modeling component 240 may resolve those entities using graph-backed operations. For example, an “Entity index” may be automatically created from a database or the knowledge graph and provide fast look-up for the semantic parsing component 230 or the modeling component 240 .
  • a “Lexical analysis” operation may be similarly graph-backed, incorporating node and edge type-names to provide the core lexicon.
  • the core lexicon may then be expand using additional databases or data sets, such as third-party data sets like Wikomary, WordNet, and heuristic morphological expansions.
  • the database component 220 searches one or more datasets associated with the graph database using the graph query.
  • the modeling component 240 may pass the graph query to the database component 220 for searching against the datasets included in the knowledge graph.
  • the database component 220 includes a search engine to perform an entity search or other term based searches using the graph query.
  • the database component 220 parses or otherwise searches attributes, characteristics, and other information of nodes, clusters, datasets, and subgraphs of the knowledge graph to identify nodes, entities, links, databases, datasets, or records, relating to one or more elements of the graph query.
  • the elements of the graph query may be individual elements, search terms, features, or other query elements representative of the natural language query.
  • the presentation component 250 returns a set of results based on the graph query.
  • the presentation component 250 may return the set of results in the graphical user interface 400 of FIG. 4 .
  • the set of results are presented in a result area 410 .
  • the result area 410 may be populated with a set of selectable interface icons 412 .
  • Each selectable interface icon may correspond to a link, dataset, node, entity or record of the knowledge graph. Selection of a selectable interface icon may direct the graphical user interface 400 to a pertinent record location associated with a specified result.
  • FIG. 5 is a flowchart of operations of the semantic parsing system 150 in performing a method 500 of converting query structures for information retrieval from graph-based data structures, according to some example embodiments. Operations of the method 500 may be performed by the semantic parsing system 150 , using components described herein.
  • the modeling component 240 segments a graph query into a set of graph query elements.
  • the graph query may be segmented into the set of graph query elements, such that each graph query element corresponds to a selectable user interface element of the set of selectable user interface elements 406 .
  • each graph query element may represent a portion of the natural language query 404 or an interpretation of at least a portion of the natural language query 404 , such as a term, entity, or relationship within the natural language query 404 .
  • the presentation component 250 In operation 520 , the presentation component 250 generates a first set of graphical interface elements 414 , 416 , and 418 corresponding to the set of graph query elements.
  • the first set of graphical interface elements 414 , 416 , and 418 may be selected as graph query elements which are stated or inferred from the natural language query 404 .
  • the presentation component 250 causes presentation of the first set of graphical interface elements within a graphical user interface.
  • the first set of graphical interface elements may be contemporaneously presented with the set of terms of the natural language query.
  • the first set of graphical interface elements 414 , 416 , and 418 may be presented within the graphical user interface 400 .
  • the modeling component 240 identifies a set of connective terms linking the set of graph query elements as an approximation of the natural language query. As shown in FIG. 4 , the set of connective terms may be inferred from the natural language query 404 without being explicitly stated or included within the natural language query. The modeling component 240 may cooperate with the semantic parsing component 230 to identify relationships between words in the natural language query 404 that indicate, suggest, or imply the connective term or set of connective terms.
  • the presentation component 250 generates a second set of graphical interface elements.
  • the second set of graphical interface elements 420 may be generated as selectable or non-selectable user interface elements.
  • the second set of graphical interface elements may correspond to the set of connective terms.
  • the second set of graphical interface elements 420 may be generated with respect to the first set of graphical interface elements 414 , 416 , and 418 .
  • the second set of graphical interface elements 420 representing connective terms, may be generated to fill in areas between the first set of graphical interface elements 414 , 416 , and 418 to generate a user readable representation of the graph query.
  • the presentation component 250 causes presentation of the second set of graphical interface elements.
  • the second set of graphical interface elements 420 may be presented contemporaneously with the first set of graphical interface elements 414 , 416 , and 418 , and the set of terms of the natural language query 404 .
  • the second set of graphical interface elements are distributed among the set of graph query elements depicted within the first set of graphical interface elements.
  • alternative interpretations or search terms may be presented within the graphical user interface 400 of FIG. 4 .
  • the semantic parsing system 150 may identify alternative search terms based on one or more of the set of terms of the natural language query.
  • the alternative search terms may be generated based on one or more of the natural language query, the intermediate semantic representation, and the graph query generated in method 300 .
  • the presentation component 250 may generate a set of alternative interface elements corresponding to the set of alternative search terms to populate a portion of the graphical user interface 400 . Once generated, the presentation component 250 may cause presentation of the set of alternative interface elements and alternative search terms.
  • the alternative interface elements and search terms may be presented contemporaneously with interface elements corresponding to the graph query element, the graph query, and the natural language query.
  • FIG. 6 is a flowchart of operations of the semantic parsing system 150 in performing a method 600 of converting query structures for information retrieval from graph-based data structures, according to some example embodiments. Operations of the method 600 may be performed by the semantic parsing system 150 , using components described herein.
  • the modeling component 240 identifies an entity within a graph query element included in the graph query.
  • the entity 702 may be identified as a term, an item, an affliction, or any other searchable aspect of a database.
  • the entity may be identified during transformation of the natural language query to the graph query, described above with respect to FIGS. 3-5 .
  • the modeling component 240 determines one or more graph query elements related to the entity.
  • the one or more graph query elements 704 may be identified in a manner similar to or the same as described above with respect to translating the natural language query to the graph query in FIG. 3 and the method 300 .
  • the presentation component 250 generates one or more interface elements 706 related to the entity.
  • the interface elements 706 represent the one or more graph query elements.
  • Each interface element may represent a distinct graph query element, such that if a plurality of graph query elements are identified a plurality of interface elements 706 are generated.
  • the modeling component 240 detects interaction with the graph query element associated with the entity.
  • the modeling component 240 may detect interaction with the graph query element 702 via a tap, touch, mouse click, or any other suitable user interaction discernable within a graphical user interface presented on a computing device.
  • the presentation component 250 causes presentation of the one or more interface elements for the one or more graph query elements relating to the entity.
  • the one or more graph query elements 704 or the interface elements 706 may be presented in a menu 708 .
  • the menu 708 may be a hovering menu, a drop down menu, a pop up window, or any other suitable selectable interface element or window.
  • the menu 708 may present additional search operations or options mirroring those described above with respect to the graphical user interface 400 of FIG. 4 .
  • the presentation component 250 cooperates with the modeling component 240 to replace the entity with a graph query element associated with the selected interface element within the graph query.
  • the entity is replaced by the selected interface element and corresponding graph query element upon detecting selection of an interface element of the one or more interface elements.
  • Semantic parsers such as the semantic parsing system 150
  • Semantic parsers are commonly evaluated using datasets in which texts are paired with their desired logical forms or denotations. Such evaluations may be effective but costly in terms of human labor.
  • Embodiments of the present semantic parsing system 150 may be evaluated via increased usability.
  • Embodiments and aspects of the present disclosure were evaluated using pairs of tasks, classified into increasing levels of difficulty as measured by the number of terms they contained and the intricacy of the semantic operations required. For each participant involved in the evaluation, one of each pair was randomly assigned as a parser task and one as a Cypher task, for a total often tasks. Random assignment was used to even out any variable difficulty not accounted for by classifications used in example embodiments of the semantic parsing system 150 .
  • the tasks took the form of short summaries like “Objects to return: providers; Restriction: specialty is cardiac surgery.” Clues contained in these summaries regarding how to formulate queries may be equally useful for English and Cypher query formulations or translations. Performance of embodiments of the semantic parsing system 150 were evaluated on the Cypher and English parts within subjects. These clues may not favor any one system. Similarly, within-subject comparisons may abstract away from participants' varying levels of expertise with Cypher graph queries.
  • Embodiments of the semantic parsing system were evaluated in the above-described manner by individuals having Cypher experience. The results of the study favored embodiments presented in the present disclosure. In the evaluation, the total time taken for the Cypher tasks was much lower using embodiments of the semantic parsing system 150 than for other search or parsing systems.
  • the disclosed semantic parsing system 150 is flexible, powerful, and easy to deploy on new, large health knowledge graphs because the central aspects of the system are defined by the graph itself. The system is under active development; we aim to provide increasingly rich access to public health data.
  • Embodiments of the semantic parsing system 150 improve usability of knowledge graph searching over graph query languages and are easier for novice users to navigate. Further, embodiments of the semantic parsing system 150 are easier to scale than pure natural language query systems.
  • the semantic parsing system 150 enables expansion and scaling across a broad range of dataset and database domains with minimal or no human intervention or annotation.
  • Components may constitute either software components (e.g., code embodied on a machine-readable medium) or hardware components.
  • a “hardware component” is a tangible unit capable of performing certain operations and may be configured or arranged in a certain physical manner.
  • one or more computer systems e.g., a standalone computer system, a client computer system, or a server computer system
  • one or more hardware components of a computer system e.g., a processor or a group of processors
  • software e.g., an application or application portion
  • a hardware component may be implemented mechanically, electronically, or any suitable combination thereof.
  • a hardware component may include dedicated circuitry or logic that is permanently configured to perform certain operations.
  • a hardware component may be a special-purpose processor, such as a Field-Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC).
  • a hardware component may also include programmable logic or circuitry that is temporarily configured by software to perform certain operations.
  • a hardware component may include software executed by a general-purpose processor or other programmable processor. Once configured by such software, hardware components become specific machines (or specific components of a machine) uniquely tailored to perform the configured functions and are no longer general-purpose processors. It will be appreciated that the decision to implement a hardware component mechanically, in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.
  • hardware component should be understood to encompass a tangible entity, be that an entity that is physically constructed, permanently configured (e.g., hardwired), or temporarily configured (e.g., programmed) to operate in a certain manner or to perform certain operations described herein.
  • “hardware-implemented component” refers to a hardware component. Considering embodiments in which hardware components are temporarily configured (e.g., programmed), each of the hardware components need not be configured or instantiated at any one instance in time. For example, where a hardware component comprises a general-purpose processor configured by software to become a special-purpose processor, the general-purpose processor may be configured as respectively different special-purpose processors (e.g., comprising different hardware components) at different times. Software accordingly configures a particular processor or processors, for example, to constitute a particular hardware component at one instance of time and to constitute a different hardware component at a different instance of time.
  • Hardware components can provide information to, and receive information from, other hardware components. Accordingly, the described hardware components may be regarded as being communicatively coupled. Where multiple hardware components exist contemporaneously, communications may be achieved through signal transmission (e.g., over appropriate circuits and buses) between or among two or more of the hardware components. In embodiments in which multiple hardware components are configured or instantiated at different times, communications between such hardware components may be achieved, for example, through the storage and retrieval of information in memory structures to which the multiple hardware components have access. For example, one hardware component may perform an operation and store the output of that operation in a memory device to which it is communicatively coupled. A further hardware component may then, at a later time, access the memory device to retrieve and process the stored output. Hardware components may also initiate communications with input or output devices, and can operate on a resource (e.g., a collection of information).
  • a resource e.g., a collection of information
  • processors may be temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors may constitute processor-implemented components that operate to perform one or more operations or functions described herein.
  • processor-implemented component refers to a hardware component implemented using one or more processors.
  • the methods described herein may be at least partially processor-implemented, with a particular processor or processors being an example of hardware.
  • a particular processor or processors being an example of hardware.
  • the operations of a method may be performed by one or more processors or processor-implemented components.
  • the one or more processors may also operate to support performance of the relevant operations in a “cloud computing” environment or as a “software as a service” (SaaS).
  • SaaS software as a service
  • at least some of the operations may be performed by a group of computers (as examples of machines including processors), with these operations being accessible via a network (e.g., the Internet) and via one or more appropriate interfaces (e.g., an API).
  • processors may be distributed among the processors, not only residing within a single machine, but deployed across a number of machines.
  • the processors or processor-implemented components may be located in a single geographic location (e.g., within a home environment, an office environment, or a server farm). In other example embodiments, the processors or processor-implemented components may be distributed across a number of geographic locations.
  • FIGS. 2-6 are implemented in some embodiments in the context of a machine and an associated software architecture.
  • the components, methods, applications and so forth described above are implemented in the context of a plurality of machines, distributed across and communicating via a network, and one or more associated software architectures.
  • the sections below describe representative software architecture(s) and machine (e.g., hardware) architecture that are suitable for use with the disclosed embodiments.
  • Software architectures are used in conjunction with hardware architectures to create devices and machines tailored to particular purposes. For example, a particular hardware architecture coupled with a particular software architecture will create a mobile device, such as a mobile phone, tablet device, or so forth. A slightly different hardware and software architecture may yield a smart device for use in the “internet of things,” while yet another combination produces a server computer for use within a cloud computing architecture. Not all combinations of such software and hardware architectures are presented here as those of skill in the art can readily understand how to implement the present embodiments in different contexts from the disclosure contained herein.
  • FIG. 8 is a block diagram 800 illustrating a representative software architecture 802 , which may be used in conjunction with various hardware architectures herein described.
  • FIG. 8 is merely a non-limiting example of a software architecture and it will be appreciated that many other architectures may be implemented to facilitate the functionality described herein.
  • the software architecture 802 may be executing on hardware such as machine 900 of FIG. 9 that includes, among other things, processors 910 , memory 930 , and Input/Output (I/O) components 950 .
  • a representative hardware layer 804 is illustrated and can represent, for example, the machine 800 of FIG. 8 .
  • the representative hardware layer 804 comprises one or more processing units 806 having associated executable instructions 808 .
  • Executable instructions 808 represent the executable instructions of the software architecture 802 , including implementation of the methods, components, and so forth of FIGS. 2-7 .
  • Hardware layer 804 also includes memory and/or storage components 810 , which also have executable instructions 808 .
  • Hardware layer 804 may also comprise other hardware as indicated by 812 , which represents any other hardware of the hardware layer 804 , such as the other hardware illustrated as part of machine 900 .
  • the software 802 may be conceptualized as a stack of layers where each layer provides particular functionality.
  • the software 802 may include layers such as an operating system 814 , libraries 816 , frameworks/middleware 818 , applications 820 , and presentation layer 822 .
  • the applications 820 and/or other components within the layers may invoke API calls 824 through the software stack and receive a response, returned values, and so forth, illustrated as messages 826 in response to the API calls 824 .
  • the layers illustrated are representative in nature and not all software architectures have all layers. For example, some mobile or special purpose operating systems may not provide a frameworks/middleware layer 818 , while others may provide such a layer. Other software architectures may include additional or different layers.
  • the operating system 814 may manage hardware resources and provide common services.
  • the operating system 814 may include, for example, a kernel 828 , services 830 , and drivers 832 .
  • the kernel 828 may act as an abstraction layer between the hardware and the other software layers.
  • the kernel 828 may be responsible for memory management, processor management (e.g., scheduling), component management, networking, security settings, and so on.
  • the services 830 may provide other common services for the other software layers.
  • the drivers 832 may be responsible for controlling or interfacing with the underlying hardware.
  • the drivers 832 may include display drivers, camera drivers, Bluetooth® drivers, flash memory drivers, serial communication drivers (e.g., Universal Serial Bus (USB) drivers), Wi-Fi® drivers, audio drivers, power management drivers, and so forth depending on the hardware configuration.
  • USB Universal Serial Bus
  • the libraries 816 may provide a common infrastructure that may be utilized by the applications 820 and/or other components and/or layers.
