Text processing using natural language understanding

• US 8,924,210 B2
• Filed: 05/28/2014
• Issued: 12/30/2014
• Est. Priority Date: 05/13/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Basson, Sara H., Hamilton, Rick, Jiang, Dan Ning, Kanevsky, Dimitri, Nahamoo, David, Picheny, Michael, Ramabhadran, Bhuvana, Sainath, Tara N.
• Primary Examiner(s): Vo, Huyen X.
• Application Number:
  US14/289,434
• Publication Number:
  US 20140278410A1
• Time in Patent Office: 216 Days
• Field of Search: 704 1- 10, 704/251, 704/255, 704/257, 704/270, 704/277, 704/235
• US Class Current: 704/235
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Techniques for converting spoken speech into written speech are provided. The techniques include transcribing input speech via speech recognition, mapping each spoken utterance from input speech into a corresponding formal utterance, and mapping each formal utterance into a stylistically formatted written utterance.

Claims

1. A method for rephrasing one or more portions of text in a first text to obtain a second text, wherein the method comprises acts of:

using at least one first processor to perform natural language understanding (NLU) processing on the first text to obtain at least one semantic representation of the first text;

using the at least one semantic representation of the first text to generate at least one formal representation of the first text;

analyzing the at least one formal representation of the first text to identify at least one language characteristic that is present in the first text;

using at least one second processor to identify a transformation rule associated with the at least one language characteristic; and

obtaining the second text at least in part by applying the transformation rule associated with the at least one language characteristic to rephrase one or more portions of text in the first text.

2. The method of claim 1, wherein using the at least one semantic representation of the first text to generate at least one formal representation of the first text comprises generating a set of alternative and equivalent formal representations of the first text.

3. The method of claim 1, further comprising:

obtaining the first text at least in part by transcribing input speech via speech recognition; and

editing at least one speech recognition error to create a modified transcript of speech input.

4. The method of claim 3, wherein creating a modified transcript comprises modifying the transcript to more closely align the transcript with written grammar.

5. The method of claim 3, wherein the at least one language characteristic is a characteristic of a first language style, and wherein the transformation rule associated with the at least one language characteristic is applied to rephrase the one or more portions of text in the first text to more closely align with a second language style that is different from the first language style.

6. The method of claim 1, further comprising using a statistical equation to train a spoken to written speech translator.

7. The method of claim 6, wherein a statistical equation comprises Prob_theta(F|A)=Prob_theta(F|T) Prob(T|A)/Prob(A,F|T), where F is written speech, T is spoken speech, A is speech spoken by an individual.

8. The method of claim 1, further comprising representing one or more metrics of proximity from one language style to another, using an entropy-based measure that incorporates understandability over a specified number of words.

9. The method of claim 1, further comprising estimating one or more parameters with an expectation maximization algorithm that optimizes one or more functions via association with an auxiliary function.

10. The method of claim 9, wherein a function for estimation of one or more parameters comprises Prob_theta(F|A)=f(theta)=Prob_theta(F|T) Prob_theta(T|A)/Prob(A,F|T), where F is written speech, T is spoken speech, A is speech spoken by an individual.

11. The method of claim 10, further comprising associating the function Prob_theta(F|T) with a summation of all possible choices of associating a written utterance with one or more spoken word utterances.

12. The method of claim 11, wherein each alignment of a spoken word utterance with one or more possible formal written utterances has a likelihood measure, and wherein total probability_Prob_theta(F|T) is a summation of all likelihoods of alignments.

13. The method of claim 1, further comprising providing a system, wherein the system comprises one or more distinct software modules, each of the one or more distinct software modules being embodied on a tangible computer-readable recordable storage medium, and wherein the one or more distinct software modules comprise a speech recognition module, a formal mapping module and a stylistic formatting module executing on a hardware processor.

14. The method of claim 1, wherein the at least one first processor coincides with the at least one second processor.

15. A computer program product comprising a tangible computer readable recordable storage device including computer useable program code for rephrasing one or more portions of text in a first text to obtain a second text, the computer program product including:

computer useable program code for performing natural language understanding (NLU) processing on the first text to obtain at least one semantic representation of the first text;

computer useable program code for using the at least one semantic representation of the first text to generate at least one formal representation of the first text; and

computer useable program code for analyzing the at least one formal representation of the first text to identify at least one language characteristic that is present in the first text, identifying a transformation rule associated with the at least one language characteristic, and obtaining the second text at least in part by applying the transformation rule associated with the at least one language characteristic to rephrase one or more portions of text in the first text.

16. The computer program product of claim 15, wherein the computer useable program code for using the at least one semantic representation of the first text to generate at least one formal representation of the first text-comprises computer useable program code for generating a set of alternative and equivalent formal representations of the first text.

17. The computer program product of claim 15, further comprising computer useable program code for representing one or more metrics of proximity from one language style to another, using an entropy-based measure that incorporates understandability over a specified number of words.

18. A system for rephrasing one or more portions of text in a first text to obtain a second text, comprising:

a memory; and

at least one processor coupled to the memory and operative to;

perform natural language understanding (NLU) processing on the first text to obtain at least one semantic representation of the first text;

use the at least one semantic representation of the first text to generate at least one formal representation of the first text;

analyze the at least one formal representation of the first text to identify at least one language characteristic that is present in the first text;

identify a transformation rule associated with the at least one language characteristic; and

obtain the second text at least in part by applying the transformation rule associated with the at least one language characteristic to rephrase one or more portions of text in the first text.

19. The system of claim 18, wherein the at least one processor coupled to the memory operative to use the at least one semantic representation of the first text to generate at least one formal representation of the first text is operative to generate a set of alternative and equivalent formal representations of the first text.

20. The system of claim 18, wherein the at least one processor coupled to the memory is further operative to represent one or more metrics of proximity from one language style to another, using an entropy-based measure that incorporates understandability over a specified number of words.