WO2014070197A1 - Procédé et appareil d'agrégation avec généralisation d'informations - Google Patents

Procédé et appareil d'agrégation avec généralisation d'informations Download PDF

Info

Publication number
WO2014070197A1
WO2014070197A1 PCT/US2012/063343 US2012063343W WO2014070197A1 WO 2014070197 A1 WO2014070197 A1 WO 2014070197A1 US 2012063343 W US2012063343 W US 2012063343W WO 2014070197 A1 WO2014070197 A1 WO 2014070197A1
Authority
WO
WIPO (PCT)
Prior art keywords
generalized
phrase
constituent
specifications
phrase specifications
Prior art date
Application number
PCT/US2012/063343
Other languages
English (en)
Inventor
William Anthony BRADSHAW
Ehud Baruch REITER
Original Assignee
Data2Text Limited
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 Data2Text Limited filed Critical Data2Text Limited
Priority to PCT/US2012/063343 priority Critical patent/WO2014070197A1/fr
Publication of WO2014070197A1 publication Critical patent/WO2014070197A1/fr
Priority to US14/702,325 priority patent/US9600471B2/en
Priority to US15/421,925 priority patent/US10216728B2/en
Priority to US16/257,800 priority patent/US20190228077A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/40—Processing or translation of natural language
    • G06F40/55—Rule-based translation
    • G06F40/56—Natural language generation

