WO2022245406A1 - Systems and methods for hierarchical retrieval of semantic-based passages in deep learning - Google Patents
Systems and methods for hierarchical retrieval of semantic-based passages in deep learning Download PDFInfo
- Publication number
- WO2022245406A1 WO2022245406A1 PCT/US2022/013926 US2022013926W WO2022245406A1 WO 2022245406 A1 WO2022245406 A1 WO 2022245406A1 US 2022013926 W US2022013926 W US 2022013926W WO 2022245406 A1 WO2022245406 A1 WO 2022245406A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- documents
- passages
- document
- question
- passage
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 74
- 238000013135 deep learning Methods 0.000 title claims description 28
- 238000012549 training Methods 0.000 claims description 61
- 230000015654 memory Effects 0.000 claims description 17
- 238000013136 deep learning model Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims 3
- 230000008569 process Effects 0.000 description 41
- 238000013528 artificial neural network Methods 0.000 description 31
- 239000013598 vector Substances 0.000 description 24
- 238000013500 data storage Methods 0.000 description 18
- 238000010801 machine learning Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 8
- 238000007726 management method Methods 0.000 description 8
- 230000008520 organization Effects 0.000 description 7
- 238000013507 mapping Methods 0.000 description 5
- 230000026676 system process Effects 0.000 description 5
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 4
- 239000010931 gold Substances 0.000 description 4
- 229910052737 gold Inorganic materials 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 101100153586 Caenorhabditis elegans top-1 gene Proteins 0.000 description 3
- 101100370075 Mus musculus Top1 gene Proteins 0.000 description 3
- 238000013459 approach Methods 0.000 description 3
- 239000002585 base Substances 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 241001522296 Erithacus rubecula Species 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 241000699666 Mus <mouse, genus> Species 0.000 description 1
- 241000699670 Mus sp. Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000012458 free base Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/93—Document management systems
Definitions
- the embodiments relate generally to machine learning systems and deep learning, and more specifically to a hierarchical retrieval framework of semantic -based data.
- Machine learning (ML) and neural network (NN) systems may be utilized to attempt to understand human speech and writing, e.g., to understand the overall intent, syntax, and/or semantics of human communication.
- Such ML/NN systems may be trained using a large amount of training text, including different corpora of documents, that are pre annotated with labels (supervised), or without pre- annotated labels (unsupervised).
- different training data may be utilized, including characters, words, phrases, passages, and content from documents.
- training data, and specification of such data varies in scope, which may cause different predictions and classifications when using large corpora of documents.
- different uses of training data having different documents, passages from documents, and the like may result in unpredictable and/or slower search results once an ML/NN model is trained.
- FIG. 1 illustrates a block diagram of an example environment wherein systems and methods for predicting database query results may be used according to some embodiments.
- FIG. 2 illustrates a block diagram of another example environment according to some embodiments.
- FIG. 3 illustrates a block diagram of an exemplary computing system for retrieving documents and passages using a hierarchical retrieval in deep learning according to some embodiments.
- FIG. 4 illustrates a simplified diagram of an exemplary document and passages in a corpus of documents that may be retrieved using hierarchical retrieval of semantic -based passages in deep learning according to some embodiments.
- FIG. 5 illustrates a simplified diagram of exemplary components for hierarchical retrieval of semantic -based passages in deep learning according to some embodiments.
- FIG. 6 illustrates a simplified diagram of a flowchart for hierarchical retrieval of semantic -based passages in deep learning using a document-level and passage-level retriever described in FIGS. 3, 4, and 5 according to some embodiments.
- Deep learning has been widely used in ML and NN systems.
- open-domain QA may be used to answer a factoid question.
- dense passage retrieval may be used for answering a question.
- One of the prevalent approaches is to utilize a retriever-reader approach to provide an answer.
- open-domain question answering a question is given and a set of relevant contexts within a corpus of documents is predicted.
- extracting relevant contexts from a large corpus of documents, such as Wikipedia is difficult and suffers from weaknesses, such as where similar topics may be related to a particular question.
- passages from documents may contain only local and specific information, leading to distracting representations.
- a Dense Hierarchical Retrieval may be used to generate accurate dense representations of passages by utilizing both macroscopic semantics in the document and microscopic semantics specific to each passage.
- relevant documents to a question are retrieved, for example, based on encoding documents from a corpus of documents.
- Documents may be encoded at a document level using their abstracts, table of contents, and/or other table of titles within the documents.
- relevant passages may be retrieved by a passage-level retrieval model that is calibrated with document-level relevance.
- each passage is combined with a hierarchical title list.
- in-document negative and in-section negative samples may be used as hard contrastive samples.
- DHR is applied to large open-domain QA datasets, where a dense hierarchical retrieval model may outperform a dense passage retriever and help end-to-end QA systems establish better results on multiple open-domain QA benchmarks ⁇
- network may comprise any hardware or software-based framework that includes any artificial intelligence network or system, NN or system, and/or any training or learning models implemented thereon or therewith.
- module may comprise any hardware or software -based framework that performs one or more functions.
- the module may be implemented on one or more NNs.
- a database system accessible by a plurality of separate organizations, such as a multi-tenant database system
- methods, data structures, and systems are provided for processing a corpus of documents using a document- level retrieval model and a passage-level retrieval model.
- the database system stores multiple documents that are accessible by users of the database system, referred to as a corpus of documents or corpora of documents.
- the documents may be generated, for example, by users or administrators (e.g., agents of an organization) of the database systems based on input, articles, requests, and other documents that may provide some information, such as informational articles, encyclopedic entries, help request, training manuals, pamphlets or other articles about a subject that provide information.
- At least some documents stored by the database system are associated with passages having relevant text for the document title or subject.
- a document within a corpus of documents may further include one or more document structures, including an abstract, a table of contents (ToC), sections and corresponding section titles, subsections and corresponding subsection titles, tables of titles, paragraphs, sentences, and/or other text.
- ToC table of contents
- the embodiments described herein provide methods, computer program products, and computer database systems for hierarchical retrieval of semantic -based passages from documents using a document-level retrieval model and a passage-level retrieval mode that employ ML and NN techniques.
- An online system provides users with access to online services and corpora of documents.
- the online system may be a web-based system that provides users with access to encyclopedic resources and/or customer relationship management (CRM) software applications.
- CRM customer relationship management
- the online system stores the corpora of documents that are accessible by users of the online system and searchable using a trained ML/NN process and/or other search engine, such as a natural language processor.
- the corpora of documents may be generated, for example, by users or administrators of the online system based on input and identification of documents.
- a neural network model for processing a corpus of documents and providing relevant semantic-based passages using DHR, taking into account the specificities of each document, document structure, and passage, thereby enhancing the experience of users associated with the organization, providing faster retrieval results, and minimizing at time processing costs for text retrieval.
- the system and methods of the present disclosure can include, incorporate, or operate in conjunction with or in the environment of a database, which in some embodiments can implemented as a multi-tenant, cloud-based architecture.
- Multi-tenant cloud-based architectures have been developed to improve collaboration, integration, and community- based cooperation between customer tenants without sacrificing data security.
- multi-tenancy refers to a system where a single hardware and software platform simultaneously supports multiple user groups (also referred to as “organizations” or “tenants”) from a common data storage element (also referred to as a “multi-tenant database”).