  • the libraries 816 typically provide functionality that allows other software components to perform tasks in an easier fashion than to interface directly with the underlying operating system 814 functionality (e.g., kernel 828 , services 830 and/or drivers 832 ).
  • the libraries 816 may include system 834 libraries (e.g., C standard library) that may provide functions such as memory allocation functions, string manipulation functions, mathematic functions, and the like.
  • libraries 816 may include API libraries 836 such as media libraries (e.g., libraries to support presentation and manipulation of various media format such as Moving Pictures Experts Group 4 (MPEG4), H.264, MP3, Advanced Audio Coding (AAC), Adaptive Multi-Rate (AMR), Joint Photographic Experts Group (JPEG), Portable Network Graphics (PNG)), graphics libraries (e.g., an OpenGL framework that may be used to render two dimensions and three dimensions in a graphic content on a display), database libraries (e.g., SQLite that may provide various relational database functions), web libraries (e.g., WebKit that may provide web browsing functionality), and the like.
  • the libraries 816 may also include a wide variety of other libraries 838 to provide many other APIs to the applications 820 and other software components/modules.
  • the frameworks 818 may provide a higher-level common infrastructure that may be utilized by the applications 820 and/or other software components/modules.
  • the frameworks 818 may provide various graphical user interface functions, high-level resource management, high-level location services, and so forth.
  • the frameworks 818 may provide a broad spectrum of other APIs that may be utilized by the applications 820 and/or other software components/modules, some of which may be specific to a particular operating system or platform.
  • predictive modeling components 819 e.g., one or more components of the semantic parsing systems 150
  • At least a portion of the database component 220 and the presentation component 250 may be implemented in the middleware/frameworks 818 .
  • portions of one or more of the receiver component 210 , the database component 220 , the semantic parsing component 230 , the modeling component 240 , and the presentation component 250 may be implemented in the middleware/frameworks 818 .
  • the applications 820 include built-in applications 840 , third party applications 842 , and/or predictive modeling components 843 (e.g., user facing portions of one or more of the components of the predictive modeling system 150 ).
  • built-in applications 840 may include, but are not limited to, a contacts application, a browser application, a book reader application, a location application, a media application, a messaging application, and/or a game application.
  • Third party applications 842 may include any of the built-in applications as well as a broad assortment of other applications.
  • the third-party application 842 may be mobile software running on a mobile operating system such as iOSTM, AndroidTM, Windows® Phone, or other mobile operating systems.
  • the third-party application 842 may invoke the API calls 824 provided by the mobile operating system such as operating system 814 to facilitate functionality described herein.
  • the user facing portions of the predictive modeling components 843 may include one or more components or portions of components described with respect to FIG. 2 .
  • portions of the receiver component 210 , the database component 220 , the semantic parsing component 230 , the modeling component 240 , and the presentation component 250 , associated with user interface elements may be implemented in the form of an application.
  • the applications 820 may utilize built in operating system functions (e.g., kernel 828 , services 830 and/or drivers 832 ), libraries (e.g., system 834 , APIs 836 , and other libraries 838 ), frameworks/middleware 818 to create user interfaces to interact with users of the system. Alternatively, or additionally, in some systems interactions with a user may occur through a presentation layer, such as presentation layer 844 . In these systems, the application/component “logic” can be separated from the aspects of the application/component that interact with a user.
  • virtual machine 848 Some software architectures utilize virtual machines. In the example of FIG. 8 , this is illustrated by virtual machine 848 .
  • a virtual machine creates a software environment where applications/components can execute as if they were executing on a hardware machine (such as the machine of FIG. 9 , for example).
  • a virtual machine is hosted by a host operating system (operating system 814 in FIG. 8 ) and typically, although not always, has a virtual machine monitor 846 , which manages the operation of the virtual machine as well as the interface with the host operating system (i.e., operating system 814 ).
  • a software architecture executes within the virtual machine such as an operating system 850 , libraries 852 , frameworks/middleware 854 , applications 856 and/or presentation layer 858 . These layers of software architecture executing within the virtual machine 848 can be the same as corresponding layers previously described or may be different.
  • FIG. 9 is a block diagram illustrating components of a machine 900 , according to some example embodiments, able to read instructions (e.g., processor executable instructions) from a machine-readable medium (e.g., a non-transitory machine-readable storage medium) and perform any one or more of the methodologies discussed herein.
  • FIG. 9 shows a diagrammatic representation of the machine 900 in the example form of a computer system, within which instructions 916 (e.g., software, a program, an application, an applet, an app, or other executable code) for causing the machine 900 to perform any one or more of the methodologies discussed herein may be executed.
  • the instructions may cause the machine to execute methods described herein.
  • the instructions may implement the receiver component 210 , the database component 220 , the semantic parsing component 230 , the modeling component 240 , and the presentation component 250 of FIG. 2 , and so forth.
  • the instructions transform the general, non-programmed machine into a particular machine programmed to carry out the described and illustrated functions in the manner described.
  • the machine 900 operates as a standalone device or may be coupled (e.g., networked) to other machines in a networked system.
  • the machine 900 may operate in the capacity of a server machine or a client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment.
  • the machine 900 may comprise, but not be limited to, a server computer, a client computer, a personal computer (PC), a tablet computer, a laptop computer, a netbook, a set-top box, an entertainment media system, a web appliance, a network router, a network switch, a network bridge, or any machine capable of executing the instructions 916 , sequentially or otherwise, that specify actions to be taken by machine 900 .
  • a server computer a client computer
  • PC personal computer
  • tablet computer a laptop computer
  • netbook a set-top box
  • an entertainment media system a web appliance
  • a network router a network switch
  • a network bridge or any machine capable of executing the instructions 916 , sequentially or otherwise, that specify actions to be taken by machine 900 .
  • one or more machines may implement at least a portion of the components described above.
  • the one or more machines interacting with the machine 900 may comprise, but not be limited to a PDA, an entertainment media system, a cellular telephone, a smart phone, a mobile device, a wearable device (e.g., a smart watch), a smart home device (e.g., a smart appliance), and other smart devices.
  • a wearable device e.g., a smart watch
  • a smart home device e.g., a smart appliance
  • machine shall also be taken to include a collection of machines 900 that individually or jointly execute the instructions 916 to perform any one or more of the methodologies discussed herein.
  • the machine 900 may include processors 910 , memory 930 , and I/O components 950 , which may be configured to communicate with each other such as via a bus 902 .
  • the processors 910 e.g., a Central Processing Unit (CPU), a Reduced Instruction Set Computing (RISC) processor, a Complex Instruction Set Computing (CISC) processor, a Graphics Processing Unit (GPU), a Digital Signal Processor (DSP), an ASIC, a Radio-Frequency Integrated Circuit (RFIC), another processor, or any suitable combination thereof
  • the processors 910 may include, for example, processor 912 and processor 914 that may execute instructions 916 .
  • processor is intended to include multi-core processor that may comprise two or more independent processors (sometimes referred to as “cores”) that may execute instructions contemporaneously.
  • FIG. 9 shows multiple processors, the machine 900 may include a single processor with a single core, a single processor with multiple cores (e.g., a multi-core process), multiple processors with a single core, multiple processors with multiples cores, or any combination thereof.
  • the memory/storage 930 may include a memory 932 , such as a main memory, or other memory storage, and a storage unit 936 , both accessible to the processors 910 such as via the bus 902 .
  • the storage unit 936 and memory 932 store the instructions 916 embodying any one or more of the methodologies or functions described herein.
  • the instructions 916 may also reside, completely or partially, within the memory 932 , within the storage unit 936 , within at least one of the processors 910 (e.g., within the processor's cache memory), or any suitable combination thereof, during execution thereof by the machine 900 .
  • the memory 932 , the storage unit 936 , and the memory of processors 910 are examples of machine-readable media.
  • machine-readable medium means a device able to store instructions and data temporarily or permanently and may include, but is not be limited to, random-access memory (RAM), read-only memory (ROM), buffer memory, flash memory, optical media, magnetic media, cache memory, other types of storage (e.g., Erasable Programmable Read-Only Memory (EEPROM)) and/or any suitable combination thereof.
  • RAM random-access memory
  • ROM read-only memory
  • buffer memory flash memory
  • optical media magnetic media
  • cache memory other types of storage
  • EEPROM Erasable Programmable Read-Only Memory
  • machine-readable medium shall also be taken to include any medium, or combination of multiple media, that is capable of storing instructions (e.g., instructions 916 ) for execution by a machine (e.g., machine 900 ), such that the instructions, when executed by one or more processors of the machine 900 (e.g., processors 910 ), cause the machine 900 to perform any one or more of the methodologies described herein.
  • a “machine-readable medium” refers to a single storage apparatus or device, as well as “cloud-based” storage systems or storage networks that include multiple storage apparatus or devices.
  • the term “machine-readable medium” excludes signals per se.
  • the I/O components 950 may include a wide variety of components to receive input, provide output, produce output, transmit information, exchange information, capture measurements, and so on.
  • the specific I/O components 950 that are included in a particular machine will depend on the type of machine. For example, portable machines such as mobile phones will likely include a touch input device or other such input mechanisms, while a headless server machine will likely not include such a touch input device. It will be appreciated that the I/O components 950 may include many other components that are not shown in FIG. 9 .
  • the I/O components 950 are grouped according to functionality merely for simplifying the following discussion and the grouping is in no way limiting. In various example embodiments, the I/O components 950 may include output components 952 and input components 954 .
  • the output components 952 may include visual components (e.g., a display such as a plasma display panel (PDP), a light emitting diode (LED) display, a liquid crystal display (LCD), a projector, or a cathode ray tube (CRT)), acoustic components (e.g., speakers), haptic components (e.g., a vibratory motor, resistance mechanisms), other signal generators, and so forth.
  • a display such as a plasma display panel (PDP), a light emitting diode (LED) display, a liquid crystal display (LCD), a projector, or a cathode ray tube (CRT)
  • acoustic components e.g., speakers
  • haptic components e.g., a vibratory motor, resistance mechanisms
  • the input components 954 may include alphanumeric input components (e.g., a keyboard, a touch screen configured to receive alphanumeric input, a photo-optical keyboard, or other alphanumeric input components), point based input components (e.g., a mouse, a touchpad, a trackball, a joystick, a motion sensor, or other pointing instrument), tactile input components (e.g., a physical button, a touch screen that provides location and/or force of touches or touch gestures, or other tactile input components), audio input components (e.g., a microphone), and the like.
  • alphanumeric input components e.g., a keyboard, a touch screen configured to receive alphanumeric input, a photo-optical keyboard, or other alphanumeric input components
  • point based input components e.g., a mouse, a touchpad, a trackball, a joystick, a motion sensor, or other pointing instrument
  • tactile input components e.g., a physical button,
  • the I/O components 950 may include biometric components 956 , motion components 957 , environmental components 960 , or position components 962 among a wide array of other components.
  • the biometric components 956 may include components to detect expressions (e.g., hand expressions, facial expressions, vocal expressions, body gestures, or eye tracking), measure biosignals (e.g., blood pressure, heart rate, body temperature, perspiration, or brain waves), identify a person (e.g., voice identification, retinal identification, facial identification, fingerprint identification, or electroencephalogram based identification), and the like.
  • the motion components 958 may include acceleration sensor components (e.g., accelerometer), gravitation sensor components, rotation sensor components (e.g., gyroscope), and so forth.
  • the environmental components 960 may include, for example, illumination sensor components (e.g., photometer), temperature sensor components (e.g., one or more thermometers that detect ambient temperature), humidity sensor components, pressure sensor components (e.g., barometer), acoustic sensor components (e.g., one or more microphones that detect background noise), proximity sensor components (e.g., infrared sensors that detect nearby objects), gas sensors (e.g., gas detect sensors to detection concentrations of hazardous gases for safety or to measure pollutants in the atmosphere), or other components that may provide indications, measurements, or signals corresponding to a surrounding physical environment.
  • illumination sensor components e.g., photometer
  • temperature sensor components e.g., one or more thermometers that detect ambient temperature
  • humidity sensor components e.g., pressure sensor components (e.g., barometer)
  • the position components 962 may include location sensor components (e.g., a GPS receiver component), altitude sensor components (e.g., altimeters or barometers that detect air pressure from which altitude may be derived), orientation sensor components (e.g., magnetometers), and the like.
  • location sensor components e.g., a GPS receiver component
  • altitude sensor components e.g., altimeters or barometers that detect air pressure from which altitude may be derived
  • orientation sensor components e.g., magnetometers
  • the I/O components 950 may include communication components 964 operable to couple the machine 900 to a network 980 or devices 970 via coupling 982 and coupling 972 , respectively.
  • the communication components 964 may include a network interface component or other suitable device to interface with the network 980 .
  • communication components 964 may include wired communication components, wireless communication components, cellular communication components, Near Field Communication (NFC) components, Bluetooth® components (e.g., Bluetooth® Low Energy), Wi-Fi® components, and other communication components to provide communication via other modalities.
  • the devices 970 may be another machine or any of a wide variety of peripheral devices (e.g., a peripheral device coupled via a USB).
  • the communication components 964 may detect identifiers or include components operable to detect identifiers.
  • the communication components 964 may include Radio Frequency Identification (RFID) tag reader components, NFC smart tag detection components, optical reader components (e.g., an optical sensor to detect one-dimensional bar codes such as Universal Product Code (UPC) bar code, multi-dimensional bar codes such as Quick Response (QR) code, Aztec code, Data Matrix, Dataglyph, MaxiCode, PDF417, Ultra Code, UCC RSS-2D bar code, and other optical codes), or acoustic detection components (e.g., microphones to identify tagged audio signals).
  • RFID Radio Frequency Identification
  • NFC smart tag detection components e.g., an optical sensor to detect one-dimensional bar codes such as Universal Product Code (UPC) bar code, multi-dimensional bar codes such as Quick Response (QR) code, Aztec code, Data Matrix, Dataglyph, MaxiCode, PDF417, Ultra Code, UCC RSS-2D bar code, and other optical codes
  • RFID Radio Fre
  • IP Internet Protocol
  • Wi-Fi® Wireless Fidelity
  • one or more portions of the network 980 may be an ad hoc network, an intranet, an extranet, a VPN, a LAN, a WLAN, a WAN, a WWAN, a MAN, the Internet, a portion of the Internet, a portion of the PSTN, a plain old telephone service (POTS) network, a cellular telephone network, a wireless network, a Wi-Fi® network, another type of network, or a combination of two or more such networks.
  • POTS plain old telephone service
  • the network 980 or a portion of the network 980 may include a wireless or cellular network and the coupling 982 may be a Code Division Multiple Access (CDMA) connection, a Global System for Mobile communications (GSM) connection, or other type of cellular or wireless coupling.
  • the coupling 982 may implement any of a variety of types of data transfer technology, such as Single Carrier Radio Transmission Technology (1 ⁇ RTT), Evolution-Data Optimized (EVDO) technology, General Packet Radio Service (GPRS) technology, Enhanced Data rates for GSM Evolution (EDGE) technology, third Generation Partnership Project (3GPP) including 3G, fourth generation wireless (4G) networks.
  • RTT Single Carrier Radio Transmission Technology
  • EVDO Evolution-Data Optimized
  • GPRS General Packet Radio Service
  • EDGE Enhanced Data rates for GSM Evolution
  • 3GPP Third Generation Partnership Project
  • 4G fourth generation wireless
  • UMTS Universal Mobile Telecommunications System
  • HSPA High Speed Packet Access
  • WiMAX Worldwide Interoperability for Microwave Access
  • LTE Long Term Evolution
  • the instructions 916 may be transmitted or received over the network 980 using a transmission medium via a network interface device (e.g., a network interface component included in the communication components 964 ) and utilizing any one of a number of well-known transfer protocols (e.g., hypertext transfer protocol (HTTP)). Similarly, the instructions 916 may be transmitted or received using a transmission medium via the coupling 972 (e.g., a peer-to-peer coupling) to devices 970 .
  • the term “transmission medium” shall be taken to include any intangible medium that is capable of storing, encoding, or carrying instructions 916 for execution by the machine 900 , and includes digital or analog communications signals or other intangible medium to facilitate communication of such software.
  • inventive subject matter has been described with reference to specific example embodiments, various modifications and changes may be made to these embodiments without departing from the broader scope of embodiments of the present disclosure.
  • inventive subject matter may be referred to herein, individually or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any single disclosure or inventive concept if more than one is, in fact, disclosed.
  • the term “or” may be construed in either an inclusive or exclusive sense. Moreover, plural instances may be provided for resources, operations, or structures described herein as a single instance. Additionally, boundaries between various resources, operations, components, engines, and data stores are somewhat arbitrary, and particular operations are illustrated in a context of specific illustrative configurations. Other allocations of functionality are envisioned and may fall within a scope of various embodiments of the present disclosure. In general, structures and functionality presented as separate resources in the example configurations may be implemented as a combined structure or resource. Similarly, structures and functionality presented as a single resource may be implemented as separate resources. These and other variations, modifications, additions, and improvements fall within a scope of embodiments of the present disclosure as represented by the appended claims. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Human Computer Interaction (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Software Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Machine Translation (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

