Grammar fragment acquisition using syntactic and semantic clustering

• US 9,330,660 B2
• Filed: 03/04/2014
• Issued: 05/03/2016
• Est. Priority Date: 09/15/1995
• Status: Expired due to Fees

• Current Assignee: AT&T Intellectual Property II LP (AT&T, Inc.), Nippon Telegraph and Telephone Corporation
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.), Nippon Telegraph and Telephone Corporation
• Inventors: Arai, Kazuhiro, Gorin, Allen L., Riccardi, Giuseppe, Wright, Jeremy H.
• Primary Examiner(s): Armstrong, Angela A
• Application Number:
  US14/196,536
• Publication Number:
  US 20140303978A1
• Time in Patent Office: 791 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering

Abstract

A method and apparatus are provided for automatically acquiring grammar fragments for recognizing and understanding fluently spoken language. Grammar fragments representing a set of syntactically and semantically similar phrases may be generated using three probability distributions: of succeeding words, of preceding words, and of associated call-types. The similarity between phrases may be measured by applying Kullback-Leibler distance to these tree probability distributions. Phrases being close in all three distances may be clustered into a grammar fragment.

Claims

1. A method comprising:

selecting candidate multi-word phrases from a set of words, wherein a maximum number of candidate multi-word phrases is based on a highest of a number of preceding contexts;

for each candidate multi-word phrase in the candidate multi-word phrases, generating a measurement associated with a succeeding context of a succeeding phrase and a preceding context of a preceding phrase using a similarity in the candidate multi-word phrases;

clustering, via a processor, the candidate multi-word phrases into a grammar fragment based on the measurement, wherein the grammar fragment represents similar phrases that are both syntactically and semantically coherent; and

recognizing input speech using the grammar fragment.

2. The method of claim 1, wherein the similarity is one of a semantic similarity and a syntactic similarity.

3. The method of claim 1, wherein each candidate phrase has both semantic associations and syntactic associations.

4. The method of claim 3, wherein the syntactic associations are syntactic probabilistic distributions of the succeeding context and syntactic probabilistic distributions of the preceding context.

5. The method of claim 4, wherein the semantic associations are semantic probabilistic distributions.

6. The method of claim 5, wherein the semantic similarity and syntactic similarity are measured by applying distance measurements between the syntactic probabilistic distributions of the succeeding context, the syntactic probabilistic distributions of the preceding context, and the semantic probabilistic distributions.

7. The method of claim 6, wherein the semantic probability distributions are combined with the syntactic probabilistic distributions of the succeeding context and the syntactic probabilistic distributions of the preceding context.

8. The method of claim 7, wherein the method is recursive.

9. The method of claim 6, wherein the semantic measurements and the syntactic measurements are calculated using Kullback-Leibler distance measurements.

10. A system comprising:

a processor; and

a computer-readable storage medium having instruction stored which, when executed by the processor, cause the processor to perform operations comprising;

selecting candidate multi-word phrases from a set of words, wherein a maximum number of candidate multi-word phrases is based on a highest of a number of preceding contexts;

for each candidate multi-word phrase in the candidate multi-word phrases, generating a measurement associated with a succeeding context of a succeeding phrase and a preceding context of a preceding phrase using a similarity in the candidate multi-word phrases;

clustering, via a processor, the candidate multi-word phrases into a grammar fragment based on the measurement, wherein the grammar fragment represents similar phrases that are both syntactically and semantically coherent; and

recognizing input speech using the grammar fragment.

11. The system of claim 10, wherein the similarity is one of a semantic similarity and a syntactic similarity.

12. The system of claim 10, wherein each candidate phrase has both semantic associations and syntactic associations.

13. The system of claim 12, wherein the syntactic associations are syntactic probabilistic distributions of the succeeding context and syntactic probabilistic distributions of the preceding context.

14. The system of claim 13, wherein the semantic associations are semantic probabilistic distributions.

15. The system of claim 14, wherein the semantic similarity and syntactic similarity are measured by applying distance measurements between the syntactic probabilistic distributions of the succeeding context, the syntactic probabilistic distributions of the preceding context, and the semantic probabilistic distributions.

16. The system of claim 15, wherein the semantic probability distributions are combined with the syntactic probabilistic distributions of the succeeding context and the syntactic probabilistic distributions of the preceding context.

17. The system of claim 16, wherein the method is recursive.

18. The system of claim 15, wherein the semantic measurements and the syntactic measurements are calculated using Kullback-Leibler distance measurements.

19. A computer-readable storage device having instructions stored which, when executed by a computing device, causes the computing device to perform operations comprising:

selecting candidate multi-word phrases from a set of words, wherein a maximum number of candidate multi-word phrases is based on a highest of a number of preceding contexts;

for each candidate multi-word phrase in the candidate multi-word phrases, generating a measurement associated with a succeeding context of a succeeding phrase and a preceding context of a preceding phrase using a similarity in the candidate multi-word phrases;

clustering, via a processor, the candidate multi-word phrases into a grammar fragment based on the measurement, wherein the grammar fragment represents similar phrases that are both syntactically and semantically coherent; and

recognizing input speech using the grammar fragment.

20. The computer-readable storage device of claim 19, wherein the similarity is one of a semantic similarity and a syntactic similarity.