- the multi-tenant design provides a number of advantages over conventional server virtualization systems.
- the multi-tenant platform operator can often make improvements to the platform based upon collective information from the entire tenant community. Additionally, because all users in the multi-tenant environment execute applications within a common processing space, it is relatively easy to grant or deny access to specific sets of data for any user within the multi-tenant platform, thereby improving collaboration and integration between applications and the data managed by the various applications.
- the multi-tenant architecture therefore allows convenient and cost-effective sharing of similar application features between multiple sets of users.
- FIG. 1 illustrates a block diagram of an example environment 110 according to some embodiments.
- Environment 110 may include user systems 112, network 114, system 116, processor system 117, application platform 118, network interface 120, tenant data storage 122, system data storage 124, program code 126, and process space 128 for executing database system processes and tenant- specific processes, such as running applications as part of an application hosting service.
- environment 110 may not have all of the components listed and/or may have other elements instead of, or in addition to, those listed above.
- environment 110 is an environment in which an on-demand database service exists.
- a user system 112 may be any machine or system that is used by a user to access a database user system.
- any of user systems 112 can be a handheld computing device, a mobile phone, a laptop computer, a notepad computer, a workstation, and/or a network of computing devices.
- user systems 112 might interact via a network 114 with an on-demand database service, which is system 116.
- An on-demand database service such as that which can be implemented using system 116, is a service that is made available to users outside of the enterprise(s) that own, maintain or provide access to system 116. As described above, such users do not need to necessarily be concerned with building and/or maintaining system 116. Instead, resources provided by system 116 may be available for such users’ use when the users need services provided by system 116 - e.g., on the demand of the users.
- Some on-demand database services may store information from one or more tenants stored into tables of a common database image to form a multi-tenant database system (MTS). Accordingly, the “on-demand database service 116” and the “system 116” will be used interchangeably herein.
- MTS multi-tenant database system
- multi-tenant database system can refer to those systems in which various elements of hardware and software of a database system may be shared by one or more customers or tenants. For example, a given application server may simultaneously process requests for a great number of customers, and a given database table may store rows of data such as feed items for a potentially much greater number of customers.
- a database image may include one or more database objects.
- RDBMS relational data base management system
- a relational data base management system (RDBMS) or the equivalent may execute storage and retrieval of information against the data base object(s).
- Application platform 118 may be a framework that allows the applications of system 116 to ran, such as the hardware and/or software infrastructure, e.g., the operating system.
- system 116 may include application platform 118 that enables creating, managing, and executing one or more applications developed by the provider of the on-demand database service, users accessing the on-demand database service via user systems 112, or third-party application developers accessing the on-demand database service via user systems 112.
- the users of user systems 112 may differ in their respective capacities, and the capacity of a particular one of user systems 112 might be entirely determined by permissions (permission levels) for the current user. For example, where a salesperson is using a particular user system 112 to interact with system 116, that user system has the capacities allotted to that salesperson. However, while an administrator is using that user system 112 to interact with system 116, that user system 112 has the capacities allotted to that administrator ⁇
- users at one permission level may have access to applications, data, and database information accessible by a lower permission level user, but may not have access to certain applications, database information, and data accessible by a user at a higher permission level. Thus, different users will have different capabilities with regard to accessing and modifying application and database information, depending on a user’s security or permission level.
- Network 114 is any network or combination of networks of devices that communicate with one another.
- network 114 can be any one or any combination of a local area network (LAN), wide area network (WAN), telephone network, wireless network, point-to-point network, star network, token ring network, hub network, or other appropriate configuration.
- LAN local area network
- WAN wide area network
- IP Internet protocol
- User systems 112 might communicate with system 116 using TCP/IP and, at a higher network level, use other common Internet protocols to communicate. Such as hypertext transfer protocol (HTTP), file transfer protocol (FTP), Andrew file system (AFS), wireless application protocol (WAP), etc.
- HTTP hypertext transfer protocol
- FTP file transfer protocol
- AFS Andrew file system
- WAP wireless application protocol
- user system 112 might include an HTTP client commonly referred to as a “browser” for sending and receiving HTTP messages to and from an HTTP server at system 116.
- HTTP server might be implemented as the sole network interface between system 116 and network 114, but other techniques might be used as well or instead.
- the interface between system 116 and network 114 includes load sharing functionality, such as round- robin HTTP request distributors to balance loads and distribute incoming HTTP requests evenly over a plurality of servers. At least for the users that are accessing that server, each of the plurality of servers has access to the MTS data; however, other alternative configurations may be used instead.
- load sharing functionality such as round- robin HTTP request distributors to balance loads and distribute incoming HTTP requests evenly over a plurality of servers. At least for the users that are accessing that server, each of the plurality of servers has access to the MTS data; however, other alternative configurations may be used instead.
- system 116 implements a web-based CRM system.
- system 116 includes application servers configured to implement and execute CRM software applications as well as provide related data, code, forms, webpages and other information to and from user systems 112 and to store to, and retrieve from, a database system related data, objects, and web page content.
- data for multiple tenants may be stored in the same physical database object.
- tenant data typically is arranged so that data of one tenant is kept logically separate from that of other tenants so that one tenant does not have access to another tenant’s data, unless such data is expressly shared.
- system 116 implements applications other than, or in addition to, a CRM application.
- system 16 may provide tenant access to multiple hosted (standard and custom) applications, including a CRM application.
- User (or third-party developer) applications which may or may not include CRM, may be supported by application platform 118, which manages creation, storage of the applications into one or more database objects, and executing of the applications in a virtual machine in the process space of system 116.
- FIG. 1 One arrangement for elements of system 116 is shown in FIG. 1, including network interface 120, application platform 118, tenant data storage 122 for tenant data 123, system data storage 124 for system data 125 accessible to system 116 and possibly multiple tenants, program code 126 for implementing various functions of system 116, and process space 128 for executing MTS system processes and tenant-specific processes, such as running applications as part of an application hosting service. Additional processes that may execute on system 116 include database indexing processes.
- each of user systems 112 could include a desktop personal computer, workstation, laptop, notepad computer, PDA, cell phone, or any wireless access protocol (WAP) enabled device or any other computing device capable of interfacing directly or indirectly to the Internet or other network connection.
- WAP wireless access protocol
- Each of user systems 112 typically runs an HTTP client, e.g., a browsing program, such as Microsoft’s Internet Explorer browser, Netscape’s Navigator browser, Opera’s browser, or a WAP-enabled browser in the case of a cell phone, notepad computer, PDA or other wireless device, or the like, allowing a user (e.g., subscriber of the multi-tenant database system) of user systems 112 to access, process, and view information, pages, and applications available to it from system 116 over network 114.
- HTTP client e.g., a browsing program, such as Microsoft’s Internet Explorer browser, Netscape’s Navigator browser, Opera’s browser, or a WAP-enabled browser in the case of a cell phone, notepad computer, PDA or other wireless device, or the like.
- Each of user systems 112 also typically includes one or more user interface devices, such as a keyboard, a mouse, trackball, touch pad, touch screen, pen or the like, for interacting with a graphical user interface (GUI) provided by the browser on a display (e.g., a monitor screen, liquid crystal display (LCD) monitor, light emitting diode (LED) monitor, organic light emitting diode (OLED) monitor, etc.) in conjunction with pages, forms, applications, and other information provided by system 116 or other systems or servers.
