Unsupervised learning of paraphrase/translation alternations and selective application thereof

• US 20060106594A1
• Filed: 11/15/2004
• Published: 05/18/2006
• Est. Priority Date: 11/15/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Brockett, Christopher J., Dolan, William B., Breck, Eric
• Granted Patent: US 7,584,092 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/237 Lexical tools

Abstract

A computer-implemented method is disclosed for applying a given paraphrase alternation pattern to an input string. The method includes generating a language model and applying the language model to determine how to apply the given paraphrase alternation pattern to the input string.

Claims

1. A computer-implemented method for applying a given paraphrase alternation pattern to an input string, the method comprising:

generating a language model; and

applying the language model to determine how to apply the given paraphrase alternation pattern to the input string.

2. The method of claim 1, wherein generating a language model comprises generating a language model based on a data set that is related in terms of subject matter to a set of data from which the given paraphrase alternation pattern was derived.

3. The method of claim 1, wherein generating a language model comprises generating a language model based on data derived from a database of news articles.

4. The method of claim 1, wherein generating a language model comprises generating a language model based on data that is in a different language than the language of the input string.

5. The method of claim 1, wherein applying the language model comprises applying the language model to determine how best to apply the given paraphrase alternation pattern to the input string.

6. The method of claim 1, wherein applying the language model comprises applying the language model to determine how to apply the given paraphrase alternation pattern so as to produce a probable sequence of words.

7. The method of claim 1, further comprising making a determination as to whether the paraphrase alternation pattern can be applied to the textual input so as to preserve meaning.

8. The method of claim 1, wherein applying a language model comprises:

applying the given paraphrase alternation pattern to the input string in a plurality of different ways to produce a plurality of different textual variations; and

applying the language model to the plurality of different textual variations to determine a probable sequence of words.

9. The method of claim 8, wherein applying the given paraphrase alternation pattern to the input string in a plurality of different ways comprises switching different combinations of words around a function word.

10. The method of claim 8, wherein applying the given paraphrase alternation pattern to the input string in a plurality of different ways comprises switching different combinations of words around a grammatical marker.

11. A computer-implemented method for applying a paraphrase alternation pattern to an input string, the method comprising:

deriving the paraphrase alternation pattern from a set of parallel texts;

creating a series of different application alternatives that each represent a different application of the paraphrase alternation pattern to the input string; and

applying the series of different application alternatives to a language model to determine a probable sequence of words.

12. The method of claim 11, wherein deriving the paraphrase alternation pattern from a set of parallel texts comprises deriving from a set of parallel, word-aligned texts.

13. The method of claim 11, wherein deriving the paraphrase alternation pattern from a set of parallel texts comprises deriving from a set of bilingual texts.

14. The method of claim 11, wherein deriving the paraphrase alternation pattern from a set of parallel texts comprises deriving from a set of monolingual texts.

15. A computer-implemented method of selecting boundaries for application of a paraphrase alternation pattern to an input string, the method comprising:

applying the paraphrase alternation pattern multiple times with multiple boundaries so as to create a plurality of alternation alternatives; and

determining at least one of the plurality of alternation alternatives that is probable sequence of words.

16. The method of claim 15, wherein determining comprises applying a language model.

17. The method of claim 15, wherein determining comprises applying a language model that reflects a subject matter that is consistent with the input string.

18. The method of claim 15, wherein determining comprises applying a language model that incorporates data derived from a database of news articles.

19. The method of claim 15, wherein determining comprises determining at least one of the plurality of alternation alternatives that appears relatively frequently within a collection of test data.

20. The method of claim 15, wherein applying so as to create a plurality of alternation alternatives comprises applying so as to switch different combinations of words around a function word.

21. The method of claim 15, wherein applying so as to create a plurality of alternation alternatives comprises applying so as to switch different combinations of words around grammatical marker.

22. The method of claim 15, further comprising determining whether the paraphrase alternation pattern can be applied to the input string so as to preserve meaning.

23. The method of claim 22, wherein determining whether the paraphrase alternation pattern can be applied comprises applying a context model to support such a determination.