In various example embodiments, a system and methods are presented for converting query structures for information retrieval from graph-based data structures. The systems and methods receive a natural language query including a set of terms and generate an intermediate semantic relationship of the set of terms of the natural language query. The systems and methods generate a graph query including graph terms corresponding to the set of terms of the natural language query defined by a graph database. The systems and methods search one or more datasets associated with the graph database using the graph query and return a set of results based on the graph query.

Description

    CLAIM FOR PRIORITY
  • This application claims the benefit of priority to U.S. Provisional Application No. 62/414,614, filed Oct. 28, 2016, which is hereby incorporated by reference in its entirety.
  • TECHNICAL FIELD
  • The subject matter disclosed herein generally relates to the technical field of special-purpose machines for dataset clustering and search engines that facilitate data set navigation and database queries, including software-configured computerized variants of such special-purpose machines and improvements to such variants, and to the technologies by which such special-purpose machines become improved compared to other special-purpose machines that facilitate generation of search results and relational links between discrete data sets using a canonical semantic layer.
  • BACKGROUND
  • Conventionally, data systems organize data into discrete sets and using standardized identifiers, categories, and characteristics. This organization enables easier and faster searching by organizing data published or consolidated by a single entity. Data systems searching differing data sets, published across multiple entities, encounter difficulties in correlating organizational structures. Further difficulties are encountered where data sets are provided in differing formats. While conventional data systems may be able to retrieve distinct documents or elements from multiple data sets, these data systems often provide the documents with no context or relation to other documents presented within the same or similar search results. As a result, conventional data systems attempting to draw inferences or determine links between data sets often present results with unacceptable degrees of uncertainty.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • Various ones of the appended drawings merely illustrate example embodiments of the present disclosure and cannot be considered as limiting its scope.
  • FIG. 1 is a block diagram illustrating a networked system, according to some example embodiments.
  • FIG. 2 is a block diagram of an example semantic parsing system, according to various embodiments.
  • FIG. 3 is a flowchart illustrating an example method of converting query structures for information retrieval from graph-based data structures using the semantic parsing system, according to various embodiments.
  • FIG. 4 is an example graphical user interface of the semantic parsing system, according to various embodiments.
  • FIG. 5 is a flowchart illustrating an example method of converting query structures for information retrieval from graph-based data structures using the semantic parsing system, according to various embodiments.
  • FIG. 6 is a flowchart illustrating an example method of converting query structures for information retrieval from graph-based data structures using the semantic parsing system, according to various embodiments.
  • FIG. 7 is an example graphical user interface of the semantic parsing system, according to various embodiments
  • FIG. 8 is a block diagram illustrating an example of a software architecture that may be installed on a machine, according to some example embodiments.
  • FIG. 9 illustrates a diagrammatic representation of a machine in the form of a computer system within which a set of instructions may be executed for causing the machine to perform any one or more of the methodologies discussed herein, according to an example embodiment.
  • The headings provided herein are merely for convenience and do not necessarily affect the scope or meaning of the terms used.
  • DETAILED DESCRIPTION
  • The description that follows includes systems, methods, techniques, instruction sequences, and computing machine program products that embody illustrative embodiments of the disclosure. In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide an understanding of various embodiments of the inventive subject matter. It will be evident, however, to those skilled in the art, that embodiments of the inventive subject matter may be practiced without these specific details. In general, well-known instruction instances, protocols, structures, and techniques are not necessarily shown in detail.
  • Systems and method described herein define a semantic parsing system or semantic parsing engine for dataset graphs method for large scale knowledge graphs (e.g., health knowledge graphs) that is graph-backed in the sense that its grammar and semantic concepts are derived automatically from the graph schema. The methods and systems also enable a superior search experience compared to raw database queries. Although described with respect to healthcare information, technologies, data sets, and semantic relationships, it should be understood that the systems and methods described herein are able to generate a connected knowledge graph by unifying any suitable data set, information, set of publications, or set of documents using semantic layers organizing or underlying the data sources and using machine learning techniques to generate models to incorporate new edges and relationships into the canonical layer.
  • An enormous amount of datasets (e.g., such as public health released by governments like the United States, industries, or individual entities) have been made available for public use over the last few years. Taken together, these datasets have the potential to provide a comprehensive picture of the various industry domains. In the example of the healthcare domain: drugs, procedures, diseases, providers, and so forth. Only patient-level data is missing, because of privacy considerations, but census and survey data still support analyses based on fine-grained demographics. These releases outline not only the core ontology of the healthcare space (e.g., doctors, hospitals, manufacturers, drugs, devices, procedures, and so on), but also support serious inquiry into the dynamics of the space, including prescribing behaviors for providers, recalls and adverse events, hospital quality evaluations, population-level psychological and social characteristics, and so forth. Where released datasets involve other industries, similar ontological outlines may be modeled and dynamics of industry practice, governmental regulation, and users (e.g., customer, practitioner, or third-party entities) may be similarly investigated and modeled. Further, modeling of industry dynamics and ontologies supports or enables drawing of inferences and links using modeled representations of the datasets.
  • The systems and methods disclosed herein present an approach to developing semantic parsers over large knowledge graphs, such as large health knowledge graphs (HKGs) derived from these public datasets. These semantic parsers are graph-backed, such that the schema for the target graph is used to define the core space of entities, concepts, and relations; it provides the initial seed sets for defining the semantic lexicon; and it helps delimit the space of rules for syntactic and semantic combination. Thus, very large and complex grammars are easily instantiated, addressing one of the major bottlenecks for semantic parsing at scale.
  • The result of the systems and methods disclosed herein is expanded access to public health information, so the semantic parser, in some example embodiments, is natural language search into health knowledge graphs. Natural language searching may differ from a database query language, which can be cumbersome even for experts and which puts most information out of reach for regular users. The promise of natural language search is that it removes these obstacles. To assess progress on this accessibility issue, the present disclosure includes a usability study comparing the semantic parsing system with issuing raw graph query language statements. All participants were experts in the graph query language. As a group, they completed tasks faster and in fewer attempts with our system than with raw queries, and they preferred our system for everything except very complex queries.
  • With reference to FIG. 1, an example embodiment of a high-level client-server-based network architecture 100 is shown. A networked system 102, in the example forms of a network-based predictive modeling system, provides server-side functionality via a network 104 (e.g., the Internet or wide area network (WAN)) to one or more client devices 110. FIG. 1 illustrates, for example, a web client 112 (e.g., a browser, such as the INTERNET EXPLORER® browser developed by Microsoft® Corporation of Redmond. Washington State), an application 114, and a programmatic client 116 executing on client device 110.
  • The client device 110 may comprise, but is not limited to, mobile phones, desktop computers, laptops, personal digital assistants (PDAs), smart phones, tablets, ultra books, netbooks, laptops, multi-processor systems, microprocessor-based or programmable consumer electronics, game consoles, set-top boxes, or any other communication device that a user may utilize to access the networked system 102. In some embodiments, the client device 110 may comprise a display component (not shown) to display information (e.g., in the form of user interfaces). In further embodiments, the client device 110 may comprise one or more of a touch screens, accelerometers, gyroscopes, cameras, microphones, global positioning system (GPS) devices, and so forth.
  • The client device 110 may be a device of a user that is used to perform a transaction involving object data and predictive models within the networked system 102. One or more users 106 may be a person, a machine, or other means of interacting with client device 110. In embodiments, the user 106 is not part of the network architecture 100, but may interact with the network architecture 100 via client device 110 or another means. For example, one or more portions of network 104 may be an ad hoc network, an intranet, an extranet, a virtual private network (VPN), a local area network (LAN), a wireless LAN (WLAN), a WAN, a wireless WAN (WWAN), a metropolitan area network (MAN), a portion of the Internet, a portion of the Public Switched Telephone Network (PSTN), a cellular telephone network, a wireless network, a WiFi network, a WiMax network, another type of network, or a combination of two or more such networks. Each of the client device 110 may include one or more applications (also referred to as “apps”) such as, but not limited to, a web browser, messaging application, electronic mail (email) application, and the like.
  • One or more users 106 may be a person, a machine, or other means of interacting with the client device 110. In example embodiments, the user 106 is not part of the network architecture 100, but may interact with the network architecture 100 via the client device 110 or other means. For instance, the user provides input (e.g., touch screen input or alphanumeric input) to the client device 110 and the input is communicated to the networked system 102 via the network 104. In this instance, the networked system 102, in response to receiving the input from the user, communicates information to the client device 110 via the network 104 to be presented to the user. In this way, the user can interact with the networked system 102 using the client device 110.
  • An application program interface (API) server 120 and a web server 122 are coupled to, and provide programmatic and web interfaces respectively to, one or more application servers 140. The application servers 140 may host one or more publication systems 142 and a semantic parsing systems 150, each of which may comprise one or more components or applications and each of which may be embodied as hardware, software, firmware, or any combination thereof. The application servers 140 are, in turn, shown to be coupled to one or more database servers 124 that facilitate access to one or more information storage repositories or database(s) 126. In an example embodiment, the databases 126 are storage devices that store information to be posted (e.g., publications or listings) to the publication system 142. The databases 126 may also store object data, historical data, and predictive modeling data in accordance with example embodiments.
  • Additionally, a third-party application 132, executing on third party server(s) 130, is shown as having programmatic access to the networked system 102 via the programmatic interface provided by the API server 120. For example, the third-party application 132, utilizing information retrieved from the networked system 102, supports one or more features or functions on a website hosted by the third party.
  • The publication system 142 may provide a number of publication, archival, and data storage functions and services to users 106 that access the networked system 102. For example, the publication system 142 may gather, publish, and store object data, historical data for one or more objects, sales data for one or more objects, revenue data for one or more objects, release data for one or more objects, competitor data for one or more objects, publicly distributed datasets for industries, datasets for users or practitioners associated with identified industries, census and other demographic data informing industry datasets, and taxonomy data sets comprising ontological descriptions of industry datasets. The publication system 142 may publish the received or accessed datasets or may provide a consolidated database of the received or accessed datasets to an internal database or publicly available database to enable generation of predictive models and dataset network models based on the datasets. In some embodiments, the publication system 142 accesses one or more third party servers or databases (e.g., the third-party server 130) to retrieve, modify, and provision the object data within the database 126.
  • The semantic parsing systems 150 may provide functionality operable to perform various dataset network model generation and predictive model generation and manipulation functions, as well as functions for generating graphical representations of datasets, dataset network models, and predictive models. For example, the semantic parsing systems 150 accesses datasets from the databases 126, the third-party servers 130, the publication system 142, the client device 110, and other sources. In some example embodiments, the semantic parsing systems 150 analyzes portions of the sets of object data to generate dataset network models and predictive models interpreting, drawing inferences from, and supplying search and result retrieval functionality for the accessed datasets. In some example embodiments, the semantic parsing systems 150 communicates with the publication systems 142 to access the datasets and transmit queries received by the semantic parsing systems 150 to the publication system 142. In an alternative embodiment, the semantic parsing systems 150 may be a part of the publication system 142.
  • Further, while the client-server-based network architecture 100 shown in FIG. 1 employs a client-server architecture, the present inventive subject matter is of course not limited to such an architecture, and could equally well find application in a distributed, or peer-to-peer, architecture system, for example. The various publication system 142 and semantic parsing systems 150 could also be implemented as standalone software programs, which do not necessarily have networking capabilities.
  • The web client 112 may access the various publication and dataset network modeling systems 142 and 150 via the web interface supported by the web server 122. Similarly, the programmatic client 116 accesses the various services and functions provided by the publication and dataset network modeling systems 142 and 150 via the programmatic interface provided by the API server 120.
  • Additionally, a third-party application(s) 128, executing on a third-party server(s) 130, is shown as having programmatic access to the networked system 102 via the programmatic interface provided by the API server 114. For example, the third-party application 128, utilizing information retrieved from the networked system 102, may support one or more features or functions on a website hosted by the third party. The third-party website may, for example, provide one or more promotional, marketplace, data repository, company interaction, or object tracking functions that are supported by the relevant applications of the networked system 102.
  • FIG. 2 is a block diagram illustrating components of the semantic parsing systems 150, according to some example embodiments. The semantic parsing systems 150 is shown as including a receiver component 210, a database component 220, a semantic parsing component 230, a modeling component 240, and a presentation component 250 all configured to communicate with one another (e.g., via a bus, shared memory, or a switch). Any one or more of the components described herein may be implemented using hardware (e.g., one or more processors of a machine) or a combination of hardware and software. For example, any component described herein may configure a processor (e.g., among one or more processors of a machine) to perform operations for which that component is designed. Moreover, any two or more of these components may be combined into a single component, and the functions described herein for a single component may be subdivided among multiple components. Furthermore, according to various example embodiments, components described herein as being implemented within a single machine, database(s) 126, or device (e.g., client device 110) may be distributed across multiple machines, database(s) 126, or devices.
