Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N5/00—Computing arrangements using knowledge-based models
  • G06N5/04—Inference or reasoning models
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
  • G06F16/33—Querying
  • G06F16/3331—Query processing
  • G06F16/334—Query execution
  • G06F16/3344—Query execution using natural language analysis
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N5/00—Computing arrangements using knowledge-based models
  • G06N5/02—Knowledge representation; Symbolic representation
  • G06N5/022—Knowledge engineering; Knowledge acquisition
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F40/00—Handling natural language data
  • G06F40/10—Text processing
  • G06F40/166—Editing, e.g. inserting or deleting
  • G06F40/169—Annotation, e.g. comment data or footnotes
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F40/00—Handling natural language data
  • G06F40/20—Natural language analysis
  • G06F40/205—Parsing
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F40/00—Handling natural language data
  • G06F40/20—Natural language analysis
  • G06F40/279—Recognition of textual entities
  • G06F40/284—Lexical analysis, e.g. tokenisation or collocates
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N5/00—Computing arrangements using knowledge-based models
  • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N5/00—Computing arrangements using knowledge-based models
  • G06N5/04—Inference or reasoning models
  • G06N5/041—Abduction
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/08—Learning methods
  • G06N3/084—Backpropagation, e.g. using gradient descent

Definitions

• the present invention relates generally to language statement processing in a computer system and more particularly to a computer program product, system, and method for using higher order actions to annotate a syntax tree with real data for concepts used to generate an answer to a question.
• a concept comprises an object in a domain of the question and relates to other concepts in an ontology of the domain; a plurality of actions in the domain of the question having parameters.
• a higher order action specifies an input, action parameters, and an output.
• the higher order action is processed to determine an element in the information space of the syntax tree corresponding to the input of the higher order action and to determine an action of the plurality of actions having parameters matching the action parameters.
• the determined element is provided as input to the determined action to produce output of the determined action that is processed according to the output specified by the higher order action.
• the information space of the syntax tree is further annotated with the output from the higher order action to use to provide an answer to the question.
• the subject matter of the embodiments may optionally include an optional embodiment that the higher order action specifies a constraint for the input.
• Determining the element in the information space of the syntax tree corresponding to the input of the higher order action comprises determining whether the information space of the syntax tree includes a concept satisfying the constraint of the input of the higher order action.
• the determined action is applied to the concept satisfying the constraint of the input of the higher order action.
• the output from the higher order action provides real data for the concept corresponding to the input of the higher order action.
• the higher order action is used to determine concepts satisfying the constraint of the input so that the determined action can be applied to the concept satisfying the constraint to provide output of data for that concept to annotate in the information space of the syntax tree.
• This allows a higher order action to trigger application of other qualifying actions to apply to the concepts in the information space to generate data for the concepts in the information space to improve the determination of answers to the question represented in the syntax tree.
• a matching strength of the actions is determined to select an action to process the element in the information space having a highest matching strength.
• a concept may comprise an attribute in the data model of the domain.
• the pattern matching module 108 enables mapping of natural language in the question 114 to concepts in the ontology of the domain.
• the concepts that annotate a token in the syntax tree 116 allow the system to consider and recognize these concepts as part of the token of the question 114 when processing the question 114.
• the memory/storage 104 may comprise a suitable volatile or non-volatile memory for storing programs to execute and information used by the program 110 to execute.
• program modules such as the program components 106 through 124 may comprise routines, programs, objects, components, logic, data structures, and so on that perform particular tasks or implement particular abstract data types.
• the programs 106, 108, 110, 112, 200, 300 may comprise program code loaded into memory and executed by a processor. Alternatively, some or all of the functions may be implemented in hardware devices, such as in Application Specific Integrated Circuits (ASICs) or executed by separate dedicated processors.
• ASICs Application Specific Integrated Circuits
• the constraint 202 may comprise a qualification for the concepts, and comprise a subject, (the input 204), a predicate, and an object, where the predicate constrains the subject to the object.
• a subClassOf .list constrains the symbol a to be any list, so that a concept node in the annotated syntax tree 118 must comprise a list in order to be subject to the action 200i.
• the input 204 may comprise a tree of concepts that must be matched for the action to be selected for execution.
• the output 206 may comprise a flat list of concepts or real data comprising the concept. Concepts within a signature can further be qualified with additional specifications.
• the default parameter for the input may be a concept. Flowever, the input may also comprise real data produced for a concept by another action, such as real product data, real invoice data, etc.
• An example of an action that searches a database for a product by name may have a signature of "Product (optional :WithName(data :UserString)) -> data Product”, such that for a concept in the tree being constrained as having the name ":UserString”, the data Product will be outputted, comprising the products having the product name.
• the semantic action module 110 performs a loop of operations at blocks 406 through 426 for each higher order action 300, in the domain of the question 114. If (at block 408) there is no matching element in the tree 118, then control proceeds to block 426 to process a next higher order action 300, until all higher order actions 300 are processed. If (at block 408) there is at least one element, e.g., concept or data, in the annotated syntax tree 118 matching the input 304 of the higher order action 300, and satisfying the constraint 302, then for each matching element j satisfying the constraint 302, control proceeds (at block 410) to perform blocks 412 through 426 in FIG. 4b to apply the higher order action i to element j.
• element e.g., concept or data
• FIG. 7 shows an information space of the syntax tree 700 representing the syntax tree 600 in node form, where the nodes having the terms in the question 114 are shown as solid filled, are linked to concept nodes shown with a white center.
• FIG. 8 shows a further annotated information space of a syntax tree 800, such as annotated syntax tree 120, after actions 200 are applied to add real data nodes linked to the concept nodes, where the real data nodes generated by the actions are shown as white nodes with a color center.
• the variants panel 802 shows the actions used to generate the real data nodes, shown as white nodes with a solid center, for the concepts, shown as solid nodes with a white center.
• the annotated syntax tree 800 may be processed to generate the candidate answers to the questions by considering the real data generated for the concepts linked to the question tokens or terms.
• a computer readable storage medium is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.
• Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages.
• the computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
• the computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
• each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s).
• the functions noted in the block may occur out of the order noted in the figures.
• two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
• System memory 906 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 910 and/or cache memory 912.
• Computer system/server 902 may further include other removable/non-removable, volatile/non-volatile computer system storage media.
• storage system 913 can be provided for reading from and writing to a non-removable, non-volatile magnetic media (not shown and typically called a "hard drive").
• network adapter 924 communicates with the other components of computer system/server 902 via bus 908. It should be understood that although not shown, other hardware and/or software components could be used in conjunction with computer system/server 902. Examples, include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.
• Devices that are in communication with each other need not be in continuous communication with each other, unless expressly specified otherwise.
• devices that are in communication with each other may communicate directly or indirectly through one or more intermediaries.

