System and method of extracting clauses for spoken language understanding

• US 9,176,946 B2
• Filed: 09/29/2014
• Issued: 11/03/2015
• Est. Priority Date: 12/24/2002
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Bangalore, Srinivas, Gupta, Narendra K., Rahim, Mazin G.
• Primary Examiner(s): SPOONER, LAMONT M
• Application Number:
  US14/499,888
• Publication Number:
  US 20150019210A1
• Time in Patent Office: 400 Days
• Field of Search: 704/1, 704/9, 704/231, 704/251
• US Class Current: 1/1
• CPC Class Codes: G06F 40/117 Tagging; Marking up details of markup languages G06F40/143; Designating a block; Setting of attributes style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G10L 15/05 Word boundary detection
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units
• CPC Class Codes: G10L 2015/081 Search algorithms, e.g. Baum-Welch or Viterbi
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

A clausifier and method of extracting clauses for spoken language understanding are disclosed. The method relates to generating a set of clauses from speech utterance text and comprises inserting at least one boundary tag in speech utterance text related to sentence boundaries, inserting at least one edit tag indicating a portion of the speech utterance text to remove, and inserting at least one conjunction tag within the speech utterance text. The result is a set of clauses that may be identified within the speech utterance text according to the inserted at least one boundary tag, at least one edit tag and at least one conjunction tag. The disclosed clausifier comprises a sentence boundary classifier, an edit detector classifier, and a conjunction detector classifier. The clausifier may comprise a single classifier or a plurality of classifiers to perform the steps of identifying sentence boundaries, editing text, and identifying conjunctions within the text.

Claims

1. A method comprising:

inserting, via a discriminative classification approach, boundary tags into speech utterance text, the boundary tags identifying boundaries selected from a group comprising phrase boundaries, sentence boundaries, and paragraph boundaries, wherein the discriminative classification approach utilizes syntactic features before and after each word being tagged, to yield boundary marked speech utterance text;

inserting, via the discriminative classification approach, edit tags in the boundary marked speech utterance text to identify at least one word of a set of duplicated words, to yield edited text and unedited text, wherein each edit tag comprises edit span information indicating how many words to the left of each edit tag to edit;

identifying coordinating conjunctions within the unedited text based on a conjunction tag, to yield identified coordinating conjunctions; and

identifying clauses in the speech utterance text based on the boundary marked speech utterance text, the edited text, and the identified coordinating conjunctions.

2. The method of claim 1, wherein the conjunction tag comprises conjunction span information indicating how many words to the left of the conjunction tag a corresponding conjunction includes.

3. The method of claim 1, wherein the edit tags indicate a portion of the boundary marked speech utterance text to remove.

4. The method of claim 1, further comprising inserting the conjunction tag within the edited text.

5. The method of claim 1, wherein a different classifier performs each step of the method.

6. The method of claim 1, wherein a single classifier performs the inserting of the boundary tags, the inserting of the edit tags, the identifying of the coordinating conjunctions, and the identifying of the clauses in the speech utterance text.

7. The method of claim 1, wherein a plurality of classifiers perform the inserting of the boundary tags, the inserting of the edit tags, the identifying of the coordinating conjunctions, and the identifying of the clauses in the speech utterance text.

8. A system comprising:

a processor; and

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

inserting, via a discriminative classification approach, boundary tags into speech utterance text, the boundary tags identifying boundaries selected from a group comprising phrase boundaries, sentence boundaries, and paragraph boundaries, wherein the discriminative classification approach utilizes syntactic features before and after each word being tagged, to yield boundary marked speech utterance text;

inserting, via the discriminative classification approach, edit tags in the boundary marked speech utterance text to identify at least one word of a set of duplicated words, to yield edited text and unedited text, wherein each edit tag comprises edit span information indicating how many words to the left of each edit tag to edit;

identifying coordinating conjunctions within the unedited text based on a conjunction tag, to yield identified coordinating conjunctions; and

identifying clauses in the speech utterance text based on the boundary marked speech utterance text, the edited text, and the identified coordinating conjunctions.

9. The system of claim 8, wherein the conjunction tag comprises conjunction span information indicating how many words to the left of the conjunction tag a corresponding conjunction includes.

10. The system of claim 8, wherein the edit tags indicate a portion of the boundary marked speech utterance text to remove.

11. The system of claim 8, the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in operations comprising inserting the conjunction tag within the edited text.

12. The system of claim 8, wherein a different classifier performs each step of the method.

13. The system of claim 8, wherein a single classifier performs the inserting of the boundary tags, the inserting of the edit tags, the identifying of the coordinating conjunctions, and the identifying of the clauses in the speech utterance text.

14. The system of claim 8, wherein a plurality of classifiers perform the inserting of the boundary tags, the inserting of the edit tags, the identifying of the coordinating conjunctions, and the identifying of the clauses in the speech utterance text.

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

inserting, via a discriminative classification approach, boundary tags into speech utterance text, the boundary tags identifying boundaries selected from a group comprising phrase boundaries, sentence boundaries, and paragraph boundaries, wherein the discriminative classification approach utilizes syntactic features before and after each word being tagged, to yield boundary marked speech utterance text;

inserting, via the discriminative classification approach, edit tags in the boundary marked speech utterance text to identify at least one word of a set of duplicated words, to yield edited text and unedited text, wherein each edit tag comprises edit span information indicating how many words to the left of each edit tag to edit;

identifying coordinating conjunctions within the unedited text based on a conjunction tag, to yield identified coordinating conjunctions; and

identifying clauses in the speech utterance text based on the boundary marked speech utterance text, the edited text, and the identified coordinating conjunctions.

16. The computer-readable storage device of claim 15, wherein the conjunction tag comprises conjunction span information indicating how many words to the left of the conjunction tag a corresponding conjunction includes.

17. The computer-readable storage device of claim 15, wherein the edit tags indicate a portion of the boundary marked speech utterance text to remove.

18. The computer-readable storage device of claim 15, having additional instructions stored which, when executed by the computing device, result in operations comprising inserting the conjunction tag within the edited text.

19. The computer-readable storage device of claim 15, wherein a different classifier performs each step of the method.

20. The computer-readable storage device of claim 15, wherein a single classifier performs the inserting of the boundary tags, the inserting of the edit tags, the identifying of the coordinating conjunctions, and the identifying of the clauses in the speech utterance text.