  • In FIG. 3, is a flowchart of operations of the semantic parsing system 150 in performing a method 300 of converting query structures for information retrieval from graph-based data structures using a semantic parsing system, according to some example embodiments. Operations of the method 300 may be performed by the semantic parsing system 150, using components described herein.
  • In operation 310, the receiver component 210 receives a natural language query. The natural language query may comprise a set of terms. The natural language query may be transmitted to the semantic parsing system 150 to perform a search on one or more databases or datasets connected together in a knowledge graph. The natural language query may include terms generated by a user associated with the query, such as by text entry. As shown in FIG. 4, the user may initially be presented with a text entry field 402 within a graphical user interface 400. The text entry field 402 may be configured to receive data entered by a user. The natural language query 404 may be displayed within the text entry field 402 upon entry by the user.
  • The knowledge graph may be comprised of a plurality of subgraphs connected together. The subgraphs may initially be isolated from one another, but connected by forming edges extending between related nodes of the isolated subgraphs in order to generate the knowledge graph. For example, the knowledge graph may be formed from public health datasets. The public health datasets under consideration may not be released by a single entity using a consistent set of identifiers. Rather, each dataset presents a partial, potentially biased view of the world, the union of all the information in them is likely to be inconsistent, and establishing even simple links between entities often must be cast as a model-based inference under uncertainty.
  • In some embodiments, the knowledge graph is formed from the distinct datasets in a manner producing a single connected graph with high confidence. For example, public datasets may be assembled into a connected graph, united thematically around common or related subjects, entities, or information. An example of suitable public datasets may include datasets related to physicians and prescribing behavior. Example public datasets may include, but are not limited to, National Provider Identifier, a registry of healthcare providers; CMS Physician Compare, data on physicians and their practices; CMS Open Payments Research, research support by manufacturers; Healthcare Taxonomy, three-level classification of medical specialties; CMS Prescriptions, information on prescriptions written under Medicare Part D; and FDA Drug Labels, information relating to drugs and their associated and regulated metadata. As described in more detail below, the natural language queries, seeking to surface information from the knowledge graph, may be formulated to take advantage of the structure of the knowledge graph.
  • Nodes and edges within the knowledge graph may be associated with types. Each type of node or edge may be associated with numerous attributes. For example, some edges may represent identity-relation edges and may be added based on identifiers, heuristic methods, and model-based inferences, with the direction chosen arbitrarily. NPI identities connect NPI, CMS Physician Compare, and CMS Prescriptions via providers. Taxonomy codes connect the NPI with the Healthcare Taxonomy. Brand and generic names connect CMS Prescriptions to FDA Drug Labels via drugs. The CMS Open Payments Research dataset, unlike CMS Prescriptions, may not contain NPI identifications, so the knowledge graph or models used to traverse the knowledge graph may be trained using a log-linear classifier and using a Dedupe package. Such training methodology may match nodes or attributes, characteristics, or metadata for nodes with high confidence. The resulting graph may be instantiated in Neo4j. In some instances, the knowledge graph may comprise a plurality of nodes and edges, each numbering in the millions.
  • In operation 320, the semantic parsing component 230 generates an intermediate semantic representation of the set of terms of the natural language query. The intermediate semantic representation may be a logical form representation. The semantic parsing component 230 may automatically convert the natural language query to the logical form representation upon receipt of the natural language query from the text entry field 402 of the graphical user interface 400 depicted in FIG. 4. In some instances, the semantic parsing component 230 includes PYTHON® code implemented at a webserver serving the graphical user interface 400 to a computing device of a user. The semantic parsing component 230 may be an in-memory parser. In some embodiments, the semantic parsing component 230 and the modeling component 240 form a single component handling translation of the natural language query to a graph query, described below.
  • In some embodiments, the semantic parsing component 230 comprises a graph-backed semantic parser. The semantic parsing component 230 may configure, modify, or translate the natural language query through one or more operations to navigate around the challenges of distinct datasets incorporated into a single knowledge graph and resulting from inconsistencies among the distinct datasets. The knowledge graph may be determined by the structure of the underlying databases. The edges connecting discrete subgraphs may be added to connect these isolated subgraphs based on related attributes of individual nodes within the connected subgraphs.
  • In some embodiments, the intermediate semantic representation is generated using one or more operations or sub-operations. For example, the semantic parsing component 230 may parse the set of terms of the natural language query to identify types of terms included in the natural language query. The semantic parsing component 230 may identify types such as entities, actions, comparisons, nouns, verbs, adjectives, adverbs, and other suitable types. The semantic parsing component 230 may then identify one or more relationships between the set of terms. The relationships may be based on proximity of the terms, syntactic or grammatical interactions of the terms, nature of the terms (e.g., comparative, superlative, etc.), intersecting relationships or terms, sorting relationships or terms, and any other suitable relationship. Once the natural language query has been parsed, the semantic parsing component 230 converts the set of terms to a logical form representation based on the one or more relationships. In some embodiments, the logical form representation is the intermediate semantic representation of the natural language query.
  • In some embodiments, a grammar aspect of graph-backing, in the semantic parsing component 230, is employed in translating the natural language query into the intermediate semantic representation. In previous systems, creating and maintaining grammar, syntax, and semantic grammars was a large undertaking, done separately for each queried database. The semantic parsing component 230 may employ a graph schema of the knowledge graph to define at least a portion of the grammar rules of the semantic parsing component 230. For example, where the schema contains Person-->WORKS_IN-->Location, the semantic parsing component 230 may create a syntax rule, such as “PERSON ! LOCATION PERSON” and a semantic rule, such as “T (works_in ({0}; {1}).” Since relations that are intuitively direct may correspond to long paths in the graph, the semantic parsing component 230 may additionally allow bridging concept terms in the logical forms that have no syntactic realization but establish the desired semantic links, equivalently, graph paths.
  • For example, where a natural language query includes terms of “top JANUVIA® prescribers in New York,” the query involves three uses of an intersect operator as well as one use of a sorted operator. The sorted operator may be triggered by the superlative modifier “top.” Where the semantic parsing component 230 is transforming the natural language query for the healthcare knowledge graph described above, the semantic parsing component 230 may use one or more semantic or syntax rules associated with the CMS Prescriptions sub-graph, where that sub-graph uses internal ‘cms_drug’ nodes. Further, a bridging concept may be triggered to relate a provider to a drug based on expectations generated by relationships of nodes within the knowledge graph.
  • In operation 330, the modeling component 240 generates a graph query including graph terms corresponding to the set of terms of the natural language query. As shown in FIG. 4, the graph query may be represented within the graphical user interface 400 as a set of selectable user interface elements 406. In some embodiments, generation of the graph query is based on the intermediate semantic representation. The graph terms may be defined based on a graph-based database and the set of terms of the natural language query. In some embodiments, the graph query may comprise or be generated as a cypher query. The modeling component 240 may map one or more of the natural language query and the intermediate semantic representation into a declarative query language cypher, such as an Neo4j query language Cypher. In some embodiments, the modeling component 240 interacts with the semantic parsing component 230, receiving the intermediate semantic representation and converting the representation into the graph query. The modeling component 240 may be an in-memory language model.
  • In some embodiments, the modeling component 240 uses a language model, an entity index, a lexical resource, and grammar or syntax rules associated with the knowledge graph to transform the natural language query or the intermediate semantic representation into the graph query with the graph terms. In such instances, the modeling component 240 and the resulting graph query may be defined by the underlying knowledge graph. For example, the language models used for entity detection may be trained on name-type attributes of nodes. The language models, incorporated in the modeling component 240, may resolve those entities using graph-backed operations. For example, an “Entity index” may be automatically created from a database or the knowledge graph and provide fast look-up for the semantic parsing component 230 or the modeling component 240. A “Lexical analysis” operation may be similarly graph-backed, incorporating node and edge type-names to provide the core lexicon. The core lexicon may then be expand using additional databases or data sets, such as third-party data sets like Wiktionary, WordNet, and heuristic morphological expansions.
  • In operation 340, the database component 220 searches one or more datasets associated with the graph database using the graph query. The modeling component 240 may pass the graph query to the database component 220 for searching against the datasets included in the knowledge graph. In some embodiments, the database component 220 includes a search engine to perform an entity search or other term based searches using the graph query. In some embodiments, the database component 220 parses or otherwise searches attributes, characteristics, and other information of nodes, clusters, datasets, and subgraphs of the knowledge graph to identify nodes, entities, links, databases, datasets, or records, relating to one or more elements of the graph query. The elements of the graph query may be individual elements, search terms, features, or other query elements representative of the natural language query.
  • In operation 350, the presentation component 250 returns a set of results based on the graph query. The presentation component 250 may return the set of results in the graphical user interface 400 of FIG. 4. In some embodiments, as shown in FIG. 4, the set of results are presented in a result area 410. The result area 410 may be populated with a set of selectable interface icons 412. Each selectable interface icon may correspond to a link, dataset, node, entity or record of the knowledge graph. Selection of a selectable interface icon may direct the graphical user interface 400 to a pertinent record location associated with a specified result.
  • In FIG. 5, is a flowchart of operations of the semantic parsing system 150 in performing a method 500 of converting query structures for information retrieval from graph-based data structures, according to some example embodiments. Operations of the method 500 may be performed by the semantic parsing system 150, using components described herein.
  • In operation 510, the modeling component 240 segments a graph query into a set of graph query elements. As shown in FIG. 4, the graph query may be segmented into the set of graph query elements, such that each graph query element corresponds to a selectable user interface element of the set of selectable user interface elements 406. In some embodiments, each graph query element may represent a portion of the natural language query 404 or an interpretation of at least a portion of the natural language query 404, such as a term, entity, or relationship within the natural language query 404.
  • In operation 520, the presentation component 250 generates a first set of graphical interface elements 414, 416, and 418 corresponding to the set of graph query elements. The first set of graphical interface elements 414, 416, and 418 may be selected as graph query elements which are stated or inferred from the natural language query 404.
  • In operation 530, the presentation component 250 causes presentation of the first set of graphical interface elements within a graphical user interface. The first set of graphical interface elements may be contemporaneously presented with the set of terms of the natural language query. As shown in FIG. 4, once generated, the first set of graphical interface elements 414, 416, and 418 may be presented within the graphical user interface 400.
  • In operation 540, the modeling component 240 identifies a set of connective terms linking the set of graph query elements as an approximation of the natural language query. As shown in FIG. 4, the set of connective terms may be inferred from the natural language query 404 without being explicitly stated or included within the natural language query. The modeling component 240 may cooperate with the semantic parsing component 230 to identify relationships between words in the natural language query 404 that indicate, suggest, or imply the connective term or set of connective terms.
  • In operation 550, the presentation component 250 generates a second set of graphical interface elements. As shown in FIG. 4, the second set of graphical interface elements 420 may be generated as selectable or non-selectable user interface elements. The second set of graphical interface elements may correspond to the set of connective terms. In some embodiments, as shown in FIG. 4, the second set of graphical interface elements 420 may be generated with respect to the first set of graphical interface elements 414, 416, and 418. In such embodiments, the second set of graphical interface elements 420, representing connective terms, may be generated to fill in areas between the first set of graphical interface elements 414, 416, and 418 to generate a user readable representation of the graph query.
  • In operation 560, the presentation component 250 causes presentation of the second set of graphical interface elements. The second set of graphical interface elements 420 may be presented contemporaneously with the first set of graphical interface elements 414, 416, and 418, and the set of terms of the natural language query 404. In some embodiments, the second set of graphical interface elements are distributed among the set of graph query elements depicted within the first set of graphical interface elements.
  • In some embodiments, alternative interpretations or search terms may be presented within the graphical user interface 400 of FIG. 4. In such embodiments, during operations 320-330, the semantic parsing system 150 may identify alternative search terms based on one or more of the set of terms of the natural language query. In some embodiments, the alternative search terms may be generated based on one or more of the natural language query, the intermediate semantic representation, and the graph query generated in method 300. The presentation component 250 may generate a set of alternative interface elements corresponding to the set of alternative search terms to populate a portion of the graphical user interface 400. Once generated, the presentation component 250 may cause presentation of the set of alternative interface elements and alternative search terms. The alternative interface elements and search terms may be presented contemporaneously with interface elements corresponding to the graph query element, the graph query, and the natural language query.
  • In FIG. 6, is a flowchart of operations of the semantic parsing system 150 in performing a method 600 of converting query structures for information retrieval from graph-based data structures, according to some example embodiments. Operations of the method 600 may be performed by the semantic parsing system 150, using components described herein.
  • In operation 610, the modeling component 240 identifies an entity within a graph query element included in the graph query. As shown in FIG. 7, the entity 702 may be identified as a term, an item, an affliction, or any other searchable aspect of a database. The entity may be identified during transformation of the natural language query to the graph query, described above with respect to FIGS. 3-5.
  • In operation 620, the modeling component 240 determines one or more graph query elements related to the entity. The one or more graph query elements 704 may be identified in a manner similar to or the same as described above with respect to translating the natural language query to the graph query in FIG. 3 and the method 300.
  • In operation 630, the presentation component 250 generates one or more interface elements 706 related to the entity. In some embodiments, the interface elements 706 represent the one or more graph query elements. Each interface element may represent a distinct graph query element, such that if a plurality of graph query elements are identified a plurality of interface elements 706 are generated.