- GUI graphical user interface
- the user interface device can be used to access data and applications hosted by system 116, and to perform searches on stored data, and otherwise allow a user to interact with various GUI pages that may be presented to a user.
- each of user systems 112 and all of its components are operator configurable using applications, such as a browser, including computer code ran using a central processing unit such as an Intel Pentium® processor or the like.
- system 116 (and additional instances of an MTS, where more than one is present) and all of their components might be operator configurable using application(s) including computer code to run using a central processing unit such as processor system 117, which may include an Intel Pentium® processor or the like, and/or multiple processor units.
- a computer program product embodiment includes a machine -readable storage medium (media) having instructions stored thereon/in which can be used to program a computer to perform any of the processes of the embodiments described herein.
- Computer code for operating and configuring system 116 to intercommunicate and to process webpages, applications and other data and media content as described herein are preferably downloaded and stored on a hard disk, but the entire program code, or portions thereof, may also be stored in any other volatile or non volatile memory medium or device as is well known, such as a read only memory (ROM) or random-access memory (RAM), or provided on any media capable of storing program code, such as any type of rotating media including floppy disks, optical discs, digital versatile disk (DVD), compact disk (CD), microdrive, and magneto-optical disks, and magnetic or optical cards, nanosystems (including molecular memory integrated circuits (ICs)), or any type of media or device suitable for storing instructions and/or data.
- ROM read only memory
- RAM random-access memory
- any media capable of storing program code such as any type of rotating media including floppy disks, optical discs, digital versatile disk (DVD), compact disk (CD), microdrive, and magneto-optical disks, and magnetic
- the entire program code, or portions thereof may be transmitted and downloaded from a software source over a transmission medium, e.g., over the Internet, or from another server, as is well known, or transmitted over any other conventional network connection as is well known (e.g., extranet, virtual private network (VPN), LAN, etc.) using any communication medium and protocols (e.g., TCP/IP, HTTP, HTTPS, Ethernet, etc.) as are well known.
- a transmission medium e.g., over the Internet, or from another server, as is well known, or transmitted over any other conventional network connection as is well known (e.g., extranet, virtual private network (VPN), LAN, etc.) using any communication medium and protocols (e.g., TCP/IP, HTTP, HTTPS, Ethernet, etc.) as are well known.
- computer code for implementing embodiments of the present disclosure can be implemented in any programming language that can be executed on a client system and/or server or server system such as, for example, C, C++, HTML, any other markup language, JavaTM, JavaScript, ActiveX, any other scripting language, such as VBScript, and many other programming languages as are well known may be used.
- JavaTM is a trademark of Sun Microsystems, Inc.
- system 116 is configured to provide webpages, forms, applications, data and media content to the user (client) systems 112 to support the access by user systems 112 as tenants of system 116.
- system 116 provides security mechanisms to keep each tenant’ s data separate unless the data is shared.
- MTS Mobility Management Entity
- they may be located in close proximity to one another (e.g., in a server farm located in a single building or campus), or they may be distributed at locations remote from one another (e.g., one or more servers located in city A and one or more servers located in city B).
- each MTS could include one or more logically and/or physically connected servers distributed locally or across one or more geographic locations.
- server is meant to include a computer system, including processing hardware and process space(s), and an associated storage system and database application (e.g., object-oriented data base management system (OODBMS) or rational database management system (RDBMS)) as is well known in the art.
- OODBMS object-oriented data base management system
- RDBMS rational database management system
- server system and “server” are often used interchangeably herein.
- database object described herein can be implemented as single databases, a distributed database, a collection of distributed databases, a database with redundant online or offline backups or other redundancies, etc., and might include a distributed database or storage network and associated processing intelligence.
- FIG. 2 also illustrates environment 110, which may be used to implement embodiments described herein.
- FIG. 2 further illustrates elements of system 116 and various interconnections, according to some embodiments.
- FIG. 2 shows that each of user systems 112 may include a processor system 112A, a memory system 112B, an input system 112C, and an output system 112D.
- FIG. 2 shows network 114 and system 116.
- system 116 may include tenant data storage 122, tenant data 123, system data storage 124, system data 125, a user interface (UI) 230, an application program interface (API) 232, a PL/Salesforce.com object query language (PL/SOQL) 234, save routines 236, an application setup mechanism 238, applications servers 200I-200 N , a system process space 202, tenant process spaces 204, a tenant management process space 210, a tenant storage area 212, a user storage 214, and application metadata 216.
- environment 110 may not have the same elements as those listed above and/or may have other elements instead of, or in addition to, those listed above.
- processor system 112A may be any combination of one or more processors.
- Memory system 112B may be any combination of one or more memory devices, short-term, and/or long-term memory.
- Input system 112C may be any combination of input devices, such as one or more keyboards, mice, trackballs, scanners, cameras, and/or interfaces to networks.
- Output system 112D may be any combination of output devices, such as one or more monitors, printers, and/or interfaces to networks.
- system 116 may include network interface 120 (of FIG.
- Each application server 200 may be configured to access tenant data storage 122 and tenant data 123 therein, and system data storage 124 and system data 125 therein to serve requests of user systems 112.
- Tenant data 123 might be divided into individual tenant storage areas 212, which can be either a physical arrangement and/or a logical arrangement of data.
- user storage 214 and application metadata 216 might be similarly allocated for each user. For example, a copy of a user’ s most recently used (MRU) items might be stored to user storage 214.
- MRU most recently used
- UI 230 provides a user interface
- API 232 provides an application programmer interface, to system 116 resident processes and to users and/or developers at user systems 112.
- the tenant data and the system data may be stored in various databases, such as one or more OracleTM databases.
- Application platform 118 includes an application setup mechanism 238 that supports application developers’ creation and management of applications, which may be saved as metadata into tenant data storage 122 by save routines 236 for execution by subscribers as one or more tenant process spaces 204 managed by tenant management process space 210, for example. Invocations to such applications may be coded using PL/SOQL 234 that provides a programming language style interface extension to API 232. Some embodiments of PL/SOQL language are discussed in further detail in U.S. Pat. No. 7,730,478, filed Sep. 21, 2007, entitled, “Method and System For Allowing Access to Developed Applications Via a Multi-Tenant On-Demand Database Service,” which is incorporated herein by reference. Invocations to applications may be detected by one or more system processes, which manage retrieving application metadata 216 for the subscriber, making the invocation and executing the metadata as an application in a virtual machine.
- Each application server 200 may be communicably coupled to database systems, e.g., having access to system data 125 and tenant data 123, via a different network connection.
- database systems e.g., having access to system data 125 and tenant data 123
- one application server 200i might be coupled via network 114 (e.g., the Internet)
- another application server 200 N-I might be coupled via a direct network link
- another application server 200 N might be coupled by yet a different network connection.
- Transfer Control Protocol and Internet Protocol TCP/IP
- TCP/IP Transfer Control Protocol and Internet Protocol
- each application server 200 is configured to handle requests for any user associated with any organization that is a tenant. Because it is desirable to be able to add and remove application servers from the server pool at any time for any reason, there is preferably no server affinity for a user and/or organization to a specific application server 200.
- an interface system implementing a load balancing function e.g., an F5 Big-IP load balancer
- the load balancer uses a least connections algorithm to route user requests to application servers 200.
