Method and system for learning ontological relations from documents

• US 20080154578A1
• Filed: 12/26/2006
• Published: 06/26/2008
• Est. Priority Date: 12/26/2006
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Xu, Kui, Weng, Fuliang
• Granted Patent: US 7,630,981 B2
• Time in Patent Office: Days
• US Class Current: 704/4
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models

Abstract

Embodiments of an ontological determination method for use in natural language processing applications are described. In one embodiment, shallow lexico-syntactic patterns are applied to identify relations by extracting term features to distinguish relation terms from non-relation terms, identifying coordinate relations for every adjacent terms; identifying short-distance ontological (e.g., hypernym or part-whole relations) for other adjacent terms based on term features and lexico-syntactic patterns; and then inferring long-distance hypernym and part-whole relations based on the identified coordinate relations and the short-distance relations.

Claims

1. A method of learning ontological relations in a document comprising:

extracting term features from noun-phrases in the document;

generating short-distance patterns for both coordinate terms and ontological relations in the document;

generalizing the short-distance patterns for both the coordinate terms and the ontological relations;

identifying short-distance coordinate relations and ontological relations respectively from the generalized short-distance coordinate terms and short-distance ontological relations; and

deriving long-distance ontological relations from the identified short-distance coordinate relations and ontological relations.

2. The method of claim 1, wherein the document comprises a plurality of terms characterized by syntactic relationships among the terms.

3. The method of claim 1, wherein at least one ontological relation of the ontological relations is selected from the group consisting of:

hypernym, part-whole, synonym, antonym, coordinate, entailment, troponym, and casual relations.

4. The method of claim 1, wherein the short-distance coordinate terms comprise terms separate by at most one term.

6. The method of claim 1, wherein generalizing the short-distance patterns comprises:

grouping the short-distance patterns by verbs or prepositions;

extracting the longest common substring within each group of pattern strings; and

deriving generalized patterns for every verb or preposition.

7. The method of claim 1, wherein identifying short-distance coordinate terms comprises performing statistical classification on the coordinate terms.

8. The method of claim 1, wherein identifying short-distance ontological relations comprises performing statistical classification on the ontological relations.

9. The method of claim 1, wherein the long-distance ontological relations are used in a natural language processing system to build a knowledge base for use with a natural language processing system.

5. The method of claim 5, wherein the long-distance ontological relations comprise ontological relations between terms separated by at least two terms.

10. A system for learning ontological relations in a document, comprising:

an input stage for inputting noun phrase portions of sentences in the document;

a knowledge base including words from the document; and

an ontological learning component configured to

identify relations by extracting term features from the noun phrase portions to distinguish relation terms from non-relation terms,

identify coordinate relations for every pair of adjacent terms,

identify short-distance ontological relations for other adjacent terms based on term features and lexico-syntactic patterns, and

infer long-distance ontological relations based on the identified coordinate relations and the short-distance relations.

11. The system of claim 10, wherein at least one ontological relation of the ontological relations is selected from the group consisting of hypernym, part-whole, synonym, antonym, coordinate, entailment, troponym, and casual relations.

12. The system of claim 10, wherein the long-distance ontological relations comprise ontological relations between terms separated by at least two terms.

13. The system of claim 10, further comprising a natural language processing system functionally coupled to the knowledge base and utilizing words stored in the knowledge base.

14. The system of claim 13, wherein the natural language processing system comprises a dialog system.

15. The system of claim 13, wherein the natural language processing system is selected from the group consisting of a reasoning system, a question and answer system, an information retrieval system, a machine translation system, and a semantic inference system.

16. A machine-readable medium including instructions which when executed in a processing system perform the operations of:

extracting term features from noun-phrases in the document;

generating short-distance patterns for both coordinate terms and ontological relations in an input document;

generalizing the short-distance patterns for both the coordinate terms and the ontological relations;

identifying short-distance coordinate relations and ontological relations respectively from the generalized short-distance coordinate terms and short-distance ontological relations; and

deriving long-distance ontological relations from the identified short-distance coordinate relations and ontological relations.

17. The machine-readable medium of claim 16 further comprising instructions to:

group the short-distance patterns by verbs;

extract the longest common substring within each group of pattern strings; and

derive generalized patterns for every verb.

18. The machine-readable medium of claim 16 further comprising instructions to:

group the short-distance patterns by prepositions;

extract the longest common substring within each group of pattern strings; and

derive generalized patterns for every preposition.

19. The medium of claim 16, further comprising instructions to build a knowledge base for use with a natural language processing system.