  • In operation 640, the modeling component 240 detects interaction with the graph query element associated with the entity. The modeling component 240 may detect interaction with the graph query element 702 via a tap, touch, mouse click, or any other suitable user interaction discernable within a graphical user interface presented on a computing device.
  • In operation 650, the presentation component 250 causes presentation of the one or more interface elements for the one or more graph query elements relating to the entity. In some embodiments, as shown in FIG. 7, the one or more graph query elements 704 or the interface elements 706 may be presented in a menu 708. The menu 708 may be a hovering menu, a drop down menu, a pop up window, or any other suitable selectable interface element or window. The menu 708 may present additional search operations or options mirroring those described above with respect to the graphical user interface 400 of FIG. 4.
  • In operation 660, the presentation component 250 cooperates with the modeling component 240 to replace the entity with a graph query element associated with the selected interface element within the graph query. In some embodiments, the entity is replaced by the selected interface element and corresponding graph query element upon detecting selection of an interface element of the one or more interface elements.
  • Semantic parsers, such as the semantic parsing system 150, are commonly evaluated using datasets in which texts are paired with their desired logical forms or denotations. Such evaluations may be effective but costly in terms of human labor. Embodiments of the present semantic parsing system 150 may be evaluated via increased usability.
  • Embodiments and aspects of the present disclosure were evaluated using pairs of tasks, classified into increasing levels of difficulty as measured by the number of terms they contained and the intricacy of the semantic operations required. For each participant involved in the evaluation, one of each pair was randomly assigned as a parser task and one as a Cypher task, for a total often tasks. Random assignment was used to even out any variable difficulty not accounted for by classifications used in example embodiments of the semantic parsing system 150. The tasks took the form of short summaries like “Objects to return: providers; Restriction: specialty is cardiac surgery.” Clues contained in these summaries regarding how to formulate queries may be equally useful for English and Cypher query formulations or translations. Performance of embodiments of the semantic parsing system 150 were evaluated on the Cypher and English parts within subjects. These clues may not favor any one system. Similarly, within-subject comparisons may abstract away from participants' varying levels of expertise with Cypher graph queries.
  • Embodiments of the semantic parsing system were evaluated in the above-described manner by individuals having Cypher experience. The results of the study favored embodiments presented in the present disclosure. In the evaluation, the total time taken for the Cypher tasks was much lower using embodiments of the semantic parsing system 150 than for other search or parsing systems. The disclosed semantic parsing system 150 is flexible, powerful, and easy to deploy on new, large health knowledge graphs because the central aspects of the system are defined by the graph itself. The system is under active development; we aim to provide increasingly rich access to public health data. Embodiments of the semantic parsing system 150 improve usability of knowledge graph searching over graph query languages and are easier for novice users to navigate. Further, embodiments of the semantic parsing system 150 are easier to scale than pure natural language query systems. The semantic parsing system 150 enables expansion and scaling across a broad range of dataset and database domains with minimal or no human intervention or annotation.
  • Modules, Components, and Logic
  • Certain embodiments are described herein as including logic or a number of components, modules, or mechanisms. Components may constitute either software components (e.g., code embodied on a machine-readable medium) or hardware components. A “hardware component” is a tangible unit capable of performing certain operations and may be configured or arranged in a certain physical manner. In various example embodiments, one or more computer systems (e.g., a standalone computer system, a client computer system, or a server computer system) or one or more hardware components of a computer system (e.g., a processor or a group of processors) may be configured by software (e.g., an application or application portion) as a hardware component that operates to perform certain operations as described herein.
  • In some embodiments, a hardware component may be implemented mechanically, electronically, or any suitable combination thereof. For example, a hardware component may include dedicated circuitry or logic that is permanently configured to perform certain operations. For example, a hardware component may be a special-purpose processor, such as a Field-Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC). A hardware component may also include programmable logic or circuitry that is temporarily configured by software to perform certain operations. For example, a hardware component may include software executed by a general-purpose processor or other programmable processor. Once configured by such software, hardware components become specific machines (or specific components of a machine) uniquely tailored to perform the configured functions and are no longer general-purpose processors. It will be appreciated that the decision to implement a hardware component mechanically, in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.
  • Accordingly, the phrase “hardware component” should be understood to encompass a tangible entity, be that an entity that is physically constructed, permanently configured (e.g., hardwired), or temporarily configured (e.g., programmed) to operate in a certain manner or to perform certain operations described herein. As used herein, “hardware-implemented component” refers to a hardware component. Considering embodiments in which hardware components are temporarily configured (e.g., programmed), each of the hardware components need not be configured or instantiated at any one instance in time. For example, where a hardware component comprises a general-purpose processor configured by software to become a special-purpose processor, the general-purpose processor may be configured as respectively different special-purpose processors (e.g., comprising different hardware components) at different times. Software accordingly configures a particular processor or processors, for example, to constitute a particular hardware component at one instance of time and to constitute a different hardware component at a different instance of time.
  • Hardware components can provide information to, and receive information from, other hardware components. Accordingly, the described hardware components may be regarded as being communicatively coupled. Where multiple hardware components exist contemporaneously, communications may be achieved through signal transmission (e.g., over appropriate circuits and buses) between or among two or more of the hardware components. In embodiments in which multiple hardware components are configured or instantiated at different times, communications between such hardware components may be achieved, for example, through the storage and retrieval of information in memory structures to which the multiple hardware components have access. For example, one hardware component may perform an operation and store the output of that operation in a memory device to which it is communicatively coupled. A further hardware component may then, at a later time, access the memory device to retrieve and process the stored output. Hardware components may also initiate communications with input or output devices, and can operate on a resource (e.g., a collection of information).
  • The various operations of example methods described herein may be performed, at least partially, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors may constitute processor-implemented components that operate to perform one or more operations or functions described herein. As used herein, “processor-implemented component” refers to a hardware component implemented using one or more processors.
  • Similarly, the methods described herein may be at least partially processor-implemented, with a particular processor or processors being an example of hardware. For example, at least some of the operations of a method may be performed by one or more processors or processor-implemented components. Moreover, the one or more processors may also operate to support performance of the relevant operations in a “cloud computing” environment or as a “software as a service” (SaaS). For example, at least some of the operations may be performed by a group of computers (as examples of machines including processors), with these operations being accessible via a network (e.g., the Internet) and via one or more appropriate interfaces (e.g., an API).
  • The performance of certain of the operations may be distributed among the processors, not only residing within a single machine, but deployed across a number of machines. In some example embodiments, the processors or processor-implemented components may be located in a single geographic location (e.g., within a home environment, an office environment, or a server farm). In other example embodiments, the processors or processor-implemented components may be distributed across a number of geographic locations.
  • Machine and Software Architecture
  • The components, methods, applications and so forth described in conjunction with FIGS. 2-6 are implemented in some embodiments in the context of a machine and an associated software architecture. In various embodiments, the components, methods, applications and so forth described above are implemented in the context of a plurality of machines, distributed across and communicating via a network, and one or more associated software architectures. The sections below describe representative software architecture(s) and machine (e.g., hardware) architecture that are suitable for use with the disclosed embodiments.
  • Software architectures are used in conjunction with hardware architectures to create devices and machines tailored to particular purposes. For example, a particular hardware architecture coupled with a particular software architecture will create a mobile device, such as a mobile phone, tablet device, or so forth. A slightly different hardware and software architecture may yield a smart device for use in the “internet of things,” while yet another combination produces a server computer for use within a cloud computing architecture. Not all combinations of such software and hardware architectures are presented here as those of skill in the art can readily understand how to implement the present embodiments in different contexts from the disclosure contained herein.
  • Software Architecture
  • FIG. 8 is a block diagram 800 illustrating a representative software architecture 802, which may be used in conjunction with various hardware architectures herein described. FIG. 8 is merely a non-limiting example of a software architecture and it will be appreciated that many other architectures may be implemented to facilitate the functionality described herein. The software architecture 802 may be executing on hardware such as machine 900 of FIG. 9 that includes, among other things, processors 910, memory 930, and Input/Output (I/O) components 950. A representative hardware layer 804 is illustrated and can represent, for example, the machine 800 of FIG. 8. The representative hardware layer 804 comprises one or more processing units 806 having associated executable instructions 808. Executable instructions 808 represent the executable instructions of the software architecture 802, including implementation of the methods, components, and so forth of FIGS. 2-7. Hardware layer 804 also includes memory and/or storage components 810, which also have executable instructions 808. Hardware layer 804 may also comprise other hardware as indicated by 812, which represents any other hardware of the hardware layer 804, such as the other hardware illustrated as part of machine 900.
  • In the example architecture of FIG. 8, the software 802 may be conceptualized as a stack of layers where each layer provides particular functionality. For example, the software 802 may include layers such as an operating system 814, libraries 816, frameworks/middleware 818, applications 820, and presentation layer 822. Operationally, the applications 820 and/or other components within the layers may invoke API calls 824 through the software stack and receive a response, returned values, and so forth, illustrated as messages 826 in response to the API calls 824. The layers illustrated are representative in nature and not all software architectures have all layers. For example, some mobile or special purpose operating systems may not provide a frameworks/middleware layer 818, while others may provide such a layer. Other software architectures may include additional or different layers.
  • The operating system 814 may manage hardware resources and provide common services. The operating system 814 may include, for example, a kernel 828, services 830, and drivers 832. The kernel 828 may act as an abstraction layer between the hardware and the other software layers. For example, the kernel 828 may be responsible for memory management, processor management (e.g., scheduling), component management, networking, security settings, and so on. The services 830 may provide other common services for the other software layers. The drivers 832 may be responsible for controlling or interfacing with the underlying hardware. For instance, the drivers 832 may include display drivers, camera drivers, Bluetooth® drivers, flash memory drivers, serial communication drivers (e.g., Universal Serial Bus (USB) drivers), Wi-Fi® drivers, audio drivers, power management drivers, and so forth depending on the hardware configuration.
  • The libraries 816 may provide a common infrastructure that may be utilized by the applications 820 and/or other components and/or layers. The libraries 816 typically provide functionality that allows other software components to perform tasks in an easier fashion than to interface directly with the underlying operating system 814 functionality (e.g., kernel 828, services 830 and/or drivers 832). The libraries 816 may include system 834 libraries (e.g., C standard library) that may provide functions such as memory allocation functions, string manipulation functions, mathematic functions, and the like. In addition, the libraries 816 may include API libraries 836 such as media libraries (e.g., libraries to support presentation and manipulation of various media format such as Moving Pictures Experts Group 4 (MPEG4), H.264, MP3, Advanced Audio Coding (AAC), Adaptive Multi-Rate (AMR), Joint Photographic Experts Group (JPEG), Portable Network Graphics (PNG)), graphics libraries (e.g., an OpenGL framework that may be used to render two dimensions and three dimensions in a graphic content on a display), database libraries (e.g., SQLite that may provide various relational database functions), web libraries (e.g., WebKit that may provide web browsing functionality), and the like. The libraries 816 may also include a wide variety of other libraries 838 to provide many other APIs to the applications 820 and other software components/modules.
  • The frameworks 818 (also sometimes referred to as middleware) may provide a higher-level common infrastructure that may be utilized by the applications 820 and/or other software components/modules. For example, the frameworks 818 may provide various graphical user interface functions, high-level resource management, high-level location services, and so forth. The frameworks 818 may provide a broad spectrum of other APIs that may be utilized by the applications 820 and/or other software components/modules, some of which may be specific to a particular operating system or platform. In some example embodiments, predictive modeling components 819 (e.g., one or more components of the semantic parsing systems 150) may be implemented at least in part within the middleware/frameworks 818. For example, in some instances, at least a portion of the database component 220 and the presentation component 250, providing graphical and non-graphical user interface functions, may be implemented in the middleware/frameworks 818. Similarly, in some example embodiments, portions of one or more of the receiver component 210, the database component 220, the semantic parsing component 230, the modeling component 240, and the presentation component 250 may be implemented in the middleware/frameworks 818.
  • The applications 820 include built-in applications 840, third party applications 842, and/or predictive modeling components 843 (e.g., user facing portions of one or more of the components of the predictive modeling system 150). Examples of representative built-in applications 840 may include, but are not limited to, a contacts application, a browser application, a book reader application, a location application, a media application, a messaging application, and/or a game application. Third party applications 842 may include any of the built-in applications as well as a broad assortment of other applications. In a specific example, the third-party application 842 (e.g., an application developed using the Android™ or iOS™ software development kit (SDK) by an entity other than the vendor of the particular platform) may be mobile software running on a mobile operating system such as iOS™, Android™, Windows® Phone, or other mobile operating systems. In this example, the third-party application 842 may invoke the API calls 824 provided by the mobile operating system such as operating system 814 to facilitate functionality described herein. In various example embodiments, the user facing portions of the predictive modeling components 843 may include one or more components or portions of components described with respect to FIG. 2. For example, in some instances, portions of the receiver component 210, the database component 220, the semantic parsing component 230, the modeling component 240, and the presentation component 250, associated with user interface elements (e.g., data entry and data output functions), may be implemented in the form of an application.