- Other examples of load balancing algorithms such as round robin and observed response time, also can be used.
- system 116 is multi-tenant, wherein system 116 handles storage of, and access to, different objects, data and applications across disparate users and organizations.
- one tenant might be a company that employs a sales force where each salesperson uses system 116 to manage his or her sales process and/or provide information to other users, agents, and administrators, which may be searchable.
- a user might maintain contact data, leads data, customer follow-up data, performance data, goals and progress data, training material, research articles, etc., all applicable to that user (e.g., in tenant data storage 122).
- tenant data storage 122 since all of the data and the applications to access, view, modify, report, transmit, calculate, etc., can be maintained and accessed by a user system having nothing more than network access, the user can manage his or her information from any of many different user systems. For example, if a salesperson is visiting a customer and the customer has Internet access in their lobby, the salesperson can obtain critical updates as to that customer while waiting for the customer to arrive in the lobby.
- each user’s data might be separate from other users’ data regardless of the employers of each user, some data might be organization-wide data shared or accessible by a plurality of users or all of the users for a given organization that is a tenant. Thus, there might be some data structures managed by system 116 that are allocated at the tenant level while other data structures might be managed at the user level. Because an MTS might support multiple tenants including possible competitors, the MTS should have security protocols that keep data, applications, and application use separate. Also, because many tenants may opt for access to a MTS rather than maintain their own system, redundancy, up-time, and backup are additional functions that may be implemented in the MTS. In addition to user-specific data and tenant specific data, system 116 might also maintain system level data usable by multiple tenants or other data. Such system level data might include industry reports, news, postings, and the like that are sharable among tenants.
- user systems 112 (which may be client systems) communicate with application servers 200 to request and update system-level and tenant- level data from system 116 that may require sending one or more queries to tenant data storage 122 and/or system data storage 124.
- System 116 e.g., an application server 200 in system 116) automatically generates one or more structured query language (SQL) statements (e.g., one or more SQL queries) that are designed to access the desired information.
- SQL structured query language
- System data storage 124 may generate query plans to access the requested data from the database, which may include external objects based on references to the objects within a document.
- Each database can generally be viewed as a collection of objects, such as a set of logical tables, containing data fitted into predefined categories.
- a “table” is one representation of a data object and may be used herein to simplify the conceptual description of objects and custom objects. It should be understood that “table” and “object” may be used interchangeably herein.
- Each table generally contains one or more data categories logically arranged as columns or fields in a viewable schema. Each row or record of a table contains an instance of data for each category defined by the fields.
- these categories or groupings can include various standard tables associated with corpora of documents, such as listings of documents belong to a corpus, as well as information associated with searching those corpora submitted to the system (e.g., encoded documents, abstracts, ToCs, textual passages, and additional aforementioned document text).
- a database may include a table that describes a corpus of documents (e.g., one or more documents that may be searched for a subject or the system itself) and may include this text of the documents within the corpora.
- tables and documents in a database might be provided for use by all tenants or may be only viewable by some tenants and agents (e.g., users and administrators) of the system.
- tenants may be allowed to create and store custom objects, or they may be allowed to customize standard entities or objects, for example by creating custom fields for standard objects, including custom index fields.
- Systems and methods for creating custom objects as well as customizing standard objects in a multi-tenant database system are described in further detail in U.S. Pat. No. 7,779,039, filed April 2, 2004, entitled “Custom Entities and Fields in a Multi-Tenant Database System,” which is incorporated herein by reference.
- all custom entity data rows are stored in a single multi-tenant physical table, which may contain multiple logical tables per organization. It is transparent to customers that their multiple “tables” are in fact stored in one large table or that their data may be stored in the same table as the data of other customers.
- Multi-tenant database system 116 described above may be accessed and used by a number of customers, clients, or other persons (generally, “users”), regarding searching and/or browsing of an encyclopedic entry, inquiry, problem, question, issue, support-related matter, training or education, etc.
- other types of search systems may also utilize the processes described herein to provide dense hierarchical retrieval of semantic-based passages in documents.
- a search bar, voice interface, or similar user interface tool is provided to facilitate interaction between system 116 and the user. The search tool allows a user to query the database(s) to access information or data concerning or relating to various documents, objects, and/or entities relevant to the user.
- documents For large databases with many records and information, however, there may be large amounts of documents where some or all of the documents include one or more document structures (e.g., an abstract, a ToC, sections and corresponding section titles, subsections and corresponding subsection titles, tables of titles, and/or the like) and passages (e.g., paragraphs, sentences, and/or other text).
- a document may include document structures designating sections and passages and corresponding text for passages.
- conventional search techniques for open-domain QA e.g., a machine learning system trained using character or word embeddings or vectors
- a database system’s search index data may not be an accurate basis to predict proper search results for a search query when not considering documents and document structures in addition to passages. It is a difficult task to predict and order search results for searches performed by users on large corpora of documents.
- documents may include document structures, passages, and the like.
- the database system predict the documents that are most relevant or applicable to a user’ s search or query so that the desired information or data is presented to the user in the fewest number of keystrokes, mouse clicks, user interfaces, etc.
- systems and methods are provided for predicting and returning search results using one or more dense hierarchical retrieval models that may include a document-level retrieval model and encoder and a passage-level retrieval model and encoder.
- FIG. 3 is a simplified diagram of a computing device that implements a hierarchical retrieval of semantic based training data for deep learning, according to some embodiments described herein. As shown in FIG. 3, computing device 300 includes a processor 310 coupled to memory 320.
- processor 310 Operation of computing device 300 is controlled by processor 310.
- processor 310 may be representative of one or more central processing units, multi-core processors, microprocessors, microcontrollers, digital signal processors, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), graphics processing units (GPUs) and/or the like in computing device 300.
- Computing device 300 may be implemented as a stand-alone subsystem, as a board added to a computing device, and/or as a virtual machine.
- Memory 320 may be used to store software executed by computing device 300 and/or one or more data structures used during operation of computing device 300.
- Memory 320 may include one or more types of machine-readable media. Some common forms of machine-readable media may include floppy disk, flexible disk, hard disk, magnetic tape, any other magnetic medium, CD-ROM, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, RAM, PROM, EPROM, FLASH- EPROM, any other memory chip or cartridge, and/or any other medium from which a processor or computer is adapted to read.
- Processor 310 and/or memory 320 may be arranged in any suitable physical arrangement.
- processor 310 and/or memory 320 may be implemented on a same board, in a same package (e.g., system-in-package), on a same chip (e.g., system- on-chip), and/or the like.
- processor 310 and/or memory 320 may include distributed, virtualized, and/or containerized computing resources. Consistent with such embodiments, processor 310 and/or memory 320 may be located in one or more data centers and/or cloud computing facilities.
- memory 320 may include non-transitory, tangible, machine readable media and/or a medium that includes executable code that when run by one or more processors (e.g., processor 310) may cause the one or more processors to perform the methods described in further detail herein.
- memory 320 includes instructions for a deep learning module 330 that may be used to implement and/or emulate the systems and models, and/or to implement any of the methods described further herein.
- deep learning module 330 may receive an input 340, e.g., such as a question for corpus of documents, via a data interface 315. Deep learning module 330 may also receive and/or access one or more corpora of documents for the question.