Definitions

  • Embodiments of the present invention relate generally to natural language generation technologies and, more particularly, relate to a method, apparatus, and computer program product for aggregating phrase specifications.
  • a natural language generation (NLG) system is configured to transform raw input data that is expressed in a non-linguistic format into a format that can be expressed linguistically, such as through the use of natural language.
  • raw input data may take the form of a value of a stock market index over time and, as such, the raw input data may include data that is suggestive of a time, a duration, a value and/or the like. Therefore, an NLG system may be configured to input the raw input data and output text that linguistically describes the value of the stock market index; for example, "Securities markets rose steadily through most of the morning, before sliding downhill late in the day.”
  • Data that is input into a NLG system may be provided in, for example, a recurrent formal structure.
  • the recurrent formal structure may comprise a plurality of individual fields and defined relationships between the plurality of individual fields.
  • the input data may be contained in a spreadsheet or database, presented in a tabulated log message or other defined structure, encoded in a 'knowledge representation' such as the resource description framework (RDF) triples that make up the Semantic Web and/or the like.
  • the data may include numerical content, symbolic content or the like. Symbolic content may include, but is not limited to, alphanumeric and other non- numeric character sequences in any character encoding, used to represent arbitrary elements of information.
  • the output of the NLG system is text in a natural language (e.g. English, Japanese or Swahili), but may also be in the form of synthesized speech.
  • a method comprises identifying two or more generalized phrase specifications.
  • the two or more generalized phrase specifications contain at least one aggregatable constituent.
  • the method of this embodiment may also include generating an aggregated phrase specification from the two or more generalized phrase specifications.
  • the aggregated phrase specification comprises a specification for a combined noun phrase generated from the aggregatable constituents and one or more additional constituents based on a determined level of generalization.
  • an apparatus includes at least one processor and at least one memory including computer program code with the at least one memory and the computer program code being configured, with the at least one processor, to cause the apparatus to at least identify two or more generalized phrase specifications.
  • the two or more generalized phrase specifications contain at least one aggregatable constituent.
  • the at least one memory and computer program code may also be configured to, with the at least one processor, cause the apparatus to generate an aggregated phrase specification from the two or more generalized phrase specifications.
  • the aggregated phrase specification comprises at least one of a combined noun phrase generated from the at least one aggregatable constituents and one or more additional constituents based on a determined level of generalization.
  • a computer program product may be provided that includes at least one non-transitory computer-readable storage medium having computer-readable program instructions stored therein with the computer- readable program instructions including program instructions configured to identify two or more generalized phrase specifications.
  • the two or more generalized phrase specifications contain at least one aggregatable constituent.
  • the computer-readable program instructions may also include program instructions configured to generate an aggregated phrase specification from the two or more generalized phrase specifications.
  • the aggregated phrase specification comprises at least one of a combined noun phrase generated from the at least one aggregatable constituents and one or more additional constituents based on a determined level of generalization.
  • an apparatus includes means for identifying two or more generalized phrase specifications.
  • the two or more generalized phrase specifications contain at least one aggregatable constituent.
  • the apparatus of this embodiment may also include means for generating an aggregated phrase specification from the two or more generalized phrase specifications.
  • the aggregated phrase specification comprises at least one of a combined noun phrase generated from the at least one aggregatable constituents and one or more additional constituents based on a determined level of generalization.
  • Figure 1 is a schematic representation of a natural language generation environment that may benefit from some example embodiments of the present invention
  • Figure 2 illustrates an example flow diagram that may be performed by an aggregator in accordance with some example embodiments of the present invention
  • Figure 3 illustrates a block diagram of an apparatus that embodies a natural language generation environment having an aggregator in accordance with some example embodiments of the present invention.
  • FIGS. 4-7 illustrate flowcharts that may be performed by an aggregator in accordance with some example embodiments of the present invention.
  • words, phrases, sentences or the like may be aggregated to enhance readability, for example instead of "Stocks retreated from a broad advance yesterday. Stocks closed mixed", an aggregated sentence may recite: “Stocks retreated from a broad advance yesterday and closed mixed.” As can be seen from this example, the latter sentence is more readable and flows much more naturally.
  • "Pressure is stable” and “Temperature is stable” can be aggregated into a more readable sentence: "Pressure and temperature are stable”.
  • the complexity of the words, phrases, sentences or the like may hinder the ability for a natural language generation system to aggregate words, phrases, sentences or the like; for example, aggregating sentences with detailed numeric values like: "Pressure is stable at 20psi” and "Temperature is stable at 30C".
  • some example embodiments that are described herein are configured to aggregate phrase specifications by generalizing their respective properties or constituents, such as the detailed numeric values in the example above (e.g. 20 psi and 30C).
  • a vague descriptor that generalizes the value of 20 psi and 30C such as "within their normal range” or "within a standard operating range” would enable aggregation of sentences that would otherwise not be aggregatable.
  • a resultant aggregated sentence may be: "Pressure and temperature are within their normal range”.
  • phrase specification is a specification of the content of a linguistic constituent such as a sentence.
  • representations of content include, but are not limited to, meaning text theory (e.g. SemR, DSyntR and/or SSyntR), lambda calculus representations of semantics, case frames, messages, pre-constructed surface form fragments and/or like.
  • one or more phrase specifications and a domain-specific function which specifies allowable generalizations (e.g. generalizations of constituents within the phrase specification that do not significantly reduce utility of an output text from an end- user's perspective) of those one or more phrase specifications may be identified.
  • the one or more phrase specifications may be aggregated based on the generalization and/or removal of one or more constituents (e.g. a coherent subpart of a phrase specification, such as, but not limited to, a property within a message, an argument to a predicate, a syntactic subconstituent within a larger syntactic element, a role within a case frame and/or like) within the phrase specification.
  • one or more generalized phrase specifications may be compared and those generalized phrase specifications of the one or more generalized phrase specifications that can be aggregated (e.g. are identical but for an aggregatable constituent) are placed into groups.
  • a level of generalization may then be determined that still enables the group of phrase specifications to be aggregated.
  • the aggregatable constituents may be combined or otherwise merged to create an aggregated phrase specification.
  • the aggregated phrase specification may contain one or more additional constituents based on the determined level of generalization.
  • Figure 1 is an example block diagram of example components of an example natural language generation environment 100.
  • the natural language generation environment 100 comprises a natural language generation system 102, message store 104, a domain model 106 and/or linguistic resources 108.
  • the natural language generation system 102 may take the form of, for example, a code module, a component, circuitry and/or the like.
  • the components of the natural language generation environment 100 are configured to provide various logic (e.g. code, instructions, functions, routines and/or the like) and/or services related to the natural language generation system, the microplanner and a referring expression generation system.
  • a message store 104 or knowledge pool is configured to store one or more messages that are accessible by the natural language generation system 102.
  • Messages are one example of a phrase specification described herein and are language independent data structures that correspond to informational elements in a text and/or collect together underlying data, referred to as properties, arguments or slots, which can be presented within a fragment of natural language such as a phrase or sentence.
  • Messages may be represented in various ways; for example, each property may consist of a named attribute and its corresponding value; these values may recursively consist of sets of named attributes and their values, and each message may belong to one of a set of predefined types.
  • the concepts and relationships that make up messages may be drawn from an ontology (e.g.
  • the domain model 106 is a representation of information about a particular domain and specifies how information about a domain is communicated in language.
  • a domain model may contain an ontology that specifies the kinds of objects, instances, concepts and/or the like that may exist in the domain in concrete or abstract form, properties that may be predicated of the objects, concepts and the like, relationships that may hold between the objects, concepts and the like, and representations of any specific knowledge that is required to function in the particular domain.
  • the domain model 106 may also contain a set of rules for generalization, removal and/or aggregation of phrase specifications that are generated based on a corpus analysis, domain analysis or the like.
  • a natural language generation system such as natural language generation system 102, is configured to generate words, phrases, sentences, text or the like which may take the form of a natural language text.
  • the natural language generation system 102 comprises a document planner 1 12, a microplanner 1 14 and/or a realizer 1 16.
