Systems and methods for improving the efficiency of syntactic and semantic analysis in automated processes for natural language understanding using argument ordering

• US 9,965,461 B2
• Filed: 03/03/2014
• Issued: 05/08/2018
• Est. Priority Date: 03/01/2013
• Status: Active Grant

• Current Assignee: The Software Shop, Inc.
• Original Assignee: The Software Shop, Inc.
• Inventors: Jackson, Jeffrey
• Primary Examiner(s): Shah, Paras D
• Assistant Examiner(s): Blankenagel, Bryan S
• Application Number:
  US14/195,500
• Publication Number:
  US 20140249802A1
• Time in Patent Office: 1,527 Days
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

A natural language understanding system may be given the capability to construct a semantically detailed parse tree for each acceptable interpretation of an input natural language expression (or fewer such parse trees than interpretations) by independently solving sub-trees corresponding to various series of post nominal modifiers and associating those partial solutions with corresponding nodes in the overall parse tree. The argument order in predicate calculus atomic formulas may be standardized in a manner that supports the use of a chart parser applied to a head-driven phase structure grammar and that permits a simplified more tractable grammar that in turn can be used as a domain general semantic grammar.

Claims

1. A method comprising:

using at least a processor and memory for performing syntactic and semantic analysis by;

receiving a natural language predicating expression;

determining, by the processor, a first thematic role sequence;

determining, by the processor, a second thematic role sequence;

applying, by the processor, the first thematic role sequence to the natural language predicating expression;

applying, by the processor, the second thematic role sequence to the natural language predicating expression for determining a standardized order of thematic roles contained in the first thematic role sequence;

constructing, by the processor, a representation of an artificial language predicating expression with the standardized order of thematic roles contained in the first thematic role sequence in which predicate arguments are represented using the applied second thematic role sequence,

wherein the representation of the artificial language predicating expression comprises a specification of an artificial logical predicate and a specification of the predicate arguments of the logical predicate, wherein each of the arguments corresponds to at least one thematic role in the first thematic role sequences; and

displaying in a user interface the representation of the artificial language predicating expression based on at least one thematic role included in the first thematic role sequence and the second thematic role sequence,

wherein constructing the representation of an artificial language predicating expression with the standardized order by the processor, in which predicate arguments are presented, thereby constructing the representation of an artificial language predicating expression with the standardized order by the processor improves the processing speed and efficiency of syntactic and semantic analysis at the processor.

2. The method of claim 1, further comprising receiving a grammar rule, wherein the first thematic role sequence and the second thematic role sequence are associated with the grammar rule.

3. The method of claim 2, further comprising:

parsing the natural language predicating expression into a plurality of natural language predicating expression parts using the grammar rule;

determining a correspondence between at least one first thematic role sequence element and at least one of the natural language predicating expression parts;

receiving a correspondence between at least one second thematic role sequence element and at least one artificial language predicating expression argument place; and

determining an order of at least one artificial language predicating expression argument based on determining the correspondence between at least one first thematic role sequence element and at least one of the natural language predicating expression part and based on receiving the correspondence between at least one second thematic role sequence element and at least one artificial language predicating expression argument place.

4. The method of claim 1, further comprising:

receiving a first data structure representing at least a partial meaning for each one of at least one of the natural language predicating expression parts;

receiving at least one second data structure representing at least a partial meaning for an artificial language predicating expression argument, wherein the artificial language predicating expression argument corresponds to a second thematic role sequence element;

receiving a specification of the identity of an element of the second thematic role sequence that corresponds to the at least one second data structure;

assigning the first data structure for each one of the at least one natural language predicating expression part to a corresponding one of at least one artificial language predicating expression argument place based on determining the correspondence between at least one first thematic role sequence element and the at least one of the natural language predicating expression part and based on receiving the correspondence between the at least one second thematic role sequence element and the at least one artificial language predicating expression argument place; and

assigning each of the received at least one second data structure to the artificial predicating expression argument place of the corresponding identified element of the second thematic role sequence.

