Apparatus and method for spoken language understanding by using semantic role labeling

• US 20060080101A1
• Filed: 03/31/2005
• Published: 04/13/2006
• Est. Priority Date: 10/12/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Hakkani-Tur, Dilek Z., Tur, Gokhan, Chotimongkol, Ananlada
• Granted Patent: US 7,742,911 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

An apparatus and a method are provided for using semantic role labeling for spoken language understanding. A received utterance semantically parsed by semantic role labeling. A predicate or at least one argument is extracted from the semantically parsed utterance. An intent is estimated based on the predicate or the at least one argument. In another aspect, a method is provided for training a spoken language dialog system that uses semantic role labeling. An expert is provided with a group of predicate/argument pairs. Ones of the predicate/argument pairs are selected as intents. Ones of the arguments are selected as named entities. Mappings from the arguments to frame slots are designed.

Claims

1. A spoken language understanding method, comprising:

semantically parsing a received utterance by semantic role labeling;

extracting one of a predicate or at least one argument from the semantically parsed utterance; and

estimating an intent based on at least one of the extracted predicate or the at least one extracted argument.

2. The method of claim 1, further comprising estimating at least one associated named entity using the at least one argument.

3. The method of claim 1, further comprising outputting the estimated intent.

4. The method of claim 2, further comprising outputting the at least one associated named entity.

5. The method of claim 3, further comprising:

performing an action based on the output estimated intent.

6. The method of claim 1, further comprising:

syntactically preprocessing the utterance before using semantic role labeling to semantically parse the utterance.

7. The method of claim 1, further comprising:

performing feature extraction of the utterance.

8. The method of claim 7, wherein the performing of feature extraction is performed using part-of-speech tagging, syntactic parsing, and named entity extraction.

9. The method of claim 1, further comprises:

mapping the estimated intent to a frame; and

mapping the at least one argument to at least one frame slot of the frame.

10. A method for training a spoken language dialog system that uses semantic role labeling, the method comprising:

providing an expert with a plurality of predicate/argument pairs;

selecting ones of the predicate/argument pairs as intents;

selecting ones of the arguments as named entities; and

designing mappings from the arguments to frame slots.

11. The method of claim 10, further comprising:

grouping the arguments; and

defining the grouped ones of the arguments as values of a named entity.

12. The method of claim 10, further comprising:

using a clustering approach to determine potential named entities from the arguments.

13. The method of claim 10, further comprising:

using a clustering approach to determine potential intents from the predicate/argument pairs

14. The method of claim 10, wherein the provided predicate/argument pairs are from a domain of interest.

15. An apparatus comprising:

a processor; and

storage for storing data and a plurality of instructions for the processor, wherein the apparatus is configured to;

semantically parse a received utterance by semantic role labeling,

extract one of a predicate or at least one argument from the semantically parsed utterance, and

estimate an intent based on at least one of the extracted predicate or the at least one extracted argument.

16. The apparatus of claim 15, wherein the apparatus is further configured to estimate at least one associated named entity using the at least one argument.

17. The apparatus of claim 15, wherein the apparatus is further configured to output the estimated intent.

18. The apparatus of claim 16, where in the apparatus is further configured to output the associated named entities.

19. The apparatus of claim 17, wherein the apparatus is further configured to:

perform an action based on the output estimated intent.

20. The apparatus of claim 15, wherein the apparatus is further configured to:

syntactically preprocess the utterance before semantically parsing the utterance by semantic role labeling.

21. The apparatus of claim 15, wherein the apparatus is further configured to:

perform feature extraction of the utterance.

22. The apparatus of claim 21 wherein the apparatus is configured to perform the feature extraction using part-of-speech tagging, syntactic parsing, and named entity extraction.

23. The apparatus of claim 15, wherein the apparatus is further configured to:

map the estimated intent to a frame; and

map the at least one argument to at least one frame slot of the frame.

24. An apparatus comprising:

means for semantically parsing a received utterance by semantic role labeling;

means for extracting one of a predicate or at least one argument from the semantically parsed utterance;

means for estimating an intent based on at least one of the extracted predicate or the at least one argument;