  • the natural language generation system 102 may also be in data communication with the message store 104, the domain model 106 and/or the linguistic resources 108.
  • the linguistic resources include, but are not limited to, text schemas, aggregation rules, reference rules, lexicalization rules and/or grammar rules that may be used by one or more of the document planner 1 12, the microplanner 1 14 and/or the realizer 1 16.
  • Other natural language generation systems may be used in some example embodiments, such as a natural language generation system as described in Building Natural Language Generation Systems by Ehud Reiter and Robert Dale, Cambridge University Press (2000), which is incorporated by reference in its entirety herein.
  • the document planner 1 12 is configured to input one or more messages from the message store 104.
  • the document planner 1 12 may comprise a content determination process that is configured to select the messages, such as the messages that contain a representation of the data that is to be output via a natural language text.
  • the document planner 1 12 may also comprise a structuring process that determines the order of messages to be included in a text.
  • the document planner 1 12 may access one or more text schemas for the purposes of content determination and document structuring.
  • the output of the document planner 1 12 may be a tree-structured object or other data structure that is referred to as a document plan.
  • the leaf nodes of the tree may contain the messages, and the intermediate nodes of the tree structure object may be configured to indicate how the subordinate nodes are related (e.g. elaboration, consequence, contrast, sequence and/or the like) to each other.
  • the microplanner 1 14 is configured to construct a realization specification based on the document plan output from the document planner 1 12, such that the document plan may be expressed in natural language.
  • the microplanner 1 14 may convert one or more messages into a text specification by performing aggregation, lexicalization and referring expression generation.
  • a text specification is a specification of the content of a linguistic constituent such as a sentence and contains a set of instructions for a realizer, such as realizer 1 16, to produce a grammatically well-formed text.
  • the output of the microplanner 1 14, in some example embodiments, is a tree-structured realization specification whose leaf-nodes are text specifications, and whose internal nodes express rhetorical relations between the leaf nodes.
  • the microplanner 1 14 and the aggregator 120 are further described with reference to Figure 2.
  • a realizer 1 16 is configured to traverse a text specification output by the microplanner 1 14 to express the text specification in natural language.
  • the realization process that is applied to each text specification makes use of a grammar (e.g. the grammar of the linguistic resources 108) which specifies the valid syntactic structures in the language and further provides a way of mapping from phrase specifications into the corresponding natural language sentences.
  • the output of the process is, in some example embodiments, a natural language text.
  • Figure 2 illustrates an example flow diagram that may be performed by a microplanner 1 14, an aggregator 120 and/or the like in accordance with some example embodiments of the present invention.
  • the microplanner 1 14 may cause the aggregator 120 to input or the aggregator 120 may otherwise input one or more phrase specifications.
  • the aggregator 120 may then identify or otherwise determine a constituent in the one or more phrase specifications that is aggregatable.
  • the aggregatable constituent may refer to an entity, such as heart rate, respiration rate, temperature, pressure and/or the like.
  • a phrase specification may contain multiple aggregatable constituents and, as such, the use of aggregatable constituent herein should not be considered as limiting the disclosure to a single aggregatable constituent in a phrase specification.
  • a phrase specification may also have one or more constituents that are generalizable or removable.
  • Constituents that are generalizable or removable may be defined by the domain model 106 for a particular domain and/or may be identified based on a corpus analysis, business rules, user settings and/or the like. For example, a particular value, such as a temperature, may be generalized by a range such as "below the normal range", “in the normal range” or “above the normal range” in some domains, but in other domains such a generalization may be improper.
  • the domain model 106 may contain a generalized constituent list which provides a list of alternative generalized constituents for a given generalizable constituent.
  • the domain model 106 may also define the various levels of generalization for each generalizable constituent. For example, the domain model may identify "within a normal range" as the most generalized constituent; whereas, other more specific generalizations may be available, such as "between 25C and 35C". Alternatively or additionally, the microplanner 1 14, the aggregator 120 or the like may receive or otherwise determine, via a reordering flag, whether the one or more phrase specifications can be reordered for the purposes of aggregation. As such, and as shown in block 202, the one or more phrase specifications may be generalized.
  • Such a generalization may include, but is not limited to, generalizing all of the constituents that are marked as generalizable by the aggregator 120 and/or removing all of the constituents that are marked as removable by the aggregator 120.
  • the constituents may be generalized using a generalized constituent marked as most generalized in the generalized constituent list or predefined constituent list.
  • the generalized constituent list may contain one or more constituents that may be selected by the aggregator 120 to replace a generalizable constituent in a phrase specification.
  • the constituent "last Sunday” may be generalized by, from least generalized or lowest level of generalization to most generalized or highest level of generalization, "earlier this week", “earlier this month", or "in the past".
  • a portion of the constituents marked as generalizable may be generalized and/or a portion of the constituents marked as removable may be removed.
  • a group of generalized phrase specifications that can be aggregated together are identified by the aggregator 120. For example, sequences of phrase specifications (if reordering is not permitted based on the reordering flag) or subsets of the generalized phrase specifications (if reordering is permitted based on the reordering flag) may be identified as being aggregatable in an instance in which the sequences or subsets of phrase specifications are identical except for their identified aggregatable constituent.
  • phrase specifications may also be aggregated based on an indication in the domain model 106, business rules, a user setting and/or the like.
  • the one or more phrase specifications are generalized to a highest level of generalization at block 202 to identify groups of phrase specifications that can be aggregated. Once those groups of phrase specifications are identified, then at block 206, the level of generalization may be reduced or otherwise lowered so long as the group of phrase specifications can still be aggregated. For example, constituents may be added back that were removed so long as the group of phrase specifications can still be aggregated. As is shown in block 206, a level of generalization that permits the group of phrase specifications to still be aggregated is determined by the aggregator 120. In some example embodiments, the constituents that were removed at block 202 may be added back to the phrase specifications in the group providing the phrase specifications in the group are still aggregatable.
  • a generalized constituent may be added back to the phrase specification instead of the removed constituent if the generalized constituent enables the group of phrase specification to still be aggregatable whereas adding the removed constituent would render the group of phrase specifications no longer aggregatable.
  • less generalized constituents, as defined by the generalized constituent listing, may replace the generalized constituents providing the phrase specifications in the group are still aggregatable.
  • the aggregator 120 may incrementally generalize one or more phrase specifications until the one or more phrase specifications are aggregatable, alternatively the aggregator 120 may determine multiple levels of generalization for each phrase specification and aggregate the phrase specifications based on the lowest level of generalization, and/or the like.
  • an aggregated phrase specification is generated.
  • the aggregated phrase specification may contain a combination of the constituents, such as a combined noun phrase, that contains the identified aggregatable constituents and further contains one or more additional constituents based on the determined level of generalization.
  • the aggregated phrase specification may contain the combined noun phrase and the one or more generalized constituents but may otherwise be a copy of a phrase specification of the one or more phrase specifications in the group of phrase specifications.
  • the aggregated phrase specification may be output by the aggregator 120 to the microplanner and/or realizer for use in generating an output text.
  • the aggregator 120 may input one or more phrase specifications (shown as sentences in this example), such as “heart rate was stable at 72 yesterday", “mean blood pressure was unstable yesterday with mean value 95” and "respiratory rate was stable at 16 yesterday”.
  • phrase specifications shown as sentences in this example
  • those constituents that are generalizable or removable may be identified. For example, “at 72" in “heart rate was stable at 72 yesterday” and “at 16” in “respiratory rate was stable at 16 yesterday” may be marked as generalizable based on the domain model, business rules, a user setting and/or the like.
  • both “at 72" and “at 16” may be generalized as “within the normal range” based on a generalizable constituent listing in the domain model.
  • “yesterday” in both “heart rate was stable at 72 yesterday” and “respiratory rate was stable at 16 yesterday” may be marked as removable.
  • Both “with mean value 95” and “yesterday” may also be marked as removable in "mean blood pressure was unstable yesterday with mean value 95".
  • Those constituents marked as removable may be indicated as such by the domain model, business rules, a user setting and/or the like.
  • the one or more phrase specifications may be generalized by removing each of the removable constituents and by replacing each of the generalizable constituents with generalized constituents.
  • the one or more generalized phrase specifications may then contain: "heart rate was stable within normal range", “mean blood pressure was unstable” and “respiratory rate was stable within normal range” in some example embodiments.