5. The method of claim 4, wherein assigning the first data structure representing at least the partial meaning for each one of the at least one of natural language predicating expression parts to the plurality of artificial language predicating expression argument places, comprises establishing a correspondence between each one of the at least one first thematic role sequence elements and at least one of the at least one second thematic role sequence elements.

6. The method of claim 1, wherein each one of the at least one first thematic role sequence elements is the at least one of the second thematic role sequence elements.

7. The method of claim 1, further comprising storing the translated natural language predicating expression in a database.

8. The method of claim 1, further comprising receiving the natural language predicating expression in a user interface.

9. A system comprising:

at least a processor and memory comprising a natural language parser, the natural language parser being configured to;

perform, by the processor, syntactic and semantic analysis;

receive, by the processor, a natural language predicating expression;

determine, by the processor, a first thematic role sequence;

determine, by the processor, a second thematic role sequence;

apply, by the processor, the first thematic role sequence to the natural language predicating expression;

apply, by the processor, the second thematic role sequence to the natural language predicating expression for determining a standardized order of thematic roles contained in the first thematic role sequence; and

construct, by the processor, a representation of an artificial language predicating expression with the standardized order of thematic roles contained in the first thematic role sequence in which predicate arguments are represented by using the applied second thematic role sequence,

wherein the representation of the artificial language predicating expression comprises a specification of an artificial logical predicate and a specification of the predicate arguments of the logical predicate, wherein each of the arguments corresponds to at least one thematic role in the first thematic role sequences; and

a user interface that displays the representation of the artificial language predicating expression based on at least one thematic role included in the first thematic role sequence and the second thematic role sequence,

wherein the construction of the representation of an artificial language predicating expression with the standardized order by the processor, in which predicate arguments are presented, thereby construction of the representation of an artificial language predicating expression with the standardized order by the processor improves the processing speed and efficiency of syntactic and semantic analysis at the processor.

10. The system of claim 9, wherein the natural language parser is further configured to receive a grammar rule, wherein the first thematic role sequence and the second thematic role sequence are associated with the grammar rule.

11. The system of claim 10, wherein the natural language parser is further configured to:

parse the natural language predicating expression into a plurality of natural language predicating expression parts using the grammar rule;

determine a correspondence between at least one first thematic role sequence element and at least one of the natural language predicating expression parts; and

receive a correspondence between at least one second thematic role sequence element and at least one artificial language predicating expression argument place; and

determine an order of at least one artificial language predicating expression argument based on determining the correspondence between at least one first thematic role sequence element and at least one of the natural language predicating expression part and based on receiving the correspondence between at least one second thematic role sequence element and at least one artificial language predicating expression argument place.

12. The system of claim 9, wherein the natural language parser is further configured to:

receive a first data structure representing at least a partial meaning for each one of at least one of the natural language predicating expression parts;

receive at least one second data structure representing at least a partial meaning for an artificial language predicating expression argument, wherein the artificial language predicating expression argument corresponds to a second thematic role sequence element;

receive a specification of the identity of an element of the second thematic role sequence that corresponds to the at least one second data structure;

assign the first data structure for each one of the at least one natural language predicating expression parts to a corresponding one of at least one artificial language predicating expression argument place based on determining the correspondence between at least one first thematic role sequence element and the at least one of the natural language predicating expression part and based on receiving the correspondence between the at least one second thematic role sequence element and the at least one artificial language predicating expression argument place; and

assign each of the received at least one second data structure to the artificial predicating expression argument place of the corresponding identified element of the second thematic role sequence.

13. The system of claim 9, wherein the natural language parser is further configured to establish a correspondence between each one of the at least one first thematic role sequence elements and at least one of the at least one second thematic role sequence elements.

14. The system of claim 9, wherein each one of the at least one first thematic role sequence elements is the at least one of the second thematic role sequence elements.

15. The system of claim 9, wherein the processor is further configured to store the translated natural language predicating expression in a database.

16. The method of claim 9, wherein the processor is further configured to receive the natural language predicating expression in a user interface.

17. A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

perform, by the computing device, syntactic and semantic analysis;

receive, by the computing device, a natural language predicating expression;

determine, by the computing device, a first thematic role sequence;

determine, by the computing device, a second thematic role sequence;

apply, by the computing device, the first thematic role sequence to the natural language predicating expression;

apply, by the computing device, the second thematic role sequence to the natural language predicating expression for determining a standardized order of thematic roles contained in the first thematic role sequence;

construct, by the computing device, a representation of an artificial language predicating expression with the standardized order of thematic roles contained in the first thematic role sequence in which predicate arguments are represented by using the applied second thematic role sequence,

wherein the construction of the representation of an artificial language predicating expression with the standardized order by the processor, in which predicate arguments are presented thereby construction of the representation of an artificial language predicating expression with the standardized order by the processor improves the processing speed and efficiency of syntactic and semantic analysis at the processor; and

display, in a user interface of the computing device, the representation of the artificial language predicating expression based on at least one thematic role included in the first thematic role sequence and the second thematic role sequence,

wherein the representation of the artificial language predicating expression comprises a specification of an artificial logical predicate and a specification of the predicate arguments of the logical predicate, wherein each of the arguments corresponds to at least one thematic role in the first thematic role sequences.

18. The computer program product of claim 17, wherein the program instructions are executable by the computing device to cause the computing device to receive a grammar rule, wherein the first thematic role sequence and the second thematic role sequence are associated with the grammar rule.

19. The computer program product of claim 18, wherein the program instructions are executable by the computing device to cause the computing device to:

parse, by the computing device, the natural language predicating expression into a plurality of natural language predicating expression parts using the grammar rule;

determine, by the computing device, a correspondence between at least one first thematic role sequence element and at least one of the natural language predicating expression parts;

receive, by the computing device, a correspondence between at least one second thematic role sequence element and at least one artificial language predicating expression argument place; and

determine, by the computing device, an order of at least one artificial language predicating expression argument based on determining the correspondence between at least one first thematic role sequence element and at least one of the natural language predicating expression part and based on receiving the correspondence between at least one second thematic role sequence element and at least one artificial language predicating expression argument place.

20. The computer program product of claim 17, wherein the program instructions are executable by the computing device to cause the computing device to:

receive, by the computing device, a first data structure representing at least a partial meaning for each one of at least one of the natural language predicating expression parts;

receive, by the computing device, at least one second data structure representing at least a partial meaning for an artificial language predicating expression argument, wherein the artificial language predicating expression argument corresponds to a second thematic role sequence element;

receive, by the computing device, a specification of the identity of an element of the second thematic role sequence that corresponds to the at least one second data structure;

assign, by the computing device, the first data structure for each one of the plurality of natural language predicating expression parts to a corresponding one of at least one artificial language predicating expression argument place based on determining the correspondence between at least one first thematic role sequence element and the at least one of the natural language predicating expression part and based on receiving the correspondence between the at least one second thematic role sequence element and the at least one artificial language predicating expression argument place; and

assign, by the computing device, each of the received at least one second data structure to the artificial predicating expression argument place of the corresponding identified element of the second thematic role sequence.

21. The computer program product of claim 20, wherein the program instructions are executable by the computing device to cause the computing device to assign the first data structure representing at least the partial meaning for each one of the at least one of natural language predicating expression parts to the plurality of artificial language predicating expression argument places, comprises establishing a correspondence between each one of the at least one first thematic role sequence elements and at least one of the at least one second thematic role sequence elements.

22. The computer program product of claim 17, wherein each one of the at least one first thematic role sequence elements is the at least one of the second thematic role sequence elements.

23. The computer program product of claim 17, wherein the program instructions are executable by the computing device to cause the computing device to store, by the computer programming product, the translated natural language predicating expression in a database.

24. The computer program product of claim 17, wherein the program instructions are executable by the computing device to cause the computing device to receive, by the computer programming product, the natural language predicating expression in a user interface.