Landscapes

• Engineering & Computer Science (AREA)
• Theoretical Computer Science (AREA)
• General Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Computational Linguistics (AREA)
• Artificial Intelligence (AREA)
• Data Mining & Analysis (AREA)
• Computing Systems (AREA)
• Software Systems (AREA)
• Evolutionary Computation (AREA)
• Mathematical Physics (AREA)
• General Health & Medical Sciences (AREA)
• Health & Medical Sciences (AREA)
• Audiology, Speech & Language Pathology (AREA)
• Databases & Information Systems (AREA)
• Life Sciences & Earth Sciences (AREA)
• Molecular Biology (AREA)
• Biophysics (AREA)
• Biomedical Technology (AREA)
• Machine Translation (AREA)
• Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Priority Applications (3)

Applications Claiming Priority (2)

Publications (1)

Family

ID=74869682

Family Applications (1)

Country Status (5)

Families Citing this family (6)

Citations (5)

Family Cites Families (11)

• 2019
  • 2019-09-18 US US16/575,341 patent/US11379738B2/en active Active
• 2020
  • 2020-09-08 WO PCT/IB2020/058338 patent/WO2021053457A1/en not_active Ceased
  • 2020-09-08 GB GB2204446.5A patent/GB2602238A/en not_active Withdrawn
  • 2020-09-08 JP JP2022516431A patent/JP7558258B2/ja active Active
  • 2020-09-08 CN CN202080063909.5A patent/CN114375447B/zh active Active
• 2022
  • 2022-05-19 US US17/664,220 patent/US11842290B2/en active Active
• 2023
  • 2023-10-06 US US18/482,670 patent/US20250117574A1/en active Pending

Patent Citations (5)

Also Published As

Similar Documents

Legal Events