  • a group of generalized phrase specifications may then be identified.
  • a group of generalized phrase specifications may include those phrase specifications that can be aggregated (e.g. phrase specifications that are identical but for the aggregatable constituent).
  • phrase specifications that are identical but for the aggregatable constituent.
  • “heart rate was stable within normal range” and “respiratory rate was stable within normal range” may be determined as aggregatable because they are identical but for the aggregatable constituents "heart rate” and “respiratory rate” and thus form a group.
  • “Mean blood pressure was unstable” is not aggregatable with the other phrase specifications based on the constituent "was unstable”.
  • phrase specifications within the group are analyzed to determine the level of generalization that would still enable the phrase specifications within the group to be aggregated. For example, the constituent "yesterday” was removed from both phrase specifications and, as such, the addition of the constituent "yesterday” back to the phrase specifications would still enable the phrase specifications to be aggregated because each of the phrase specifications in the group would remain identical but for the aggregatable constituent.
  • the phrase specifications to be aggregated may include “heart rate was stable within normal range yesterday” and “respiratory rate was stable within normal range yesterday”.
  • the aggregatable constituents, "heart rate” and “respiratory rate” may be combined to form combined noun phrase “heart rate and respiratory rate”.
  • the aggregator 120 may generate the noun phrase "heart and respiratory rate”.
  • Heart and respiratory rate may then be combined with or otherwise instantiated in an aggregated phrase specification with the remaining constituents in a phrase specification of the group of phrase specifications.
  • the aggregated phrase specification is configured to contain those constituents of the phrase specification of the group of phrase specifications based on the determined level of generalization (e.g. "were stable within normal range yesterday"). As such, the resultant aggregated phrase specification contains "heart and respiratory rate were stable within normal range yesterday". Therefore, an output text may include the aggregated phrase specification "heart and respiratory rate were stable within normal range yesterday" and any unchanged (e.g. not aggregated) phrase specifications in original form (e.g. not generalized), such as "mean blood pressure was unstable yesterday with mean value 95".
  • Figure 3 is an example block diagram of an example computing device for practicing embodiments of an example aggregator.
  • Figure 3 shows a computing system 300 that may be utilized to implement a natural language generation environment having a natural language generation system 102 including, in some examples, a document planner 1 12, a microplanner 1 14 having an aggregator 120 and/or a realizer 1 16.
  • a document planner 1 12 a microplanner 1 14 having an aggregator 120 and/or a realizer 1 16.
  • One or more general purpose or special purpose computing systems/devices may be used to implement the natural language generation system 102.
  • the computing system 300 may comprise one or more distinct computing systems/devices and may span distributed locations.
  • the natural language generation system 102 may be configured to operate remotely via the network 316.
  • a pre-processing module or other module that requires heavy computational load may be configured to perform that computational load and thus may be on a remote device or server.
  • the realizer 1 16 may be accessed remotely.
  • the natural language generation environment may be operable remotely, such as via a cloud source, may be operable on a client device that embodies at a least a portion of the one or more blocks, and/or the like.
  • each block shown may represent one or more such blocks as appropriate to a specific example embodiment. In some cases one or more of the blocks may be combined with other blocks.
  • the natural language generation system 102 may be implemented in software, hardware, firmware, or in some combination to achieve the capabilities described herein.
  • computing system 300 comprises a computer memory (“memory”) 302, a display 304, one or more processors 306, input/output devices 308 (e.g., keyboard, mouse, CRT or LCD display, touch screen, gesture sensing device and/or the like), other computer-readable media 310, and communications interface 312.
  • memory e.g., random access memory
  • processors 306 e.g., keyboard, mouse, CRT or LCD display, touch screen, gesture sensing device and/or the like
  • other computer-readable media 310 e.g., keyboard, mouse, CRT or LCD display, touch screen, gesture sensing device and/or the like
  • the processor 306 may, for example, be embodied as various means including one or more microprocessors with accompanying digital signal processor(s), one or more processor(s) without an accompanying digital signal processor, one or more coprocessors, one or more multi-core processors, one or more controllers, processing circuitry, one or more computers, various other processing elements including integrated circuits such as, for example, an application-specific integrated circuit (ASIC) or field- programmable gate array (FPGA), or some combination thereof. Accordingly, although illustrated in Figure 3 as a single processor, in some embodiments the processor 306 comprises a plurality of processors. The plurality of processors may be in operative communication with each other and may be collectively configured to perform one or more functionalities of the reference system as described herein.
  • ASIC application-specific integrated circuit
  • FPGA field- programmable gate array
  • the natural language generation system 102 is shown residing in memory 302.
  • the memory 302 may comprise, for example, transitory and/or non-transitory memory, such as volatile memory, non-volatile memory, or some combination thereof. Although illustrated in Figure 3 as a single memory, the memory 302 may comprise a plurality of memories. The plurality of memories may be embodied on a single computing device or may be distributed across a plurality of computing devices collectively configured to function as the natural language system, the microplanner and/or the reference system.
  • the memory 302 may comprise, for example, a hard disk, random access memory, cache memory, flash memory, a compact disc read only memory (CD-ROM), digital versatile disc read only memory (DVD-ROM), an optical disc, circuitry configured to store information, or some combination thereof.
  • a hard disk random access memory
  • cache memory flash memory
  • CD-ROM compact disc read only memory
  • DVD-ROM digital versatile disc read only memory
  • optical disc circuitry configured to store information, or some combination thereof.
  • some portion of the contents, some or all of the components of the natural language generation system 102 may be stored on and/or transmitted over the other computer-readable media 310.
  • the components of the natural language generation system 102 preferably execute on one or more processors 306 and are configured to enable operation of an aggregator, as described herein.
  • code or programs 314 e.g., an administrative interface, a Web server, and the like
  • data repositories such as other data sources
  • code or programs 314 also reside in the memory 302, and preferably execute on one or more processors 306.
  • processors 306 execute on one or more of the components in Figure 3 may not be present in any specific implementation.
  • some embodiments may not provide other computer readable media 310 or a display 304.
  • the natural language generation system 102 is further configured to provide functions such as those described with reference to Figure 1 .
  • the natural language generation system 102 may interact with the network 316, via the communications interface 312, with remote data sources 318 (e.g. remote reference data, remote performance data, remote aggregation data, remote knowledge pools and/or the like), third-party content providers 320 and/or client devices 322.
  • the network 316 may be any combination of media (e.g., twisted pair, coaxial, fiber optic, radio frequency), hardware (e.g., routers, switches, repeaters, transceivers), and protocols (e.g., TCP/IP, UDP, Ethernet, Wi-Fi, WiMAX, Bluetooth) that facilitate communication between remotely situated humans and/or devices.
  • the network 316 may take the form of the internet or may be embodied by a cellular network such as an LTE based network.
  • the communications interface 312 may be capable of operating with one or more air interface standards, communication protocols, modulation types, access types, and/or the like.
  • the client devices 322 include desktop computing systems, notebook computers, mobile phones, smart phones, personal digital assistants, tablets and/or the like.
  • components/modules of the natural language generation system 102 are implemented using standard programming techniques.
  • the natural language generation system 102 may be implemented as a "native" executable running on the processor 306, along with one or more static or dynamic libraries.
  • the natural language generation system 102 may be implemented as instructions processed by a virtual machine that executes as one of the other programs 314.
  • a range of programming languages known in the art may be employed for implementing such example embodiments, including representative implementations of various programming language paradigms, including but not limited to, object-oriented (e.g., Java, C++, C#, Visual Basic.NET, Smalltalk, and the like), functional (e.g., ML, Lisp, Scheme, and the like), procedural (e.g., C, Pascal, Ada, Modula, and the like), scripting (e.g., Perl, Ruby, Python, JavaScript, VBScript, and the like), and declarative (e.g., SQL, Prolog, and the like).
  • object-oriented e.g., Java, C++, C#, Visual Basic.NET, Smalltalk, and the like
  • functional e.g., ML, Lisp, Scheme, and the like
  • procedural e.g., C, Pascal, Ada, Modula, and the like
  • scripting e.g., Perl, Ruby, Python, JavaScript, VBScript, and
  • the embodiments described above may also use synchronous or asynchronous client-server computing techniques.
  • the various components may be implemented using more monolithic programming techniques, for example, as an executable running on a single processor computer system, or alternatively decomposed using a variety of structuring techniques, including but not limited to, multiprogramming, multithreading, client-server, or peer-to-peer, running on one or more computer systems each having one or more processors.
  • Some embodiments may execute concurrently and asynchronously, and communicate using message passing techniques. Equivalent synchronous embodiments are also supported.
  • other functions could be implemented and/or performed by each component/module, and in different orders, and by different components/modules, yet still achieve the described functions.