- Data interface 315 may be any of a user interface that receives a question for a QA dataset, or a communication interface that may receive or retrieve a previously requested question from another system and/or stored by a database.
- Deep learning module 330 may generate an output 350, such as an answer result from a corpus of documents based on a question of input 340.
- the answer result may include one or more documents and/or passages from the documents determined using deep learning module 330, which may be ranked, listed, categorized, and/or scored based on their relevance to the question determined using a document- level retrieval model and a passage-level retrieval model.
- deep learning module 330 may further includes a dense hierarchical retrieval module 331 and a document and passage encoder module 332.
- Dense hierarchical retrieval module 331 and document and passage encoder module 332 may be used to provide a better result to an open-domain question by using a DHR methodology that considers the question using a dense document-level retrieval model in combination with a dense passage-level retrieval model.
- a question for open-domain QA on a corpus of documents may be received and encoded by dense hierarchical retrieval module 331 for a corpus of documents identified for searching using the question.
- the dense document-level retrieval model may use encoded documents (e.g., based on their abstract, ToC, and/or other document structure) that are encoded and indexed by document and passage encoder module 332.
- Dense hierarchical retrieval module 331 may utilize document and passage encoder module 332 to identify one or more documents having passages from a corpus of documents. Unrelated documents may be filtered by dense hierarchical retrieval module 331 and one or more documents for searching and/or ranking may be identified.
- the dense passage-level retrieval model of document and passage encoder module 332 may be used when encoding passages from the document(s) identified from the document-level retrieval model and the encoded question.
- the encoded passages and question may be used by the dense passage-level retrieval model to obtain top-rated passages from top-rated documents, which are scored or ranked for return to the question from the open-domain QA on the corpus of documents.
- the relevance score of returned documents and/or passages may be determined based on combination relevance scores of document relevance scores from the dense document-level retrieval model and passage relevance scores from the dense passage-level retrieval model. Further functionality of dense hierarchical retrieval module 331 and document and passage encoder module 332 are discussed in further detail with regard to FIGS. 4-6.
- deep learning module 330 and sub- modules 331-332 may be implemented using hardware, software, and/or a combination of hardware and software.
- SMS is a gRPC microservice that hosts and executes machine learning models. SMS takes in parameters via a Protobuf file, and executes models using those input parameters. SMS returns a response back to the client (e.g., user device) according to the response parameters defined.
- the SMS implementation runs on an environment for containerized applications (e.g., Salesforce Application Model (SAM)) that is separate or independent from the core applications of the multi-tenant database system, such as system 116. SMS may provide for faster deployment of the model.
- containerized applications e.g., Salesforce Application Model (SAM)
- SAM Salesforce Application Model
- SMS also provides for isolation/containerization of Java virtual machines (JVMs), so that a crash related to its model execution will not impact or affect the application servers of the database system.
- JVMs Java virtual machines
- the SMS plugin is isolated code that can initialize the model data for a particular model type, perform model-specific feature processing, and execute model based on feature vectors and other parameters.
- the plugin architecture provides various advantages, including that changes can be made to plugin code without making changes to model executor code, and that concerns about load balancing, routing, and parallelizing are reduced or eliminated with plugins.
- FIG. 4 illustrates a simplified diagram of an exemplary document and passages in a corpus of documents that may be retrieved using hierarchical retrieval of semantic -based passages in deep learning according to some embodiments.
- a document 400 in FIG. 4 displays document structures and structural elements that constitute a document having passages of text in a corpus of documents, such as articles, encyclopedic entries, training material, customer help requests and answers, and other documents in a database system.
- document 400 may be used to generate a document encoding based on one or more document structures, as well as passage encodings from short length split passages of text within the paragraphs of document 400.
- Document 400 includes a document title 402, an abstract 404, a table of contents (ToC) 406, a first section 408, and a second section 410.
- Document 400 may correspond to a document within a corpus of documents, such as an encyclopedic entry for an online encyclopedia or other searchable database and platform.
- document 400 may be viewed as a structural document, where different inputs and data is extracted and used as input for a document- level retrieval model and a passage-level retrieval model.
- These models for DHR may be used to determine a combination of relevance scores to better retrieve, score, and/or rank documents and passages for a question submitted for open-domain QA.
- the dense document- level retrieval model may utilize encoded documents from an index.
- the encoded documents may be encoded from the corpus of documents based on one or more document structures and may be indexed in an offline environment.
- the index may be accessed and used with an encoding of the question for document-level retrieval.
- document 400 For document- level retrieval, one or more document structures are required to be encoded for each of the documents in the corpus of documents. Encoding may correspond to creating an embedding or vector representation (e.g., having n-features, variables, or attributes) that represents the document based on the component parts of the document structure(s) used to encode the document.
- document 400 includes ToC 406 that may correspond to a document structure used to encode document 400 for document-level retrieval.
- document title 402 and/or abstract 404 may also be used for the document-level retrieval encoding.
- Document 400 further includes abstract 404, first section 408, and second section 410 that may be used when encoding passages of document 400 for passage-level retrieval.
- ToC 406 includes a section and/or subsection title list 412, which is then extracted and cleaned using an extraction operation 414 to generate a hierarchical title list 416.
- Hierarchical title list 416 may then be used for encoding document 400 for a document- level retrieval model and document-level retriever when a question is queried and encoded.
- each document may be viewed as a structural collection having sections S, subsections Ss, and their corresponding paragraphs.
- Each section or subsection has a corresponding title.
- each document D may also contain its own nested table of titles 11 Tsi [Ts sf , ...; TSsn]]; [Ts m [Ts s f, ...; T 3 ⁇ 4/ ]]].
- T I) may be viewed as the unique identity to distinguish documents in the corpus.
- abstract 404, first section 408, second section 410, and/or other text of document 400 may be split into short length passages.
- in-section split passage text 418 may be generated when splitting abstract 404, first section 408, and second section 410 into short length passages. This may be done by only splitting the paragraphs under the same section or subsection title into limited length passages.
- Each passage may correspond to a sequence of tokens with a nested title.
- There may be M total passages in a corpus C ⁇ Pi; Pr, ...; PM ⁇ and, for each passage P, the corresponding document that it belongs to may be determined by looking at the T D .
- p d is defined as a function that maps a given passage p to its document d
- g : d P maps a given document d to its passages P.
- the passages generated from abstract 404, first section 408, and second section 410 further include section title information and, during training, in-Doc and/or in-Sec negative training may be used to train the passage-level retrieval model.
- Extraction of hierarchical title list 416 and/or in-section split passage text 418 may use WikiExtractor code to extract the clean text-portion of articles and remove semi-structured data, such as tables, infoboxes, lists, and/or disambiguation pages.
- hierarchical title list 416 is retained for document 400. Further, the text under the same section may be concatenated and each section may be split into multiple, disjoint text blocks with maximum length not over 100 words.
- FIG. 5 illustrates a simplified diagram of exemplary components for hierarchical retrieval of semantic -based passages in deep learning according to some embodiments.
- dense hierarchical retrieval using dense document-level and dense passage-level retrieval models in FIG. 5 can be an implementation of deep learning module 330 of computing device 300.
- Components 500 of FIG. 5 may correspond to a system diagram for dense hierarchical retrieval of semantic-based features and passages from a corpus of documents using document-level and passage-level retrieval models.
- a question 501 may be provided for an open-domain QA system and may be encoded as Eo(q) using a question encoder.
- a document-level retriever 502 may be used, which may correspond to the document-level retrieval model used with encoded documents Eo(d) (e.g., based on their encoded document structures and elements).
- the documents may correspond to those in a corpus of documents 504, which may be retrieved using document-level encoding and/or embeddings of the documents.
- Corpus of documents 504 may correspond to a large set of documents that may include different subject documents. Within corpus of documents 504, each document is associated with passages, which may be broken up from corpus of documents 504 for further passage-level encoding of the passage-level retrieval model.
- Top k ⁇ documents 506 are determined based on the document-level retrieval model from the encoded documents and question. Unrelated documents may be filtered and one or more top rated or ranked documents may be returned based on the trained model for document-level retriever 502.
- passage-level retriever 508 may execute a passage-level retrieval model to determine top ranked or rated passages from those documents.
- first a document-passages mapping may be utilized to determine passages mapped to the encoded documents that were retrieved for top k ⁇ documents 506.
- the mapped passages may be identified as passages from top k ⁇ documents 510. Once passages from top k ⁇ documents 510 are determined, these passages may be encoded and provided to passage-level retriever 508.
- the encoding of question 501 may also be used with passage-level retriever 508, where passages from top k ⁇ documents 510 are encoded in order for the passage-level retrieval model to determine scored passages from top k ⁇ documents 512.
- passage-level retriever 508 Once the model of passage-level retriever 508 is applied to the encoded passages Ep(p) from passages from top k ⁇ documents 510, scored passages from top k ⁇ documents 512 may then be determined as a smaller filtered subset of the documents and corresponding passages that may be relevant to question 501.
- a reranking may be performed that combines the relevance scores of top k ⁇ documents 506 and the relevance scores of scored passages from top k ⁇ documents 512.
- the reranking may combine the scores to obtain reranked top fe passages 514 based on a combination relevance score from document-level retriever 502 and passage-level retriever 508. This allows for DHR using both document-level retrieval and passage-level retrieval models to search question 501 with corpus of documents 504.
- training operations may be executed for DHR.
- the first section of documents within the corpus of documents may be the description and/or summary of the document that contains information central to the topic in the document, such as an encyclopedic entry. This may include an abstract, and the document may further include a ToC that highlights the sections and subsections within the document.
- a nested table of contents may be linearized as 11 Tsi [T Ss r, ...; T 3 ⁇ 4 detergent]]; ...;
- the final document D may be represented as [CLS] 7b [SEP] WD [SEP] T ta bie [SEP].
- Dense document-level retrieval may use a question encoder and a document encoder based on Bidirectional Encoder Representations from Transformers (BERT) deep NN model.
- BERT corresponds to a language representation deep learning model that allows training of deep bidirectional representations in NN model layers.
- QA data sets for training data may be used. These may include standardized open-domain QA evaluation data sets including Natural Questions (NQ) having questions mined from real Google® searches and their corresponding answers in encyclopedic articles identified by annotators, TriviaQA having a set of trivia questions with answers that were scraped from the web, WebQuestions having questions selected using Google® Suggest API and answers corresponding to entities in Freebase, and/or CuratedTREC (TREC) having questions from TREC QA tracks as well as various web sources intended for open-domain QA from unstructured text.
- NQ Natural Questions
- TriviaQA having a set of trivia questions with answers that were scraped from the web
- WebQuestions having questions selected using Google® Suggest API and answers corresponding to entities in Freebase
- CuratedTREC having questions from TREC QA tracks as well as various web sources intended for open-domain QA from unstructured text.
- the highest-ranked passage determined using a deep learning model for Best Match 25 (BM25) that contains the answer may correspond to the positive passage. If none of the top one hundred retrieved passages includes the answer, the question may be discarded. Further, negative sampling and training on negative documents and passages (e.g., those appearing as positive passages but not including the answer) may also be used for model training, where rankings of passages may affect training of the dense model based on the training data. This may include use of in-Doc and in-Sec negatives for passages, which may be more biased or heavily weighted based on a closeness of the in-Doc and/or in-Sec negatives to a positive passage that includes the answer.
- in-Doc and in-Sec negatives for passages, which may be more biased or heavily weighted based on a closeness of the in-Doc and/or in-Sec negatives to a positive passage that includes the answer.
- the positive documents when training data sets, in the datasets containing the gold title (e.g., that title having a positive and/or best match) to a given question, the positive documents may be the documents having the gold title.
- the Top-1 document is retrieved that contains the answer in the whole document text as the positive document.
- three different types of negatives may be used. Intro negative may use a first section to represent each document and BM25 may then be used to retrieve the top documents, but which do not contain the answer in the whole document text. All-text negative may use the entire document text to represent each document and BM25 may then be used to retrieve the top documents, but which do not contain the answer in the whole document text. Further, in-batch negatives may be used from passages paired with other questions appearing in the training data set.
- Passage-level retriever 508 may further require encoding of passages using the passage-level retrieval model trained for passage-level retrieval.
- a subtitle list e.g., section and/or subsection title list
- a passage P will be represented as [CLS] title [SEP] subtitlei, subtitle2, ..., subtitle n [SEP] passage [SEP].
- a different E Q (.) may be used in dense document-level retrieval and dense passage-level retrieval models.
- Sim (q, d) ⁇ E Q (q) ,
- Positive and negative passages may be determined for training in a similar manner to dense passage retrieval (DPR).
- DPR dense passage retrieval
- a positive passage may be a mapping of the passage having the gold context in the passage set ⁇ P ⁇ .
- BM25 may be used to retrieve the top-1 passage containing the answer.
- BM25 negative and in-batch negatives may also be used.
- in-Doc negatives and in-Sec negatives may be used for retrieved passages.
- An in-Doc negative may be passages that do not contain the answer in the same document as the positive passage, while an in-Sec negative may be the other passages that do not contain the answer in the same section as the positive passage [0071]
- document-level retriever 502 is therefore applied to select top k ⁇ documents 506.
- the passages inside top k ⁇ documents 506 are sent to passage-level retriever 508 to determine scored passages from top k ⁇ documents 512, which are reranked using a combination of document and passage relevance scores to obtain reranked top fe passages 514.
- the document encoder E D encodes the documents from corpus of documents 504, which are indexed offline.
- top k ⁇ documents 506 are retrieved with embeddings closest to question q. All the passages from top k ⁇ documents 506 are retrieved from the mappings and the passage encoder E p is applied to all the retrieved passages. Scored passages from top k ⁇ documents 512 and the ranking or relevance scores from the document-level retrieval and passage-level retrieval are used to re-rank the passages.
- the retrieval ranking and/or relevance scores from both the dense document retrieval and dense passage retrieval contribute to the final ranking of reranked top fe passages 514.
- the document relevance score is combined with the passage relevance score, calculated by: Sim (q, D,) + l * Sim (q, Pi), Pi G D, where l is the coefficient used between the two scores.
- the scores may be substantially similar and therefore l may be close or equal to 1.
- iterative training may be applied to train both the document- level and passage-level retrieval models. For example, after an initial training, retraining using the data sets and positive/negatives may be used to further refine predictive decision-making and document/passage retrieval by the models.
- FIG. 6 illustrates a simplified diagram of a flowchart for hierarchical retrieval of semantic -based passages in deep learning using a document-level and passage-level retriever described in FIGS. 3, 4, and 5 according to some embodiments.
- One or more of processes 602-614 of method 600 may be implemented, at least in part, in the form of executable code stored on non-transitory, tangible, machine-readable media that when ran by one or more processors may cause the one or more processors to perform one or more of processes 602- 614.
- method 600 can be performed by one or more computing devices in environment 110 of FIGS. 1 and 2.
- the model(s) of deep learning module 330 uses data parsing, extracting, encoding, converting, and QA predicting processes to perform dense hierarchical retrieval of semantic- based passages and/or documents in a database system (e.g., system 116) based on document- level and passage-level retrieval models.
- a database system e.g., system 116
- these include the documents and corpora of documents that may be standard for the database system (e.g., articles, encyclopedic entries, training material, customer help requests and answers, and other documents that may be relevant to a particular database system) and provided for customers of the CRM or other system.
- method 600 starts with a process 602.
- deep learning module 330 receives a question for a corpus of documents, wherein the documents in the corpus are associated with a respective set of passages.
- the corpus of documents may correspond to corpus of documents 504 and may include documents similar to document 400, such as informational articles, encyclopedic entries, help request, training manuals, pamphlets or other articles about a subject that provide information.
- Question 501 may correspond to an input question that is a query for open-domain QA.
- the corpus of documents and an index of encoded documents are accessed.
- a dense document-level retrieval model may be used to generate encodings of documents, including document 400 and/or from corpus of documents 504, which may be designated as Erkd).
- document-level retriever 502 may retrieve En(d) after encoding for the dense model.
- Question 501 may be encoded as Eg(q), which may be encoded using a question encoder that may be utilized with a document encoder generating E D ( I), for example, for document-level retriever 502.
- document relevance scores of the documents to the question are determined using a document-level retrieval model.
- Document-level retriever may retrieve top documents 506 based on encoding Eg(q) of question 501.
- the document relevance scores may correspond to scored, ranked, or otherwise weighted values for determining a relevance of top k ⁇ documents 506 to question 501.
- top k ⁇ documents 506 may be scored and/or ordered based on their encodings, E D ( I), which may be determined from one or more document structures of document 400 and/or documents from corpus of documents 504.
- unrelated documents are filtered from the documents based on the document relevance scores.
- top k ⁇ documents 506 may correspond to a filtered subset of the documents from corpus of documents 504 based on their corresponding relevance scores.
- document-to-passages mapping may be required to determine passages from encoding E D ( I) of the documents in top k ⁇ documents 506. This allows a return of passages from top k ⁇ documents 510.
- the passages in at least one of the documents are encoded using a passage-level retrieval model.
- Passage-level retrieval 508 may encode passages from top k ⁇ documents 510 to generate encoded passages Ep(p).
- top-rated passages are obtained for the question.
- scored passages from top k ⁇ documents 512 may be returned by passage-level retrieval 508. This may be determined using the corresponding dense model based on the encodings of the question and passages.
- relevance scores from top k ⁇ documents 506 and scored passages from top k ⁇ documents 512 may be combined and/or processed to obtain reranked top fe passages 514. These top ranked passages may then be provided as output for question 501 for open-domain QA on corpus of documents 504.
- one or more neural network models may be trained on the training data.
- the neural network may perform pre-processing on training data, for example, for each word, portion of a word, or character in a training text.
- the embeddings are encoded, for example, with one or more encoding layers of the neural network to generate respective vectors.
- a pre-processing layer generates an embedding for each word in the text input sequence.
- Each embedding can be a vector.
- pre-trained vectors of a certain dimensionality may be used.
- the embedding may include partial word embeddings related to portions of a word. For example, the word “where” includes portions “wh,” “whe,” “her,” “ere,” and “re.” Partial word embeddings can help to enrich word vectors with subword information / FastText.
- a sequence of word vectors may be generated based on the sequences of words within the documents and document structures.
- a text input sequence e.g., used for training
- a mask layer masks such numbers so that they are ignored or not processed in subsequent layers, for example, to help reduce training time.
- the encoding layers learn high-level features from the words of textual input sequence.
- Each encoding layer generates encodings (e.g., vectors) which map the words in the text input sequence to a higher dimensional space.
- the encodings can encode the semantic relationship between words.
- the encoding layers or encoder stack is implemented with a recurrent neural network (RNN).
- RNNs are deep learning models that process vector sequences of variable length. This makes RNNs suitable for processing sequences of word vectors.
- the encoding layers can be implemented with one or more gated recurrent units (GRUs).
- GRUs gated recurrent units
- a GRU is a specific model of recurrent neural network (RNN) that intends to use connections through a sequence of nodes to perform machine learning of tasks. GRUs help to adjust the neural network input weights to solve the vanishing gradient problem that is common issue with RNNs.
- encoding layers can be implemented with one or more long-term short-term memory (LSTM) encoders.
- LSTM long-term short-term memory
- a plurality of the GRUs may be arranged in rows.
- a first row of the GRUs looks at or operates on information (e.g., embeddings or encodings) for respective words in the text input sequence in a first (e.g., “forward”) direction, with each GRU generating a corresponding state vector and passing that vector along to the next GRU in the row (e.g., as indicated by the arrows pointing from left to right).
- information e.g., embeddings or encodings
- a second row of GRUs looks at or operates on information (e.g., embeddings or encodings) for respective words in the input sequence in a second (e.g., “backward”) direction, with each GRU generating a corresponding hidden state vector and passing that vector along to the next GRU in the row.
- the weights (values) of the embedding matrix may be initialized at random and/or separately and updated/leamed using backpropagation at training time.
- embeddings may be learned end-to-end while training the machine learning engine and/or neural network model (with other features) on its classification task.
- the training will result in having one vector per character, word, phrase, or sentence, and cluster the vectors. For instance, two characters, words, phrases, or sentences having similar embeddings will end up having similar vectors, closer than distant embeddings.
- the embeddings are then flattened at a respective flattener and/or concatenated at a respective concatenator.
- the model of the neural network is trained using the concatenated features or vectors.
- the neural network may include or be implemented with a multi-layer or deep neural network or neural model, having one or more layers.
- multi-layer neural networks include the ResNet-32, DenseNet, PyramidNet, SENet, AWD-LSTM, AWD-QRNN and/or the like neural networks.
- the ResNet-32 neural network is described in further detail in He, et ak, “Deep Residual Learning for Image Recognition,” arXiv:1512.03385, submitted on December 10, 2015; the DenseNet neural network is described in further detail in Iandola, et ak, “Densenet: Implementing Efficient Convnet Descriptor Pyramids,” arXiv: 1404.1869, submitted April 7, 2014, the PyramidNet neural network is described in further detail in Han, et ak, “Deep Pyramidal Residual Networks,” arXiv: 1610.02915, submitted October 10, 2016; the SENet neural network is described in further detail in Hu, et ak, “Squeeze-and-Excitation Networks,” arXiv: 1709.01507, September 5, 2017; the AWD-LSTM neural network is described in further detail in Bradbury, et ak, “Quasi-Recurrent Neural Networks,” arXiv: 1611.01576, submitted on November 5, 2016;
- Each neural network layer can operate or process the features or vectors, performing, for example, regularization (e.g., L2 and LI regularization, Early stopping, etc.), normalization, and activation.
- each neural network layer may include a dense layer, batch normalization, and a dropout for deep learning.
- a respective rectifier linear unit (ReLU) at the end of each layer performs a ReLU activation function.
- An output layer of the neural network performs a softmax function to produce or generate one single model for all contexts.
- the global model predicts case objects for present queries or a test case object into a database system, such as system 116.
- the model comprises or represents a probability distribution for embeddings within a document and/or document structure (whether standard or custom) with respect to a given training document and/or document structure (e.g., corpus or corpora of documents having passages and document structures). For the distribution, each embedding has a corresponding numerical value representing or indicative of the relevance of that such embedding to the present search.
- the softmax layer can be implemented with a high-rank language model, called Mixture of Softmaxes (MoS), to alleviate softmax bottleneck issues.
- MoS Mixture of Softmaxes
- FIGS. 3, 4, 5, and 6 are merely examples of deep learning module 330 and corresponding method 600 for training and use which should not unduly limit the scope of the claims.
- computing devices such as computing device 300, may include non-transitory, tangible, machine readable media that include executable code that when ran by one or more processors (e.g., processor 310) may cause the one or more processors to perform the processes of method 600.
- machine-readable media that may include the processes of method 600 are, for example, floppy disk, flexible disk, hard disk, magnetic tape, any other magnetic medium, CD-ROM, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, RAM, PROM, EPROM, FLASH-EPROM, any other memory chip or cartridge, and/or any other medium from which a processor or computer is adapted to read.
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP22704645.5A EP4341829A1 (en) | 2021-05-17 | 2022-01-26 | Systems and methods for hierarchical retrieval of semantic-based passages in deep learning |
CN202280045940.5A CN117581223A (en) | 2021-05-17 | 2022-01-26 | System and method for hierarchical acquisition of semantic-based chapters in deep learning |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US202163189505P | 2021-05-17 | 2021-05-17 | |
US63/189,505 | 2021-05-17 | ||
US17/533,613 US20220374459A1 (en) | 2021-05-17 | 2021-11-23 | Systems and methods for hierarchical retrieval of semantic-based passages in deep learning |
US17/533,613 | 2021-11-23 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022245406A1 true WO2022245406A1 (en) | 2022-11-24 |
Family
ID=80520325
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2022/013926 WO2022245406A1 (en) | 2021-05-17 | 2022-01-26 | Systems and methods for hierarchical retrieval of semantic-based passages in deep learning |
Country Status (2)
Country | Link |
---|---|
EP (1) | EP4341829A1 (en) |
WO (1) | WO2022245406A1 (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7730478B2 (en) | 2006-10-04 | 2010-06-01 | Salesforce.Com, Inc. | Method and system for allowing access to developed applications via a multi-tenant on-demand database service |
US7779039B2 (en) | 2004-04-02 | 2010-08-17 | Salesforce.Com, Inc. | Custom entities and fields in a multi-tenant database system |
WO2012040677A1 (en) * | 2010-09-24 | 2012-03-29 | International Business Machines Corporation | Efficient passage retrieval using document metadata |
US20170140034A1 (en) * | 2015-11-16 | 2017-05-18 | International Business Machines Corporation | Concept identification in a question answering system |
US9727637B2 (en) * | 2014-08-19 | 2017-08-08 | International Business Machines Corporation | Retrieving text from a corpus of documents in an information handling system |
-
2022
- 2022-01-26 WO PCT/US2022/013926 patent/WO2022245406A1/en active Application Filing
- 2022-01-26 EP EP22704645.5A patent/EP4341829A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7779039B2 (en) | 2004-04-02 | 2010-08-17 | Salesforce.Com, Inc. | Custom entities and fields in a multi-tenant database system |
US7730478B2 (en) | 2006-10-04 | 2010-06-01 | Salesforce.Com, Inc. | Method and system for allowing access to developed applications via a multi-tenant on-demand database service |
WO2012040677A1 (en) * | 2010-09-24 | 2012-03-29 | International Business Machines Corporation | Efficient passage retrieval using document metadata |
US9727637B2 (en) * | 2014-08-19 | 2017-08-08 | International Business Machines Corporation | Retrieving text from a corpus of documents in an information handling system |
US20170140034A1 (en) * | 2015-11-16 | 2017-05-18 | International Business Machines Corporation | Concept identification in a question answering system |
Non-Patent Citations (5)
Title |
---|
BRADBURY ET AL.: "Quasi-Recurrent Neural Networks", ARXIV:1611.01576, 5 November 2016 (2016-11-05) |
HAN ET AL.: "Deep Pyramidal Residual Networks", ARXIV:1610.02915, 10 October 2016 (2016-10-10) |
HE ET AL.: "Deep Residual Learning for Image Recognition", ARXIV:1512.03385, 10 December 2015 (2015-12-10) |
HU ET AL.: "Squeeze-and-Excitation Networks", ARXIV:1709.01507, 5 September 2017 (2017-09-05) |
IANDOLA ET AL.: "Densenet: Implementing Efficient Convnet Descriptor Pyramids", ARXIV:1404.1869, 7 April 2014 (2014-04-07) |
Also Published As
Publication number | Publication date |
---|---|
EP4341829A1 (en) | 2024-03-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11403457B2 (en) | Processing referral objects to add to annotated corpora of a machine learning engine | |
US11392828B2 (en) | Case object context embeddings for machine learning training of case context | |
US11436481B2 (en) | Systems and methods for named entity recognition | |
US11328203B2 (en) | Capturing organization specificities with embeddings in a model for a multi-tenant database system | |
US11657231B2 (en) | Capturing rich response relationships with small-data neural networks | |
US20200090034A1 (en) | Determining Intent from Unstructured Input to Update Heterogeneous Data Stores | |
US9594850B2 (en) | Method and system utilizing a personalized user model to develop a search request | |
US9720944B2 (en) | Method for facet searching and search suggestions | |
US10025819B2 (en) | Generating a query statement based on unstructured input | |
US20220374459A1 (en) | Systems and methods for hierarchical retrieval of semantic-based passages in deep learning | |
US9665643B2 (en) | Knowledge-based entity detection and disambiguation | |
US20200097560A1 (en) | Ranking Enterprise Search Results Based on Relationships Between Users | |
US11720589B2 (en) | System and method for transformation of unstructured document tables into structured relational data tables | |
US10970336B2 (en) | Predicting entities for search query results | |
US10853395B2 (en) | Extraction of keywords for generating multiple search queries | |
US11347733B2 (en) | System and method for transforming unstructured numerical information into a structured format | |
US20140289236A1 (en) | Refining search results for a compound search query | |
Zoupanos et al. | Efficient comparison of sentence embeddings | |
US20200065395A1 (en) | Efficient leaf invalidation for query execution | |
Zhang et al. | Exploring linked data with contextual tag clouds | |
US9547701B2 (en) | Method of discovering and exploring feature knowledge | |
US20200293521A1 (en) | Optimized search service | |
WO2022245406A1 (en) | Systems and methods for hierarchical retrieval of semantic-based passages in deep learning | |
CN117581223A (en) | System and method for hierarchical acquisition of semantic-based chapters in deep learning | |
US11120096B2 (en) | Method and system for generating an object card |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22704645 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023571263 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022704645 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022704645 Country of ref document: EP Effective date: 20231218 |