System and method for word-sense disambiguation by recursive partitioning

• US 20060277045A1
• Filed: 06/06/2005
• Published: 12/07/2006
• Est. Priority Date: 06/06/2005
• Status: Active Grant

• Current Assignee: Cerence Inc., Cerence Operating Company (Cerence Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Gleason, Philip
• Granted Patent: US 8,099,281 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

A device and related methods for word-sense disambiguation during a text-to-speech conversion are provided. The device, for use with a computer-based system capable of converting text data to synthesized speech, includes an identification module for identifying a homograph contained in the text data. The device also includes an assignment module for assigning a pronunciation to the homograph using a statistical test constructed from a recursive partitioning of training samples, each training sample being a word string containing the homograph. The recursive partitioning is based on determining for each training sample an order and a distance of each word indicator relative to the homograph in the training sample. An absence of one of the word indicators in a training sample is treated as equivalent to the absent word indicator being more than a predefined distance from the homograph.

Claims

1. A device for use with a computer-based system capable of converting text data to synthesized speech, the device comprising:

an identification module for identifying a homograph contained in the text data; and

an assignment module for assigning a pronunciation to the homograph using a statistical test constructed from a recursive partitioning of a plurality of training samples, each training sample comprising a word string containing the homograph;

the recursive partitioning being based on determining for each of a plurality of word indicators an order and a distance of each word indicator relative to the homograph in each training sample, wherein an absence of one of the plurality of word indicators in a training sample is treated as an equivalent to the absent word indicator being more than a predefined distance from the homograph.

2. The device of claim 1, wherein the statistical test comprises determining for each of a plurality of partitioned sets generated by the recursive partitioning a respective likelihood that the homograph belongs to a particular one of the plurality of partitioned sets.

3. The device of claim 2, wherein the statistical test is constructed by iteratively constructing different partitions of the plurality of training samples each partition being based upon a different partitioning test and evaluating the different partitioning tests to determine which partitioning test effects a best separation of different pronunciations of the homograph.

4. The device of claim 3, wherein the evaluating of the different partitioning tests is based upon an entropy measure.

5. The device of claim 4, wherein the entropy measure comprises a Shannon entropy.

6. The device of claim 4, wherein the entropy measure comprises a Gini entropy.

7. A method of electronically disambiguating homographs during a computer-based text-to-speech event, the method comprising:

identifying a homograph contained in a text; and

determining a pronunciation for the homograph using a statistical test constructed from a recursive partitioning of a plurality of training samples, each training sample comprising a word string containing the homograph;

the recursive partitioning being based on determining for each of a plurality of word indicators an order and a distance of each word indicator relative to the homograph in each training sample, wherein an absence of one of the plurality of word indicators in a training sample is treated as an equivalent to the absent word indicator being more than a predefined distance from the homograph.

8. The method of claim 7, wherein the statistical test comprises determining for each of a plurality of partitioned sets generated by the recursive partitioning a respective likelihood that the homograph belongs to a particular one of the plurality of partitioned sets.

9. The method of claim 8, wherein the statistical test is constructed by iteratively constructing different partitions of the plurality of training samples each partition being based upon a different partitioning test and evaluating the different partitioning tests determine which partitioning test effects a best separation of different pronunciations of the homograph.

10. The method of claim 9, wherein evaluating the different partitioning tests comprises determining an entropy measure.

11. The method of claim 10, wherein the entropy measure comprises a Shannon entropy.

12. The method of claim 10, wherein the entropy measure comprises a Gini entropy.

13. A computer-implemented method of constructing a statistical test for determining a pronunciation of a homograph encountered during an electronic text-to-speech conversion event, the method comprising:

selecting a set of training samples, each training sample comprising a word string containing the homograph; and

recursively partitioning the set of training samples, the recursive partitioning producing a decision tree for determining the pronunciation and being based on determining for each of a plurality of word indicators an order and a distance of each word indicator relative to the homograph in each training sample, wherein an absence of one of the plurality of word indicators in a training sample is treated as an equivalent to the absent word indicator being more than a predefined distance from the homograph.

14. The method of claim 13, wherein the statistical test comprises determining for each of a plurality of partitioned sets generated by the recursive partitioning a respective likelihood that the homograph belongs to a particular one of the plurality of partitioned sets.

15. The method of claim 14, wherein the statistical test is constructed by iteratively constructing different partitions of the plurality of training samples each partition being based upon a different partitioning test and evaluating the different partitioning tests to determine which partitioning test effects a best separation of different pronunciations of the homograph.

16. The method of claim 15, wherein evaluating the different partitioning tests comprises determining an entropy measure.

17. The method of claim 15, wherein the entropy measure comprises a Shannon entropy.

18. The method of claim 15, wherein the entropy measure comprises a Gini entropy.