  • The applications 820 may utilize built in operating system functions (e.g., kernel 828, services 830 and/or drivers 832), libraries (e.g., system 834, APIs 836, and other libraries 838), frameworks/middleware 818 to create user interfaces to interact with users of the system. Alternatively, or additionally, in some systems interactions with a user may occur through a presentation layer, such as presentation layer 844. In these systems, the application/component “logic” can be separated from the aspects of the application/component that interact with a user.
  • Some software architectures utilize virtual machines. In the example of FIG. 8, this is illustrated by virtual machine 848. A virtual machine creates a software environment where applications/components can execute as if they were executing on a hardware machine (such as the machine of FIG. 9, for example). A virtual machine is hosted by a host operating system (operating system 814 in FIG. 8) and typically, although not always, has a virtual machine monitor 846, which manages the operation of the virtual machine as well as the interface with the host operating system (i.e., operating system 814). A software architecture executes within the virtual machine such as an operating system 850, libraries 852, frameworks/middleware 854, applications 856 and/or presentation layer 858. These layers of software architecture executing within the virtual machine 848 can be the same as corresponding layers previously described or may be different.
  • Example Machine Architecture and Machine-Readable Medium
  • FIG. 9 is a block diagram illustrating components of a machine 900, according to some example embodiments, able to read instructions (e.g., processor executable instructions) from a machine-readable medium (e.g., a non-transitory machine-readable storage medium) and perform any one or more of the methodologies discussed herein. Specifically, FIG. 9 shows a diagrammatic representation of the machine 900 in the example form of a computer system, within which instructions 916 (e.g., software, a program, an application, an applet, an app, or other executable code) for causing the machine 900 to perform any one or more of the methodologies discussed herein may be executed. For example, the instructions may cause the machine to execute methods described herein. Additionally, or alternatively, the instructions may implement the receiver component 210, the database component 220, the semantic parsing component 230, the modeling component 240, and the presentation component 250 of FIG. 2, and so forth. The instructions transform the general, non-programmed machine into a particular machine programmed to carry out the described and illustrated functions in the manner described.
  • In alternative embodiments, the machine 900 operates as a standalone device or may be coupled (e.g., networked) to other machines in a networked system. In a networked deployment, the machine 900 may operate in the capacity of a server machine or a client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine 900 may comprise, but not be limited to, a server computer, a client computer, a personal computer (PC), a tablet computer, a laptop computer, a netbook, a set-top box, an entertainment media system, a web appliance, a network router, a network switch, a network bridge, or any machine capable of executing the instructions 916, sequentially or otherwise, that specify actions to be taken by machine 900. In some example embodiments, in the networked deployment, one or more machines may implement at least a portion of the components described above. The one or more machines interacting with the machine 900 may comprise, but not be limited to a PDA, an entertainment media system, a cellular telephone, a smart phone, a mobile device, a wearable device (e.g., a smart watch), a smart home device (e.g., a smart appliance), and other smart devices. Further, while only a single machine 900 is illustrated, the term “machine” shall also be taken to include a collection of machines 900 that individually or jointly execute the instructions 916 to perform any one or more of the methodologies discussed herein.
  • The machine 900 may include processors 910, memory 930, and I/O components 950, which may be configured to communicate with each other such as via a bus 902. In an example embodiment, the processors 910 (e.g., a Central Processing Unit (CPU), a Reduced Instruction Set Computing (RISC) processor, a Complex Instruction Set Computing (CISC) processor, a Graphics Processing Unit (GPU), a Digital Signal Processor (DSP), an ASIC, a Radio-Frequency Integrated Circuit (RFIC), another processor, or any suitable combination thereof) may include, for example, processor 912 and processor 914 that may execute instructions 916. The term “processor” is intended to include multi-core processor that may comprise two or more independent processors (sometimes referred to as “cores”) that may execute instructions contemporaneously. Although FIG. 9 shows multiple processors, the machine 900 may include a single processor with a single core, a single processor with multiple cores (e.g., a multi-core process), multiple processors with a single core, multiple processors with multiples cores, or any combination thereof.
  • The memory/storage 930 may include a memory 932, such as a main memory, or other memory storage, and a storage unit 936, both accessible to the processors 910 such as via the bus 902. The storage unit 936 and memory 932 store the instructions 916 embodying any one or more of the methodologies or functions described herein. The instructions 916 may also reside, completely or partially, within the memory 932, within the storage unit 936, within at least one of the processors 910 (e.g., within the processor's cache memory), or any suitable combination thereof, during execution thereof by the machine 900. Accordingly, the memory 932, the storage unit 936, and the memory of processors 910 are examples of machine-readable media.
  • As used herein, “machine-readable medium” means a device able to store instructions and data temporarily or permanently and may include, but is not be limited to, random-access memory (RAM), read-only memory (ROM), buffer memory, flash memory, optical media, magnetic media, cache memory, other types of storage (e.g., Erasable Programmable Read-Only Memory (EEPROM)) and/or any suitable combination thereof. The term “machine-readable medium” should be taken to include a single medium or multiple media (e.g., a centralized or distributed database, or associated caches and servers) able to store instructions 916. The term “machine-readable medium” shall also be taken to include any medium, or combination of multiple media, that is capable of storing instructions (e.g., instructions 916) for execution by a machine (e.g., machine 900), such that the instructions, when executed by one or more processors of the machine 900 (e.g., processors 910), cause the machine 900 to perform any one or more of the methodologies described herein. Accordingly, a “machine-readable medium” refers to a single storage apparatus or device, as well as “cloud-based” storage systems or storage networks that include multiple storage apparatus or devices. The term “machine-readable medium” excludes signals per se.
  • The I/O components 950 may include a wide variety of components to receive input, provide output, produce output, transmit information, exchange information, capture measurements, and so on. The specific I/O components 950 that are included in a particular machine will depend on the type of machine. For example, portable machines such as mobile phones will likely include a touch input device or other such input mechanisms, while a headless server machine will likely not include such a touch input device. It will be appreciated that the I/O components 950 may include many other components that are not shown in FIG. 9. The I/O components 950 are grouped according to functionality merely for simplifying the following discussion and the grouping is in no way limiting. In various example embodiments, the I/O components 950 may include output components 952 and input components 954. The output components 952 may include visual components (e.g., a display such as a plasma display panel (PDP), a light emitting diode (LED) display, a liquid crystal display (LCD), a projector, or a cathode ray tube (CRT)), acoustic components (e.g., speakers), haptic components (e.g., a vibratory motor, resistance mechanisms), other signal generators, and so forth. The input components 954 may include alphanumeric input components (e.g., a keyboard, a touch screen configured to receive alphanumeric input, a photo-optical keyboard, or other alphanumeric input components), point based input components (e.g., a mouse, a touchpad, a trackball, a joystick, a motion sensor, or other pointing instrument), tactile input components (e.g., a physical button, a touch screen that provides location and/or force of touches or touch gestures, or other tactile input components), audio input components (e.g., a microphone), and the like.
  • In further example embodiments, the I/O components 950 may include biometric components 956, motion components 957, environmental components 960, or position components 962 among a wide array of other components. For example, the biometric components 956 may include components to detect expressions (e.g., hand expressions, facial expressions, vocal expressions, body gestures, or eye tracking), measure biosignals (e.g., blood pressure, heart rate, body temperature, perspiration, or brain waves), identify a person (e.g., voice identification, retinal identification, facial identification, fingerprint identification, or electroencephalogram based identification), and the like. The motion components 958 may include acceleration sensor components (e.g., accelerometer), gravitation sensor components, rotation sensor components (e.g., gyroscope), and so forth. The environmental components 960 may include, for example, illumination sensor components (e.g., photometer), temperature sensor components (e.g., one or more thermometers that detect ambient temperature), humidity sensor components, pressure sensor components (e.g., barometer), acoustic sensor components (e.g., one or more microphones that detect background noise), proximity sensor components (e.g., infrared sensors that detect nearby objects), gas sensors (e.g., gas detect sensors to detection concentrations of hazardous gases for safety or to measure pollutants in the atmosphere), or other components that may provide indications, measurements, or signals corresponding to a surrounding physical environment. The position components 962 may include location sensor components (e.g., a GPS receiver component), altitude sensor components (e.g., altimeters or barometers that detect air pressure from which altitude may be derived), orientation sensor components (e.g., magnetometers), and the like.
  • Communication may be implemented using a wide variety of technologies. The I/O components 950 may include communication components 964 operable to couple the machine 900 to a network 980 or devices 970 via coupling 982 and coupling 972, respectively. For example, the communication components 964 may include a network interface component or other suitable device to interface with the network 980. In further examples, communication components 964 may include wired communication components, wireless communication components, cellular communication components, Near Field Communication (NFC) components, Bluetooth® components (e.g., Bluetooth® Low Energy), Wi-Fi® components, and other communication components to provide communication via other modalities. The devices 970 may be another machine or any of a wide variety of peripheral devices (e.g., a peripheral device coupled via a USB).
  • Moreover, the communication components 964 may detect identifiers or include components operable to detect identifiers. For example, the communication components 964 may include Radio Frequency Identification (RFID) tag reader components, NFC smart tag detection components, optical reader components (e.g., an optical sensor to detect one-dimensional bar codes such as Universal Product Code (UPC) bar code, multi-dimensional bar codes such as Quick Response (QR) code, Aztec code, Data Matrix, Dataglyph, MaxiCode, PDF417, Ultra Code, UCC RSS-2D bar code, and other optical codes), or acoustic detection components (e.g., microphones to identify tagged audio signals). In addition, a variety of information may be derived via the communication components 964, such as, location via Internet Protocol (IP) geo-location, location via Wi-Fi® signal triangulation, location via detecting a NFC beacon signal that may indicate a particular location, and so forth.
  • Transmission Medium
  • In various example embodiments, one or more portions of the network 980 may be an ad hoc network, an intranet, an extranet, a VPN, a LAN, a WLAN, a WAN, a WWAN, a MAN, the Internet, a portion of the Internet, a portion of the PSTN, a plain old telephone service (POTS) network, a cellular telephone network, a wireless network, a Wi-Fi® network, another type of network, or a combination of two or more such networks. For example, the network 980 or a portion of the network 980 may include a wireless or cellular network and the coupling 982 may be a Code Division Multiple Access (CDMA) connection, a Global System for Mobile communications (GSM) connection, or other type of cellular or wireless coupling. In this example, the coupling 982 may implement any of a variety of types of data transfer technology, such as Single Carrier Radio Transmission Technology (1×RTT), Evolution-Data Optimized (EVDO) technology, General Packet Radio Service (GPRS) technology, Enhanced Data rates for GSM Evolution (EDGE) technology, third Generation Partnership Project (3GPP) including 3G, fourth generation wireless (4G) networks. Universal Mobile Telecommunications System (UMTS), High Speed Packet Access (HSPA), Worldwide Interoperability for Microwave Access (WiMAX), Long Term Evolution (LTE) standard, others defined by various standard setting organizations, other long range protocols, or other data transfer technology.
  • The instructions 916 may be transmitted or received over the network 980 using a transmission medium via a network interface device (e.g., a network interface component included in the communication components 964) and utilizing any one of a number of well-known transfer protocols (e.g., hypertext transfer protocol (HTTP)). Similarly, the instructions 916 may be transmitted or received using a transmission medium via the coupling 972 (e.g., a peer-to-peer coupling) to devices 970. The term “transmission medium” shall be taken to include any intangible medium that is capable of storing, encoding, or carrying instructions 916 for execution by the machine 900, and includes digital or analog communications signals or other intangible medium to facilitate communication of such software.
  • Language
  • Throughout this specification, plural instances may implement components, operations, or structures described as a single instance. Although individual operations of one or more methods are illustrated and described as separate operations, one or more of the individual operations may be performed concurrently, and nothing requires that the operations be performed in the order illustrated. Structures and functionality presented as separate components in example configurations may be implemented as a combined structure or component. Similarly, structures and functionality presented as a single component may be implemented as separate components. These and other variations, modifications, additions, and improvements fall within the scope of the subject matter herein.
  • Although an overview of the inventive subject matter has been described with reference to specific example embodiments, various modifications and changes may be made to these embodiments without departing from the broader scope of embodiments of the present disclosure. Such embodiments of the inventive subject matter may be referred to herein, individually or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any single disclosure or inventive concept if more than one is, in fact, disclosed.
  • The embodiments illustrated herein are described in sufficient detail to enable those skilled in the art to practice the teachings disclosed. Other embodiments may be used and derived therefrom, such that structural and logical substitutions and changes may be made without departing from the scope of this disclosure. The Detailed Description, therefore, is not to be taken in a limiting sense, and the scope of various embodiments is defined only by the appended claims, along with the full range of equivalents to which such claims are entitled.
  • As used herein, the term “or” may be construed in either an inclusive or exclusive sense. Moreover, plural instances may be provided for resources, operations, or structures described herein as a single instance. Additionally, boundaries between various resources, operations, components, engines, and data stores are somewhat arbitrary, and particular operations are illustrated in a context of specific illustrative configurations. Other allocations of functionality are envisioned and may fall within a scope of various embodiments of the present disclosure. In general, structures and functionality presented as separate resources in the example configurations may be implemented as a combined structure or resource. Similarly, structures and functionality presented as a single resource may be implemented as separate resources. These and other variations, modifications, additions, and improvements fall within a scope of embodiments of the present disclosure as represented by the appended claims. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

