Bootstrapping sense characterizations of occurrences of polysemous words in dictionaries

• US 6,081,775 A
• Filed: 06/16/1999
• Issued: 06/27/2000
• Est. Priority Date: 07/31/1997
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Dolan, William B.
• Primary Examiner(s): Thomas, Joseph
• Application Number:
  US09/334,391
• Time in Patent Office: 377 Days
• Field of Search: 704/10, 704/9, 704/8, 704/1, 704/2, 704/4, 704/7, 704/5, 707/530, 707/531, 707/532, 707/533
• US Class Current: 704/10
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms

Abstract

The present invention is directed to characterizing the sense of an occurrence of a polysemous word in a representation of a dictionary. In a preferred embodiment, the representation of the dictionary is made up of a plurality of text segments containing word occurrences having a word sense characterization and word occurrences not having a word sense characterization. The embodiment first selects a plurality of the dictionary text segments that each contain a first word. The embodiment then identifies from among the selected text segments a first and a second occurrence of a second word. The identified second occurrence of the second word has a word sense characterization. The embodiment then attributes to the first occurrence of the second word sense characterization of the second occurrence of the second word.

Claims

1. A method in a computer system for, in a representation of one or more dictionaries comprising a plurality of text segments, characterizing the sense of an occurrence of a polysemous word, the method comprising the steps of:

selecting a plurality of dictionary text segments each containing a first word;

identifying among the selected dictionary text segments a first occurrence of a second word, the first occurrence of the second word having no word sense characterization;

identifying among the selected dictionary text segments a second occurrence of the second word, the second occurrence of the second word having a word sense characterization; and

attributing to the first occurrence of the second word the word sense characterization of the second occurrence of the second word.

2. The method of claim 1 wherein the text segments of the dictionary include term definitions.

3. The method of claim 1 wherein the text segments of the dictionary include term usage examples.

4. The method of claim 1 wherein the second occurrence of the second word is in a dictionary text segment for defining or exemplifying the usage of the second word.

5. The method of claim 1 wherein the attributing step is only performed where a condition relating to the identified occurrences of the second word is satisfied.

6. The method of claim 1 wherein the attributing step is only performed where the identified occurrences of the second word share the same part of speech.

7. The method of claim 1 wherein the identified occurrences of the second word both have the verb part of speech, and wherein the attributing step is only performed where the identified occurrences of the second word are either both transitive verbs or are both intransitive verbs.

8. The method of claim 1 wherein the attributing step is only performed where the second occurrence of the second word has no positive register features.

9. The method of claim 1, further comprising the steps of:

identifying within the selected word subgraph a third node representing a third occurrence of the second word, the third node having a word sense characterization; and

determining to attribute to the first node the word sense characterization of the second occurrence of the second word rather than the word sense characterization of the third occurrence of the second word based upon a characteristic of the second occurrence of the second word.

10. The method of claim 9 wherein the determining step determines to attribute to the first occurrence of the second word the word sense characterization of the second occurrence of the second word rather than the word sense characterization of the third occurrence of the second word based upon a determination that the first and second occurrences of the second word are from the same dictionary, while the first and third occurrences of the second word are not from the same dictionary.

11. The method of claim 9 wherein the determining step determines to attribute to the first occurrence of the second word the word sense characterization of the second occurrence of the second word rather than the word sense characterization of the third occurrence of the second word based upon a determination that the second occurrence of the second word is more closely related to the first word than is the third occurrence of the second word.

12. A computer-readable medium whose contents cause a computer system to, in a representation of one or more dictionaries comprising a plurality of text segments, characterize the sense of an occurrence of a polysemous word by:

selecting a plurality of dictionary text segments each containing a first word;

identifying among the selected dictionary text segments a first occurrence of a second word, the first occurrence of the second word having no word sense characterization;

identifying among the selected dictionary text segments a second occurrence of the second word, the second occurrence of the second word having a word sense characterization; and

attributing to the first occurrence of the second word the word sense characterization of the second occurrence of the second word.

13. The computer-readable medium of claim 12 wherein the text segments of the dictionary include term definitions.

14. The computer-readable medium of claim 12 wherein the text segments of the dictionary include term usage examples.

15. The computer-readable medium of claim 12 wherein the second occurrence of the second word is in a dictionary text segment for defining or exemplifying the usage of the second word.

16. The computer-readable medium of claim 12 wherein the attributing is only performed where a condition relating to the identified occurrences of the second word is satisfied.

17. The computer-readable medium of claim 12 wherein the attributing is only performed where the identified occurrences of the second word share the same part of speech.

18. The computer-readable medium of claim 12 wherein the identified occurrences of the second word both have the verb part of speech, and wherein the attributing is only performed where the identified occurrences of the second word are either both transitive verbs or are both intransitive verbs.

19. The computer-readable medium of claim 12 wherein the attributing is only performed where the second occurrence of the second word has no positive register features.

20. The computer-readable medium of claim 12 wherein the contents of the computer-readable medium cause the computer system to further:

identify within the selected word subgraph a third node representing a third occurrence of the second word, the third node having a word sense characterization; and

determine to attribute to the first node the word sense characterization of the second occurrence of the second word rather than the word sense characterization of the third occurrence of the second word based upon a characteristic of the second occurrence of the second word.

21. The computer-readable medium of claim 20 wherein the determining determines to attribute to the first occurrence of the second word the word sense characterization of the second occurrence of the second word rather than the word sense characterization of the third occurrence of the second word based upon a determination that the first and second occurrences of the second word are from the same dictionary, while the first and third occurrences of the second word are not from the same dictionary.

22. The computer-readable medium of claim 20 wherein the determining determines to attribute to the first occurrence of the second word the word sense characterization of the second occurrence of the second word rather than the word sense characterization of the third occurrence of the second word based upon a determination that the second occurrence of the second word is more closely related to the first word than is the third occurrence of the second word.

23. An apparatus for characterizing the sense of an occurrence of a polysemous word in a representation of a dictionary, the dictionary comprising a plurality of text segments, the apparatus comprising:

a dictionary text segment selection subsystem for selecting a plurality of dictionary text segments each containing a first word;

a word occurrence identification subsystem for identifying among the dictionary text segments selected by the dictionary text segment selection subsystem a first and second occurrence of a second word, the second occurrence of the second word having a word sense characterization and the first occurrence of the second word having no word sense characterization; and

a sense attribution subsystem for attributing to the first occurrence of the second word identified by the word occurrence identification subsystem the word sense characterization of the second occurrence of the second word identified by the word occurrence identification subsystem.