  • programming interfaces to the data stored as part of the natural language generation system 102 can be made available by mechanisms such as through application programming interfaces (API) (e.g. C, C++, C#, and Java); libraries for accessing files, databases, or other data repositories; through scripting languages such as XML; or through Web servers, FTP servers, or other types of servers providing access to stored data.
  • API application programming interfaces
  • the message store 104, the domain model 106 and/or the linguistic resources 108 may be implemented as one or more database systems, file systems, or any other technique for storing such information, or any combination of the above, including implementations using distributed computing techniques.
  • the message store 104, the domain model 106 and/or the linguistic resources 108 may be local data stores but may also be configured to access data from the remote data sources 318.
  • some or all of the components of the natural language generation system 102 may be implemented or provided in other manners, such as at least partially in firmware and/or hardware, including, but not limited to one or more ASICs, standard integrated circuits, controllers executing appropriate instructions, and including microcontrollers and/or embedded controllers, FPGAs, complex programmable logic devices ("CPLDs"), and the like.
  • Some or all of the system components and/or data structures may also be stored as contents (e.g., as executable or other machine-readable software instructions or structured data) on a computer- readable medium so as to enable or configure the computer-readable medium and/or one or more associated computing systems or devices to execute or otherwise use or provide the contents to perform at least some of the described techniques.
  • system components and data structures may also be stored as data signals (e.g., by being encoded as part of a carrier wave or included as part of an analog or digital propagated signal) on a variety of computer-readable transmission mediums, which are then transmitted, including across wireless-based and wired/cable-based mediums, and may take a variety of forms (e.g., as part of a single or multiplexed analog signal, or as multiple discrete digital packets or frames).
  • Such computer program products may also take other forms in other embodiments. Accordingly, embodiments of this disclosure may be practiced with other computer system configurations.
  • Figure 4 is a flowchart illustrating an example method performed in accordance with some example embodiments described herein.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for identifying a constituent in one or more phrase specifications as aggregatable.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for determining whether two or more of the received phrase specifications contain a constituent that is aggregatable. If not, then as is shown in operation 406, an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for outputting the one or more received phrase specifications.
  • phrase specifications may be generalized in operations 408 and 410 to create one or more generalized phrase specifications.
  • a phrase specification may be generalized by identifying constituents in the phrase specification that are either generalizable or removable.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for removing all constituents identified as removable.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for replacing all constituents identified as generalizable with a most generalized constituent from a generalized constituent listing.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for causing phrase specifications that can be aggregated, based on one or more removed or generalized constituents, to be grouped into phrase specification groups and stored in a data structure ListPhraseSpecGroups.
  • the two or more generalized phrase specifications are identified as aggregatable in an instance in which each of the two or more generalized phrase specifications are identical but for the aggregatable constituents in each of the two or more generalized phrase specifications.
  • Operations 414-424 are configured to generate aggregated phrase specifications for each of the groups of phrase specifications.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for setting a data structure PhraseSpecGroup to a first group of phrase specifications in ListPhraseSpecGroups.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for generating an aggregated phrase specification based on at least one phrase specification in PhraseSpecGroup.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for populating the aggregated phrase specification with a combined noun phrase or other aggregation of the constituents that are identified as aggregatable constituents in the phrase specifications in PhraseSpecGroup.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for populating the aggregated phrase specification with one or more constituents based on a determined level of generalization. Populating the aggregated phrase specification with one or more constituents based on a determined level of generalization is further described with reference to Figure 5.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for determining whether there are additional groups of phrase specifications in ListPhraseSpecGroups. If so, then as is shown in operation 424, an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for setting PhraseSpecGroup to the next group of phrase specifications in ListPhraseSpecGroups. The process then loops back to operation 416.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for outputting one or more aggregated phrase specifications and/or one or more phrase specifications that were not aggregated.
  • Figure 5 is a flowchart illustrating an example method of populating the aggregated phrase specification with one or more constituents based on a determined level of generalization performed in accordance with some example embodiments described herein.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for determining whether a constituent was removed in operation 408 from a phrase specification in PhraseSpecGroup. If not, then the process continues to decision operation 508.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for determining whether the phrase specifications in PhraseSpecGroup would still be aggregatable with the removed constituent or a generalized version of the removed constituent. If not, then the process continues to decision operation 508.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for populating the aggregated phrase specification with the removed constituent or a generalized constituent of the removed constituent provided that it is consistent with the other phrase specifications in PhraseSpecGroup and, as such, the PhraseSpecGroup is still aggregatable.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for determining whether a constituent was generalized in operation 410 from a phrase specification in PhraseSpecGroup. If not, then the process ends.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for determining whether the phrase specifications in PhraseSpecGroup would still be aggregatable with a less generalized version of the generalized constituent. If not, then the process ends.
  • an apparatus may include means, such as the microplanner 1 14, the aggregator 120, the processor 306, or the like, for populating the aggregated phrase specification with another generalized constituent, such as a less generalized constituent, from the constituent listing provided that it is consistent with the other phrase specifications in PhraseSpecGroup and, as such, the PhraseSpecGroup is still aggregatable.
  • the aggregator 120 is configured to select the least generalized constituent or the constituent that closest to the original constituent.
  • a generalized constituent may be generated based on a predefined constituent listing that is defined by the domain model and is configured to provide constituents from least general to most general.
  • FIGS 2 and 4-7 illustrate example flowcharts of the operations performed by an apparatus, such as computing system 300 of Figure 3, in accordance with example embodiments of the present invention.
  • each block of the flowcharts, and combinations of blocks in the flowcharts may be implemented by various means, such as hardware, firmware, one or more processors, circuitry and/or other devices associated with execution of software including one or more computer program instructions.
  • one or more of the procedures described above may be embodied by computer program instructions.
  • the computer program instructions which embody the procedures described above may be stored by a memory 302 of an apparatus employing an embodiment of the present invention and executed by a processor 306 in the apparatus.
  • any such computer program instructions may be loaded onto a computer or other programmable apparatus (e.g., hardware) to produce a machine, such that the resulting computer or other programmable apparatus provides for implementation of the functions specified in the flowcharts' block(s).
  • These computer program instructions may also be stored in a non-transitory computer-readable storage memory that may direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable storage memory produce an article of manufacture, the execution of which implements the function specified in the flowcharts' block(s).
  • the computer program instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operations to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide operations for implementing the functions specified in the flowcharts' block(s).
  • the operations of Figures 2 and 4-7 when executed, convert a computer or processing circuitry into a particular machine configured to perform an example embodiment of the present invention.
  • the operations of Figures 2 and 4-7 define an algorithm for configuring a computer or processor, to perform an example embodiment.
  • a general purpose computer may be provided with an instance of the processor which performs the algorithm of Figures 2 and 4-7 to transform the general purpose computer into a particular machine configured to perform an example embodiment.
  • blocks of the flowchart support combinations of means for performing the specified functions and combinations of operations for performing the specified functions. It will also be understood that one or more blocks of the flowcharts', and combinations of blocks in the flowchart, can be implemented by special purpose hardware-based computer systems which perform the specified functions, or combinations of special purpose hardware and computer instructions.
  • certain ones of the operations herein may be modified or further amplified as described herein. Moreover, in some embodiments additional optional operations may also be included. It should be appreciated that each of the modifications, optional additions or amplifications described herein may be included with the operations herein either alone or in combination with any others among the features described herein.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Machine Translation (AREA)

Abstract

La présente invention concerne des procédés, des appareils et des produits programme d'ordinateur, configurés pour réaliser une agrégation de spécifications d'expressions. Dans certains exemples de modes de réalisation, un procédé comprend l'identification d'au moins deux spécifications d'expressions généralisées. Dans certains exemples de modes de réalisation, les au moins deux spécifications d'expressions généralisées contiennent au moins un constituant pouvant être agrégé. Le procédé de ce mode de réalisation peut aussi comprendre la génération d'une spécification d'expression agrégée, depuis les au moins deux spécifications d'expressions généralisées. Dans certains exemples de modes de réalisation, la spécification d'expression agrégée comprend une expression nominale combinée, générée à partir des constituants pouvant être agrégés et un ou plusieurs constituants supplémentaires, sur la base d'un niveau déterminé de généralisation.
PCT/US2012/063343 2012-11-02 2012-11-02 Procédé et appareil d'agrégation avec généralisation d'informations WO2014070197A1 (fr)

Priority Applications (4)

Application Number Priority Date Filing Date Title
PCT/US2012/063343 WO2014070197A1 (fr) 2012-11-02 2012-11-02 Procédé et appareil d'agrégation avec généralisation d'informations
US14/702,325 US9600471B2 (en) 2012-11-02 2015-05-01 Method and apparatus for aggregating with information generalization
US15/421,925 US10216728B2 (en) 2012-11-02 2017-02-01 Method and apparatus for aggregating with information generalization
US16/257,800 US20190228077A1 (en) 2012-11-02 2019-01-25 Method And Apparatus For Aggregating With Information Generalization

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/US2012/063343 WO2014070197A1 (fr) 2012-11-02 2012-11-02 Procédé et appareil d'agrégation avec généralisation d'informations

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US14/702,325 Continuation US9600471B2 (en) 2012-11-02 2015-05-01 Method and apparatus for aggregating with information generalization

Publications (1)

Publication Number Publication Date
WO2014070197A1 true WO2014070197A1 (fr) 2014-05-08

Family

ID=47295155

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2012/063343 WO2014070197A1 (fr) 2012-11-02 2012-11-02 Procédé et appareil d'agrégation avec généralisation d'informations

Country Status (1)

Country Link
WO (1) WO2014070197A1 (fr)

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9697197B1 (en) 2011-01-07 2017-07-04 Narrative Science Inc. Automatic generation of narratives from data using communication goals and narrative analytics
US9697492B1 (en) 2011-01-07 2017-07-04 Narrative Science Inc. Automatic generation of narratives from data using communication goals and narrative analytics
WO2018020056A1 (fr) 2016-07-26 2018-02-01 Sling Supply International, S.A. Système pour le montage/démontage de pales sur des aérogénérateurs
US10572606B1 (en) 2017-02-17 2020-02-25 Narrative Science Inc. Applied artificial intelligence technology for runtime computation of story outlines to support natural language generation (NLG)
US10699079B1 (en) 2017-02-17 2020-06-30 Narrative Science Inc. Applied artificial intelligence technology for narrative generation based on analysis communication goals
US10706236B1 (en) 2018-06-28 2020-07-07 Narrative Science Inc. Applied artificial intelligence technology for using natural language processing and concept expression templates to train a natural language generation system
US10747823B1 (en) 2014-10-22 2020-08-18 Narrative Science Inc. Interactive and conversational data exploration
US10755046B1 (en) 2018-02-19 2020-08-25 Narrative Science Inc. Applied artificial intelligence technology for conversational inferencing
US10853583B1 (en) 2016-08-31 2020-12-01 Narrative Science Inc. Applied artificial intelligence technology for selective control over narrative generation from visualizations of data
US10943069B1 (en) 2017-02-17 2021-03-09 Narrative Science Inc. Applied artificial intelligence technology for narrative generation based on a conditional outcome framework
US10963649B1 (en) 2018-01-17 2021-03-30 Narrative Science Inc. Applied artificial intelligence technology for narrative generation using an invocable analysis service and configuration-driven analytics
US10990767B1 (en) 2019-01-28 2021-04-27 Narrative Science Inc. Applied artificial intelligence technology for adaptive natural language understanding
US11042709B1 (en) 2018-01-02 2021-06-22 Narrative Science Inc. Context saliency-based deictic parser for natural language processing
US11068661B1 (en) 2017-02-17 2021-07-20 Narrative Science Inc. Applied artificial intelligence technology for narrative generation based on smart attributes
US11170038B1 (en) 2015-11-02 2021-11-09 Narrative Science Inc. Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from multiple visualizations
US11222184B1 (en) 2015-11-02 2022-01-11 Narrative Science Inc. Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from bar charts
US11232268B1 (en) 2015-11-02 2022-01-25 Narrative Science Inc. Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from line charts
US11238090B1 (en) 2015-11-02 2022-02-01 Narrative Science Inc. Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from visualization data
US11288328B2 (en) 2014-10-22 2022-03-29 Narrative Science Inc. Interactive and conversational data exploration
US11561684B1 (en) 2013-03-15 2023-01-24 Narrative Science Inc. Method and system for configuring automatic generation of narratives from data
US11568148B1 (en) 2017-02-17 2023-01-31 Narrative Science Inc. Applied artificial intelligence technology for narrative generation based on explanation communication goals
US11922344B2 (en) 2014-10-22 2024-03-05 Narrative Science Llc Automatic generation of narratives from data using communication goals and narrative analytics
US11954445B2 (en) 2017-02-17 2024-04-09 Narrative Science Llc Applied artificial intelligence technology for narrative generation based on explanation communication goals
US12086562B2 (en) 2020-08-07 2024-09-10 Salesforce, Inc. Applied artificial intelligence technology for performing natural language generation (NLG) using composable communication goals and ontologies to generate narrative stories

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
EHUD REITER; ROBERT DALE: "Building Natural Language Generation Systems", 2000, CAMBRIDGE UNIVERSITY PRESS
HERCULES DALIANIS ET AL: "Aggregation in natural language generation", 28 April 1993, TRENDS IN NATURAL LANGUAGE GENERATION AN ARTIFICIAL INTELLIGENCE PERSPECTIVE, SPRINGER BERLIN HEIDELBERG, BERLIN, HEIDELBERG, PAGE(S) 88 - 105, ISBN: 978-3-540-60800-4, XP019198347 *
JAMES SHAW: "Clause Aggregation Using Linguistic Knowledge", PROC. OF IWNLG,1998, 1 January 1998 (1998-01-01), pages 138 - 147, XP055093580, Retrieved from the Internet <URL:http://acl.ldc.upenn.edu/W/W98/W98-1415.pdf> [retrieved on 20131216] *
REGINA BARZILAY ET AL: "Aggregation via set partitioning for natural language generation", PROCEEDINGS OF THE MAIN CONFERENCE ON HUMAN LANGUAGE TECHNOLOGY CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION OF COMPUTATIONAL LINGUISTICS -, 1 January 2006 (2006-01-01), Morristown, NJ, USA, pages 359 - 366, XP055093582, DOI: 10.3115/1220835.1220881 *

Cited By (55)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10755042B2 (en) 2011-01-07 2020-08-25 Narrative Science Inc. Automatic generation of narratives from data using communication goals and narrative analytics
US9697492B1 (en) 2011-01-07 2017-07-04 Narrative Science Inc. Automatic generation of narratives from data using communication goals and narrative analytics
US9720899B1 (en) 2011-01-07 2017-08-01 Narrative Science, Inc. Automatic generation of narratives from data using communication goals and narrative analytics
US9977773B1 (en) 2011-01-07 2018-05-22 Narrative Science Inc. Automatic generation of narratives from data using communication goals and narrative analytics
US11501220B2 (en) 2011-01-07 2022-11-15 Narrative Science Inc. Automatic generation of narratives from data using communication goals and narrative analytics
US9697197B1 (en) 2011-01-07 2017-07-04 Narrative Science Inc. Automatic generation of narratives from data using communication goals and narrative analytics
US11921985B2 (en) 2013-03-15 2024-03-05 Narrative Science Llc Method and system for configuring automatic generation of narratives from data
US11561684B1 (en) 2013-03-15 2023-01-24 Narrative Science Inc. Method and system for configuring automatic generation of narratives from data
US11288328B2 (en) 2014-10-22 2022-03-29 Narrative Science Inc. Interactive and conversational data exploration
US11922344B2 (en) 2014-10-22 2024-03-05 Narrative Science Llc Automatic generation of narratives from data using communication goals and narrative analytics
US11475076B2 (en) 2014-10-22 2022-10-18 Narrative Science Inc. Interactive and conversational data exploration
US10747823B1 (en) 2014-10-22 2020-08-18 Narrative Science Inc. Interactive and conversational data exploration
US11238090B1 (en) 2015-11-02 2022-02-01 Narrative Science Inc. Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from visualization data
US11232268B1 (en) 2015-11-02 2022-01-25 Narrative Science Inc. Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from line charts
US11222184B1 (en) 2015-11-02 2022-01-11 Narrative Science Inc. Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from bar charts
US11188588B1 (en) 2015-11-02 2021-11-30 Narrative Science Inc. Applied artificial intelligence technology for using narrative analytics to interactively generate narratives from visualization data
US11170038B1 (en) 2015-11-02 2021-11-09 Narrative Science Inc. Applied artificial intelligence technology for using narrative analytics to automatically generate narratives from multiple visualizations
WO2018020056A1 (fr) 2016-07-26 2018-02-01 Sling Supply International, S.A. Système pour le montage/démontage de pales sur des aérogénérateurs
US11341338B1 (en) 2016-08-31 2022-05-24 Narrative Science Inc. Applied artificial intelligence technology for interactively using narrative analytics to focus and control visualizations of data
US11144838B1 (en) 2016-08-31 2021-10-12 Narrative Science Inc. Applied artificial intelligence technology for evaluating drivers of data presented in visualizations
US10853583B1 (en) 2016-08-31 2020-12-01 Narrative Science Inc. Applied artificial intelligence technology for selective control over narrative generation from visualizations of data
US10755053B1 (en) 2017-02-17 2020-08-25 Narrative Science Inc. Applied artificial intelligence technology for story outline formation using composable communication goals to support natural language generation (NLG)
US11568148B1 (en) 2017-02-17 2023-01-31 Narrative Science Inc. Applied artificial intelligence technology for narrative generation based on explanation communication goals
US11562146B2 (en) 2017-02-17 2023-01-24 Narrative Science Inc. Applied artificial intelligence technology for narrative generation based on a conditional outcome framework
US10713442B1 (en) 2017-02-17 2020-07-14 Narrative Science Inc. Applied artificial intelligence technology for interactive story editing to support natural language generation (NLG)
US10719542B1 (en) 2017-02-17 2020-07-21 Narrative Science Inc. Applied artificial intelligence technology for ontology building to support natural language generation (NLG) using composable communication goals
US11068661B1 (en) 2017-02-17 2021-07-20 Narrative Science Inc. Applied artificial intelligence technology for narrative generation based on smart attributes
US11983503B2 (en) 2017-02-17 2024-05-14 Salesforce, Inc. Applied artificial intelligence technology for narrative generation based on a conditional outcome framework
US10699079B1 (en) 2017-02-17 2020-06-30 Narrative Science Inc. Applied artificial intelligence technology for narrative generation based on analysis communication goals
US10762304B1 (en) 2017-02-17 2020-09-01 Narrative Science Applied artificial intelligence technology for performing natural language generation (NLG) using composable communication goals and ontologies to generate narrative stories
US11954445B2 (en) 2017-02-17 2024-04-09 Narrative Science Llc Applied artificial intelligence technology for narrative generation based on explanation communication goals
US10572606B1 (en) 2017-02-17 2020-02-25 Narrative Science Inc. Applied artificial intelligence technology for runtime computation of story outlines to support natural language generation (NLG)
US10943069B1 (en) 2017-02-17 2021-03-09 Narrative Science Inc. Applied artificial intelligence technology for narrative generation based on a conditional outcome framework
US10585983B1 (en) 2017-02-17 2020-03-10 Narrative Science Inc. Applied artificial intelligence technology for determining and mapping data requirements for narrative stories to support natural language generation (NLG) using composable communication goals
US11816438B2 (en) 2018-01-02 2023-11-14 Narrative Science Inc. Context saliency-based deictic parser for natural language processing
US11042708B1 (en) 2018-01-02 2021-06-22 Narrative Science Inc. Context saliency-based deictic parser for natural language generation
US11042709B1 (en) 2018-01-02 2021-06-22 Narrative Science Inc. Context saliency-based deictic parser for natural language processing
US10963649B1 (en) 2018-01-17 2021-03-30 Narrative Science Inc. Applied artificial intelligence technology for narrative generation using an invocable analysis service and configuration-driven analytics
US11003866B1 (en) 2018-01-17 2021-05-11 Narrative Science Inc. Applied artificial intelligence technology for narrative generation using an invocable analysis service and data re-organization
US11023689B1 (en) 2018-01-17 2021-06-01 Narrative Science Inc. Applied artificial intelligence technology for narrative generation using an invocable analysis service with analysis libraries
US11561986B1 (en) 2018-01-17 2023-01-24 Narrative Science Inc. Applied artificial intelligence technology for narrative generation using an invocable analysis service
US12001807B2 (en) 2018-01-17 2024-06-04 Salesforce, Inc. Applied artificial intelligence technology for narrative generation using an invocable analysis service
US11816435B1 (en) 2018-02-19 2023-11-14 Narrative Science Inc. Applied artificial intelligence technology for contextualizing words to a knowledge base using natural language processing
US11030408B1 (en) 2018-02-19 2021-06-08 Narrative Science Inc. Applied artificial intelligence technology for conversational inferencing using named entity reduction
US10755046B1 (en) 2018-02-19 2020-08-25 Narrative Science Inc. Applied artificial intelligence technology for conversational inferencing
US11182556B1 (en) 2018-02-19 2021-11-23 Narrative Science Inc. Applied artificial intelligence technology for building a knowledge base using natural language processing
US11126798B1 (en) 2018-02-19 2021-09-21 Narrative Science Inc. Applied artificial intelligence technology for conversational inferencing and interactive natural language generation
US10706236B1 (en) 2018-06-28 2020-07-07 Narrative Science Inc. Applied artificial intelligence technology for using natural language processing and concept expression templates to train a natural language generation system
US11334726B1 (en) 2018-06-28 2022-05-17 Narrative Science Inc. Applied artificial intelligence technology for using natural language processing to train a natural language generation system with respect to date and number textual features
US11232270B1 (en) 2018-06-28 2022-01-25 Narrative Science Inc. Applied artificial intelligence technology for using natural language processing to train a natural language generation system with respect to numeric style features
US11989519B2 (en) 2018-06-28 2024-05-21 Salesforce, Inc. Applied artificial intelligence technology for using natural language processing and concept expression templates to train a natural language generation system
US11042713B1 (en) 2018-06-28 2021-06-22 Narrative Scienc Inc. Applied artificial intelligence technology for using natural language processing to train a natural language generation system
US11341330B1 (en) 2019-01-28 2022-05-24 Narrative Science Inc. Applied artificial intelligence technology for adaptive natural language understanding with term discovery
US10990767B1 (en) 2019-01-28 2021-04-27 Narrative Science Inc. Applied artificial intelligence technology for adaptive natural language understanding
US12086562B2 (en) 2020-08-07 2024-09-10 Salesforce, Inc. Applied artificial intelligence technology for performing natural language generation (NLG) using composable communication goals and ontologies to generate narrative stories

Similar Documents

Publication Publication Date Title
US10216728B2 (en) Method and apparatus for aggregating with information generalization
WO2014070197A1 (fr) Procédé et appareil d&#39;agrégation avec généralisation d&#39;informations
US10963628B2 (en) Method and apparatus for updating a previously generated text
US10565308B2 (en) Method and apparatus for configurable microplanning
US10853584B2 (en) Method and apparatus for expressing time in an output text
US10860810B2 (en) Method and apparatus for motion description
US9355093B2 (en) Method and apparatus for referring expression generation
US10776561B2 (en) Method and apparatus for generating a linguistic representation of raw input data
WO2014035406A1 (fr) Procédé et appareil pour microplanification configurable
US20200019869A1 (en) Systems and methods for semantic inference and reasoniing
WO2014035407A1 (fr) Procédé et appareil de génération d&#39;expression de référence
US20150324374A1 (en) Method and apparatus for spatial descriptions in an output text
US11727222B2 (en) Method and apparatus for natural language document orchestrator
US10853586B2 (en) Method and apparatus for lightweight multilingual natural language realizer
WO2023249785A1 (fr) Réponse à une invite de tâche sur un code déclaratif à l&#39;aide d&#39;un modèle de langage
WO2013137903A1 (fr) Systèmes et procédés d&#39;inférence et de raisonnement sémantiques
Venkatesha et al. Detecting extended contexts in tweets using DBpedia
JP2016184400A (ja) データのファイルをアップデートするコンピュータ装置、方法、及びコンピュータプログラム
Meigen Interesting Programming Languages Used in Life Sciences
Li et al. Analyzing semantic heterogeneity in XBRL taxonomies: an ontology perspective

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: 12795922

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 12795922

Country of ref document: EP

Kind code of ref document: A1