Claims (20)

What is claimed is:
1. A method, comprising:
receiving, at one or more hardware processors of a machine, a natural language query including a set of terms;
generating, by the one or more hardware processors, an intermediate semantic representation of the set of terms of the natural language query;
based on the intermediate semantic representation, generating a graph query including graph terms corresponding to the set of terms of the natural language query defined by a graph database;
searching one or more datasets associated with the graph database using the graph query; and
returning a set of results based on the graph query.
2. The method of claim 1, wherein generating the intermediate semantic representation further comprises:
parsing the set of terms of the natural language query to identify one or more relationships between the set of terms; and
converting the set of terms to a logical form representation based on the one or more relationships, the logical form representation being the intermediate semantic representation of the natural language query.
3. The method of claim 1, wherein generating the graph query further comprises:
segmenting the graph query into a set of graph query elements;
generating a set of graphical interface elements corresponding to the set of graph query elements; and
causing presentation of the set of graphical interface elements within a graphical user interface contemporaneous with the set of terms of the natural language query.
4. The method of claim 3, wherein the set of graphical interface elements corresponding to the set of graph query elements is a first set of graphical interface elements, and generating the graph query further comprises:
identifying a set of connective terms linking the set of graph query elements as an approximation of the natural language query;
generating a second set of graphical interface elements corresponding to the set of connective terms; and
causing presentation of the second set of graphical interface elements contemporaneous with the first set of graphical interface elements and the set of terms of the natural language query, the second set of graphical interface elements distributed among the set of graph query elements depicted within the first set of graphical interface elements.
5. The method of claim 1 further comprising:
based on one or more of the set of terms of the natural language query and the graph query, generating a set of alternative search terms;
generating a set of alternative interface elements corresponding to the set of alternative search terms; and
causing presentation of the set of alternative interface elements contemporaneous with interface elements corresponding to a set of graph query elements of the graph query.
6. The method of claim 1 further comprising:
identifying an entity within a graph query element included in the graph query;
determining one or more graph query elements related to the entity; and
generating one or more interface elements representing the one or more graph query elements, each interface element representing a distinct graph query element.
7. The method of claim 6 further comprising:
detecting interaction with the graph query element associated with the entity;
causing presentation of the one or more interface elements for the one or more graph query elements relating to the entity; and
upon detecting selection of an interface element of the one or more interface elements, replacing the entity with a graph query element associated the selected interface element within the graph query.
8. A system, comprising:
one or more hardware processors; and
a processor-readable storage medium coupled to the one or more hardware processors, the processor-readable storage medium storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving, at one or more hardware processors of a machine, a natural language query including a set of terms;
generating, by the one or more hardware processors, an intermediate semantic representation of the set of terms of the natural language query;
based on the intermediate semantic representation, generating a graph query including graph terms corresponding to the set of terms of the natural language query defined by a graph database;
searching one or more datasets associated with the graph database using the graph query; and
returning a set of results based on the graph query.
9. The system of claim 8, wherein generating the intermediate semantic representation further comprises:
parsing the set of terms of the natural language query to identify one or more relationships between the set of terms; and
converting the set of terms to a logical form representation based on the one or more relationships, the logical form representation being the intermediate semantic representation of the natural language query.
10. The system of claim 8, wherein generating the graph query further comprises:
segmenting the graph query into a set of graph query elements;
generating a set of graphical interface elements corresponding to the set of graph query elements; and
causing presentation of the set of graphical interface elements within a graphical user interface contemporaneous with the set of terms of the natural language query.
11. The system of claim 10, wherein the set of graphical interface elements corresponding to the set of graph query elements is a first set of graphical interface elements, and generating the graph query further comprises:
identifying a set of connective terms linking the set of graph query elements as an approximation of the natural language query;
generating a second set of graphical interface elements corresponding to the set of connective terms; and
causing presentation of the second set of graphical interface elements contemporaneous with the first set of graphical interface elements and the set of terms of the natural language query, the second set of graphical interface elements distributed among the set of graph query elements depicted within the first set of graphical interface elements.
12. The system of claim 8, wherein the operations further comprise:
based on one or more of the set of terms of the natural language query and the graph query, generating a set of alternative search terms;
generating a set of alternative interface elements corresponding to the set of alternative search terms; and
causing presentation of the set of alternative interface elements contemporaneous with interface elements corresponding to a set of graph query elements of the graph query.
13. The system of claim 8, wherein the operations further comprise:
identifying an entity within a graph query element included in the graph query;
determining one or more graph query elements related to the entity; and
generating one or more interface elements representing the one or more graph query elements, each interface element representing a distinct graph query element.
14. The system of claim 13, wherein the operations further comprise:
detecting interaction with the graph query element associated with the entity;
causing presentation of the one or more interface elements for the one or more graph query elements relating to the entity; and
upon detecting selection of an interface element of the one or more interface elements, replacing the entity with a graph query element associated the selected interface element within the graph query.
15. A processor-readable storage medium comprising instructions that, when executed by one or more processors of a device, cause the device to implement operations comprising:
receiving a natural language query including a set of terms;
generating an intermediate semantic representation of the set of terms of the natural language query;
based on the intermediate semantic representation, generating a graph query including graph terms corresponding to the set of terms of the natural language query defined by a graph database;
searching one or more datasets associated with the graph database using the graph query; and
returning a set of results based on the graph query.
16. The processor-readable storage medium of claim 15, wherein generating the intermediate semantic representation further comprises:
parsing the set of terms of the natural language query to identify one or more relationships between the set of terms; and
converting the set of terms to a logical form representation based on the one or more relationships, the logical form representation being the intermediate semantic representation of the natural language query.
17. The processor-readable storage medium of claim 15, wherein generating the graph query further comprises:
segmenting the graph query into a set of graph query elements;
generating a set of graphical interface elements corresponding to the set of graph query elements; and
causing presentation of the set of graphical interface elements within a graphical user interface contemporaneous with the set of terms of the natural language query.
18. The processor-readable storage medium of claim 17, wherein the set of graphical interface elements corresponding to the set of graph query elements is a first set of graphical interface elements, and generating the graph query further comprises:
identifying a set of connective terms linking the set of graph query elements as an approximation of the natural language query;
generating a second set of graphical interface elements corresponding to the set of connective terms; and
causing presentation of the second set of graphical interface elements contemporaneous with the first set of graphical interface elements and the set of terms of the natural language query, the second set of graphical interface elements distributed among the set of graph query elements depicted within the first set of graphical interface elements.
19. The processor-readable storage medium of claim 15, wherein the operations further comprise:
identifying an entity within a graph query element included in the graph query;
determining one or more graph query elements related to the entity; and
generating one or more interface elements representing the one or more graph query elements, each interface element representing a distinct graph query element.
20. The processor-readable storage medium of claim 19, wherein the operations further comprise:
detecting interaction with the graph query element associated with the entity;
causing presentation of the one or more interface elements for the one or more graph query elements relating to the entity; and
upon detecting selection of an interface element of the one or more interface elements, replacing the entity with a graph query element associated the selected interface element within the graph query.
US15/796,597 2016-10-28 2017-10-27 Semantic parsing engine Abandoned US20180314729A9 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US15/796,597 US20180314729A9 (en) 2016-10-28 2017-10-27 Semantic parsing engine
US17/012,319 US11657044B2 (en) 2016-10-28 2020-09-04 Semantic parsing engine

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201662414614P 2016-10-28 2016-10-28
US15/796,597 US20180314729A9 (en) 2016-10-28 2017-10-27 Semantic parsing engine

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/012,319 Continuation US11657044B2 (en) 2016-10-28 2020-09-04 Semantic parsing engine

Publications (2)

Publication Number Publication Date
US20180121500A1 US20180121500A1 (en) 2018-05-03
US20180314729A9 true US20180314729A9 (en) 2018-11-01

Family

ID=62021410

Family Applications (2)

Application Number Title Priority Date Filing Date
US15/796,597 Abandoned US20180314729A9 (en) 2016-10-28 2017-10-27 Semantic parsing engine
US17/012,319 Active US11657044B2 (en) 2016-10-28 2020-09-04 Semantic parsing engine

Family Applications After (1)

Application Number Title Priority Date Filing Date
US17/012,319 Active US11657044B2 (en) 2016-10-28 2020-09-04 Semantic parsing engine

Country Status (2)

Country Link
US (2) US20180314729A9 (en)
WO (1) WO2018081633A1 (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10585986B1 (en) * 2018-08-20 2020-03-10 International Business Machines Corporation Entity structured representation and variant generation
US11036718B2 (en) 2018-08-30 2021-06-15 Accenture Global Solutions Limited Linking entities in dynamic graphs
EP3893142A1 (en) * 2020-04-08 2021-10-13 Beijing Baidu Netcom Science And Technology Co. Ltd. Question analysis method, device, knowledge base question answering system and electronic equipment
US11501111B2 (en) 2018-04-06 2022-11-15 International Business Machines Corporation Learning models for entity resolution using active learning
US11875253B2 (en) 2019-06-17 2024-01-16 International Business Machines Corporation Low-resource entity resolution with transfer learning

Families Citing this family (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018081633A1 (en) 2016-10-28 2018-05-03 Roam Analytics, Inc. Semantic parsing engine
WO2018081628A1 (en) 2016-10-28 2018-05-03 Roam Analytics, Inc. Dataset networking and database modeling
US10579738B2 (en) * 2017-04-05 2020-03-03 Voicebox Technologies Corporation System and method for generating a multi-lingual and multi-intent capable semantic parser based on automatically generated operators and user-designated utterances relating to the operators
US10552410B2 (en) * 2017-11-14 2020-02-04 Mindbridge Analytics Inc. Method and system for presenting a user selectable interface in response to a natural language request
US20190213284A1 (en) 2018-01-11 2019-07-11 International Business Machines Corporation Semantic representation and realization for conversational systems
US10845937B2 (en) * 2018-01-11 2020-11-24 International Business Machines Corporation Semantic representation and realization for conversational systems
US11194842B2 (en) * 2018-01-18 2021-12-07 Samsung Electronics Company, Ltd. Methods and systems for interacting with mobile device
US10838951B2 (en) * 2018-04-02 2020-11-17 International Business Machines Corporation Query interpretation disambiguation
EP3561689A1 (en) * 2018-04-23 2019-10-30 QlikTech International AB Knowledge graph data structures and uses thereof
US11250042B2 (en) * 2018-06-06 2022-02-15 Microsoft Technology Licensing Llc Taxonomy enrichment using ensemble classifiers
US10902208B2 (en) 2018-09-28 2021-01-26 International Business Machines Corporation Personalized interactive semantic parsing using a graph-to-sequence model
EP3903241A4 (en) * 2018-12-24 2022-09-14 Roam Analytics, Inc. Constructing a knowledge graph employing multiple subgraphs and a linking layer including multiple linking nodes
US10963518B2 (en) * 2019-02-22 2021-03-30 General Electric Company Knowledge-driven federated big data query and analytics platform
EP3938931A4 (en) 2019-03-11 2022-12-07 Parexel International, LLC Methods, apparatus and systems for annotation of text documents
KR102411778B1 (en) * 2019-05-28 2022-06-22 주식회사 케이티 Server, method and computer program for infering comparative advantage of multiple knowledge
US11468054B2 (en) 2019-06-11 2022-10-11 Jpmorgan Chase Bank, N.A. Systems and methods for automated analysis of business intelligence
US11475065B2 (en) * 2019-10-29 2022-10-18 Neo4J Sweden Ab Pre-emptive graph search for guided natural language interactions with connected data systems
EP3822826A1 (en) * 2019-11-15 2021-05-19 Siemens Energy Global GmbH & Co. KG Database interaction and interpretation tool
US11314785B2 (en) * 2020-01-02 2022-04-26 International Business Machines Corporation Automatic visualization and inquiry generation
CN111708899B (en) * 2020-06-13 2023-10-03 广州华建工智慧科技有限公司 Engineering information intelligent searching method based on natural language and knowledge graph
US11816102B2 (en) * 2020-08-12 2023-11-14 Oracle International Corporation Natural language query translation based on query graphs
US11726994B1 (en) * 2021-03-31 2023-08-15 Amazon Technologies, Inc. Providing query restatements for explaining natural language query results
CN114168612B (en) * 2021-09-06 2022-08-16 川投信息产业集团有限公司 Asset big data platform query acceleration method
WO2023047360A1 (en) * 2021-09-23 2023-03-30 The Joan and Irwin Jacobs Technion-Cornell Institute Multi-stage machine learning techniques for profiling hair and uses thereof

