Lexical semantic structure

• US 20050273336A1
• Filed: 09/15/2004
• Published: 12/08/2005
• Est. Priority Date: 04/23/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Parkinson, David J., Cipollone, Domenic J., Calcagno, Michael V., Olsen, Mari J. B., Chang, Su Chin, Shahani, Ravi C.
• Granted Patent: US 7,689,410 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 8/315 Object-oriented languages
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

A lexical semantic structure for modeling semantics of a natural language input on a computer is described. A set of lexical semantic categories is selected to model content of the natural language input. A methodology associates content of the natural language input to one or more categories of the set of lexical semantic categories.

Claims

1. A lexical semantic structure for modeling semantics of a natural language input on a computer comprising:

a set of lexical semantic categories selected to model content of the natural language input; and

a methodology for associating content of the natural language input to one or more categories of the set of lexical semantic categories.

2. The structure of claim 1 wherein the methodology comprises:

a collection of semantic rules for associating content of the natural language input to the set of lexical semantic categories; and

procedures for applying the collection of semantic rules to the natural language input.

3. The structure of claim 1 wherein the methodology further comprises:

a collection of semantic rules for normalizing natural language input across the set of lexical semantic categories, the collection of semantic rules adapted to identify arguments and modifiers of syntactic classes and their semantics and to associate the identified arguments to one or more categories of the set of lexical semantic categories.

4. The structure of claim 1 wherein the set of lexical semantic categories model elements of natural language input independent of any particular natural language.

5. The structure of claim 1 wherein the set of lexical semantic categories models elements of natural language input independent of any particular application.

6. The structure of claim 1 wherein the methodology is adapted to normalize the natural language input across analysis engines adapted to produce some type of syntactic category.

7. The structure of claim 1 wherein the methodology is adapted to normalize the natural language input independent of any particular natural language.

8. The structure of claim 1 wherein the methodology is adapted to normalize the natural language input across syntactic categories.

9. The structure of claim 1 wherein the set of lexical semantic categories comprises:

one or more lexical semantic categories, each lexical semantic category comprising;

one or more syntactic categories representative of a portion of the natural language input;

one or more semantic roles representative of a function of the portion within the natural language input; and

a mapping between the one or more syntactic categories and the one or more semantic roles.

10. A lexical semantic structure for modeling semantics of a natural language input comprising:

a set of categories chosen to model content of the natural language input based on cross-linguistic behavior; and

a methodology adapted to normalize content of the natural language input across languages to one or more categories of the set of categories.

11. The structure of claim 10 wherein the set of categories comprises:

syntactic categories and semantic roles derived from cross-linguistic behavior and adapted to model content of the natural language input.

12. The structure of claim 10 wherein the methodology comprises:

semantic rules for associating syntactic arguments of the natural language input with semantic roles defined by the set of categories.

13. The structure of claim 12 wherein the methodology further comprises:

a collection of procedures adapted to map syntactic categories to selected semantic roles based on the semantic rules.

14. The structure of claim 10 wherein the methodology normalizes the natural language input across languages.

15. The structure of claim 10 wherein the set of categories models natural language input independent of any particular software application.

16. The structure of claim 10 wherein the methodology normalizes the natural language input across analysis engines adapted to produce some type of syntactic category.

17. The structure of claim 10 wherein the methodology normalizes the natural language input across linguistic categories.

18. A lexical semantic structure for representing semantics of a natural language input comprising:

an inventory associating syntactic categories and semantic roles, the inventory adapted to represent content of the natural language input independent of any particular language; and

a methodology for associating content of the natural language input to the inventory.

19. The structure of claim 18 wherein the methodology comprises:

a collection of rules for associating content of the natural language input to the inventory; and

procedures for applying the collection of rules to the natural language input.

20. The structure of claim 18 wherein the inventory comprises:

one or more classes adapted to represent nouns, verbs, and modifiers of the natural language input, and semantic roles adapted to model relationships between instances of the one or more classes for normalization across languages and systems.

21. The structure of claim 18 wherein the methodology further comprises:

a collection of procedures adapted to normalize the natural language input to the inventory, the collection procedures adapted to identify arguments of syntactic categories and their semantics and to associate the identified arguments to one or more syntactic categories or semantic roles of the inventory.

22. The structure of claim 18 wherein the inventory models natural language input independent of any particular application.

23. The structure of claim 18 wherein the methodology is adapted to normalize the natural language input across analysis engines.

24. The structure of claim 18 wherein the methodology is adapted to normalize the natural language input across natural languages.

25. The structure of claim 18 wherein the inventory is stored on a computer-readable medium.

26. The structure of claim 18 wherein the methodology is adapted to normalize the natural language input across syntactic categories.

27. The structure of claim 18 wherein the inventory comprises:

one or more lexical semantic categories, each lexical semantic category comprising;

one or more syntactic categories representative of a portion of the natural language input;

one or more semantic roles representative of a function of the portion within the natural language input; and

a mapping between the one or more syntactic categories and the one or more semantic roles.