Family Cites Families (72)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5450535A (en) 1993-09-24 1995-09-12 At&T Corp. Graphs employing clusters
US6976020B2 (en) 2000-01-27 2005-12-13 Poppet International, Inc. Software composition using graph types, graph, and agents
US7177798B2 (en) * 2000-04-07 2007-02-13 Rensselaer Polytechnic Institute Natural language interface using constrained intermediate dictionary of results
KR20020045343A (en) * 2000-12-08 2002-06-19 오길록 Method of information generation and retrieval system based on a standardized Representation format of sentences structures and meanings
US6944830B2 (en) 2000-12-21 2005-09-13 Xerox Corporation System and method for browsing hierarchically based node-link structures based on an estimated degree of interest
US6968344B2 (en) 2001-07-26 2005-11-22 Tata Consultancy Services Limited Method and apparatus for object-oriented access to a relational database management system (RDBMS) based on any arbitrary predicate
EP1476834A1 (en) 2002-02-07 2004-11-17 Thinkdynamics Inc. Method and system for managing resources in a data center
US7548847B2 (en) 2002-05-10 2009-06-16 Microsoft Corporation System for automatically annotating training data for a natural language understanding system
US7769794B2 (en) 2003-03-24 2010-08-03 Microsoft Corporation User interface for a file system shell
US7761480B2 (en) 2003-07-22 2010-07-20 Kinor Technologies Inc. Information access using ontologies
US20050027664A1 (en) 2003-07-31 2005-02-03 Johnson David E. Interactive machine learning system for automated annotation of information in text
US8024335B2 (en) 2004-05-03 2011-09-20 Microsoft Corporation System and method for dynamically generating a selectable search extension
US7966246B2 (en) 2003-10-23 2011-06-21 Alphacet, Inc. User interface for correlation of analysis systems
US7974978B2 (en) * 2004-04-30 2011-07-05 International Business Machines Corporation System and method for graph indexing
JP2007536634A (en) 2004-05-04 2007-12-13 フィッシャー−ローズマウント・システムズ・インコーポレーテッド Service-oriented architecture for process control systems
US7685118B2 (en) * 2004-08-12 2010-03-23 Iwint International Holdings Inc. Method using ontology and user query processing to solve inventor problems and user problems
US7624097B2 (en) * 2005-01-14 2009-11-24 International Business Machines Corporation Abstract records
US20060242624A1 (en) * 2005-04-22 2006-10-26 Business Objects Apparatus and method for constructing a semantic layer based on XBRL data
US20070106499A1 (en) 2005-08-09 2007-05-10 Kathleen Dahlgren Natural language search system
US20080213768A1 (en) * 2006-08-17 2008-09-04 Zhauhui Cai Identification and use of biomarkers for non-invasive and early detection of liver injury
US8224862B2 (en) 2007-01-12 2012-07-17 Geni, Inc. System and method for providing a networked viral family tree
US8375014B1 (en) * 2008-06-19 2013-02-12 BioFortis, Inc. Database query builder
US8423523B2 (en) * 2008-11-13 2013-04-16 SAP France S.A. Apparatus and method for utilizing context to resolve ambiguous queries
US8554710B2 (en) * 2010-02-12 2013-10-08 Raytheon Company Converting video metadata to propositional graphs for use in an analogical reasoning system
US8386086B2 (en) 2010-04-26 2013-02-26 Accenture Global Services Limited Methods and systems for analyzing energy usage
US8380645B2 (en) * 2010-05-27 2013-02-19 Bmc Software, Inc. Method and system to enable inferencing for natural language queries of configuration management databases
US8719066B2 (en) 2010-08-17 2014-05-06 Edifice Technologies Inc. Systems and methods for capturing, managing, sharing, and visualising asset information of an organization
US10162892B2 (en) * 2011-02-28 2018-12-25 International Business Machines Corporation Identifying information assets within an enterprise using a semantic graph created using feedback re-enforced search and navigation
US9824138B2 (en) * 2011-03-25 2017-11-21 Orbis Technologies, Inc. Systems and methods for three-term semantic search
US8452851B2 (en) 2011-07-08 2013-05-28 Jildy, Inc. System and method for grouping of users into overlapping clusters in social networks
GB201200158D0 (en) 2012-01-05 2012-02-15 Rugerro Gramatica Dott Information network with linked information
US8935277B2 (en) * 2012-03-30 2015-01-13 Sap Se Context-aware question answering system
US20130262449A1 (en) * 2012-04-02 2013-10-03 Playence GmBH System and method for search refinement using knowledge model
US9183310B2 (en) * 2012-06-12 2015-11-10 Microsoft Technology Licensing, Llc Disambiguating intents within search engine result pages
US8959119B2 (en) 2012-08-27 2015-02-17 International Business Machines Corporation Context-based graph-relational intersect derived database
US9741138B2 (en) 2012-10-10 2017-08-22 International Business Machines Corporation Node cluster relationships in a graph database
EP2731023B1 (en) * 2012-11-12 2015-03-25 Software AG Method and system for processing graph queries
US8996555B2 (en) * 2012-11-26 2015-03-31 Sap Se Question answering framework for structured query languages
US9355166B2 (en) * 2013-01-31 2016-05-31 Hewlett Packard Enterprise Development Lp Clustering signifiers in a semantics graph
US9659043B2 (en) * 2013-02-07 2017-05-23 Enigma Technologies, Inc. Data system and method
DE102013003055A1 (en) * 2013-02-18 2014-08-21 Nadine Sina Kurz Method and apparatus for performing natural language searches
US9245015B2 (en) * 2013-03-08 2016-01-26 Accenture Global Services Limited Entity disambiguation in natural language text
US10262030B1 (en) * 2013-04-22 2019-04-16 Domo, Inc. Automatic dynamic reusable data recipes
US20150095303A1 (en) * 2013-09-27 2015-04-02 Futurewei Technologies, Inc. Knowledge Graph Generator Enabled by Diagonal Search
US9338097B2 (en) 2013-10-31 2016-05-10 Telefonaktiebolaget L M Ericsson (Publ) Method and system for load balancing at a data network
US9542440B2 (en) * 2013-11-04 2017-01-10 Microsoft Technology Licensing, Llc Enterprise graph search based on object and actor relationships
US10296160B2 (en) * 2013-12-06 2019-05-21 Apple Inc. Method for extracting salient dialog usage from live data
US10474671B2 (en) * 2014-05-12 2019-11-12 Google Llc Interpreting user queries based on nearby locations
US9930179B2 (en) * 2014-05-29 2018-03-27 Avaya Inc. Mechanism for work assignment in a graph-based contact center
US20150370787A1 (en) * 2014-06-18 2015-12-24 Microsoft Corporation Session Context Modeling For Conversational Understanding Systems
US10169355B2 (en) * 2014-10-27 2019-01-01 Tata Consultancy Services Limited Knowledge representation in a multi-layered database
US10445811B2 (en) * 2014-10-27 2019-10-15 Tata Consultancy Services Limited Recommendation engine comprising an inference module for associating users, households, user groups, product metadata and transaction data and generating aggregated graphs using clustering
US20160162464A1 (en) 2014-12-09 2016-06-09 Idibon, Inc. Techniques for combining human and machine learning in natural language processing
US9626453B2 (en) * 2014-12-23 2017-04-18 Sap Se Analytic solution with a self-learning and context-sensitive semantic layer
US9910903B1 (en) * 2015-03-02 2018-03-06 Ca, Inc. Autonomous decision support system using configuration inflation based ETL and content modeling
US10176219B2 (en) * 2015-03-13 2019-01-08 Microsoft Technology Licensing, Llc Interactive reformulation of speech queries
KR101646754B1 (en) * 2015-03-18 2016-08-12 연세대학교 산학협력단 Apparatus and Method of Mobile Semantic Search
US9796090B2 (en) * 2015-04-24 2017-10-24 Accenture Global Services Limited System architecture for control systems via knowledge layout search
US10754853B2 (en) * 2015-11-05 2020-08-25 Datastax, Inc. Virtual edge of a graph database
US10191734B1 (en) * 2015-12-15 2019-01-29 Open Text Corporation Method and system for software application optimization using natural language-based queries
US20170249309A1 (en) * 2016-02-29 2017-08-31 Microsoft Technology Licensing, Llc Interpreting and Resolving Conditional Natural Language Queries
US20170270418A1 (en) 2016-03-15 2017-09-21 Roam Analytics, Inc Point in time predictive graphical model exploration
US20170277841A1 (en) 2016-03-23 2017-09-28 HealthPals, Inc. Self-learning clinical intelligence system based on biological information and medical data metrics
US20170308620A1 (en) * 2016-04-21 2017-10-26 Futurewei Technologies, Inc. Making graph pattern queries bounded in big graphs
US10878000B2 (en) * 2016-07-29 2020-12-29 Hewlett Packard Enterprise Development Lp Extracting graph topology from distributed databases
US10713252B1 (en) * 2016-08-29 2020-07-14 EMC IP Holding Company LLC Methods, systems, and computer readable mediums for performing an aggregated free-form query
US10606893B2 (en) 2016-09-15 2020-03-31 International Business Machines Corporation Expanding knowledge graphs based on candidate missing edges to optimize hypothesis set adjudication
WO2018081633A1 (en) 2016-10-28 2018-05-03 Roam Analytics, Inc. Semantic parsing engine
WO2018081628A1 (en) 2016-10-28 2018-05-03 Roam Analytics, Inc. Dataset networking and database modeling
JP7030853B2 (en) 2017-07-28 2022-03-07 グーグル エルエルシー Systems and methods for predicting and summarizing medical events from electronic health records
EP3903241A4 (en) 2018-12-24 2022-09-14 Roam Analytics, Inc. Constructing a knowledge graph employing multiple subgraphs and a linking layer including multiple linking nodes
EP3938931A4 (en) 2019-03-11 2022-12-07 Parexel International, LLC Methods, apparatus and systems for annotation of text documents

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11501111B2 (en) 2018-04-06 2022-11-15 International Business Machines Corporation Learning models for entity resolution using active learning
US10585986B1 (en) * 2018-08-20 2020-03-10 International Business Machines Corporation Entity structured representation and variant generation
US11036718B2 (en) 2018-08-30 2021-06-15 Accenture Global Solutions Limited Linking entities in dynamic graphs
US11875253B2 (en) 2019-06-17 2024-01-16 International Business Machines Corporation Low-resource entity resolution with transfer learning
EP3893142A1 (en) * 2020-04-08 2021-10-13 Beijing Baidu Netcom Science And Technology Co. Ltd. Question analysis method, device, knowledge base question answering system and electronic equipment
KR20210125405A (en) * 2020-04-08 2021-10-18 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. Question analysis method, apparatus, knowledge graph question-answering system and electronic equipment
KR102441475B1 (en) 2020-04-08 2022-09-06 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. Question analysis method, apparatus, knowledge graph question-answering system and electronic equipment

Also Published As

Publication number Publication date
US20210191924A1 (en) 2021-06-24
WO2018081633A1 (en) 2018-05-03
US11657044B2 (en) 2023-05-23
US20180121500A1 (en) 2018-05-03

Similar Documents

Publication Publication Date Title
US11657044B2 (en) Semantic parsing engine
US11507629B2 (en) Dataset networking and database modeling
US10963457B2 (en) Search query and job title proximity computation via word embedding
US10733507B2 (en) Semantic clustering based retrieval for candidate set expansion
US11436522B2 (en) Joint representation learning of standardized entities and queries
US10474725B2 (en) Determining similarities among industries to enhance job searching
US10855784B2 (en) Entity based search retrieval and ranking
US11934780B2 (en) Content suggestion system
US10055457B2 (en) Entity based query filtering
US10318630B1 (en) Analysis of large bodies of textual data
US9946703B2 (en) Title extraction using natural language processing
US10817317B2 (en) Interactive informational interface
CN110168591B (en) Determining industry similarity to enhance job searching
US10956515B2 (en) Smart suggestions personalization with GLMix
US20170255906A1 (en) Candidate selection for job search ranking
EP3385868A1 (en) Title disambiguation in a social network taxonomy
US10346418B2 (en) Optimizing data access based on data aging
US10726355B2 (en) Parent company industry classifier
US20170270418A1 (en) Point in time predictive graphical model exploration
US10896231B2 (en) Querying named entities
US20210089599A1 (en) Audience filtering system

Legal Events

Date Code Title Description
AS Assignment

Owner name: ROAM ANALYTICS, INC., CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:RESCHKE, KEVIN;PELOQUIN, BEN;POTTS, CHRISTOPHER;AND OTHERS;SIGNING DATES FROM 20171030 TO 20171103;REEL/FRAME:044040/0122

STPP Information on status: patent application and granting procedure in general

Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION