Anaphora resolution using linguisitic cues, dialogue context, and general knowledge

• US 9,171,542 B2
• Filed: 03/11/2013
• Issued: 10/27/2015
• Est. Priority Date: 03/11/2013
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Gandrabur, Simona, Buist, Eric, Curin, Jan, Kleindienst, Jan, Havelka, Jiri
• Primary Examiner(s): BRYAR, JEREMIAH A
• Application Number:
  US13/793,805
• Publication Number:
  US 20140257792A1
• Time in Patent Office: 960 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

An automatic conversational system has multiple computer-implemented dialogue components for conducting an automated dialogue process with a human user. A user client delivers dialogue output prompts to the human user and receives dialogue input responses from the human user including speech inputs. An automatic speech recognition engine processes the speech inputs to determine corresponding sequences of representative text words. A natural language understanding (NLU) processing arrangement processes the dialogue input responses and the text words to determine corresponding semantic interpretations. The NLU processing arrangement includes an anaphora processor that accesses different information sources characterizing dialogue context, linguistic features, and NLU features to identify unresolved anaphora in the text words needing resolution in order to determine a semantic interpretation. A dialogue manager manages the dialogue process with the human user based on the semantic interpretations.

Claims

1. A computer-implemented method comprising:

receiving, by a computing system, data generated based on spoken user responses to prompts associated with a dialogue, the data comprising a portion corresponding to one or more of the spoken user responses spoken before a subsequently spoken response of the spoken user responses;

generating, by the computing system, a list of natural language understanding (NLU)-ranked semantic interpretations for the subsequently spoken response; and

re-ranking, by the computing system and based on their relative similarity and a context of the dialogue determined from the one or more of the spoken user responses, the list of NLU-ranked semantic interpretations to identify a semantic interpretation that resolves an unresolved anaphora in the subsequently spoken response.

2. The computer-implemented method of claim 1, wherein re-ranking the list comprises determining a plurality of key-value pairs corresponding to different possible resolutions for the unresolved anaphora.

3. The computer-implemented method of claim 2, comprising determining, by the computing system, that a key-value pair of the plurality of key-value pairs corresponds to the semantic interpretation that resolves the unresolved anaphora based on a determination that the key-value pair comprises:

a context type corresponding to the context of the dialogue; and

a context value indicating that the semantic interpretation is context based.

4. The computer-implemented method of claim 2, wherein determining the plurality of key-value pairs comprises determining, for each element of a plurality of elements of the list, a key-value pair comprising a context type and a context value.

5. The computer-implemented method of claim 4, wherein determining the key-value pair comprises determining at least one of a state of the dialogue, an expectation of the dialogue, a focus of the dialogue, or a selection based on the one or more of the spoken user responses.

6. The computer-implemented method of claim 4, comprising determining, by the computing system and for each key-value pair of the plurality of key-value pairs, a confidence score indicating a level of confidence that a possible resolution of the different possible resolutions corresponding to the key-value pair resolves the unresolved anaphora.

7. The computer-implemented method of claim 6, comprising re-ranking, for each key-value pair of the plurality of key-value pairs and based on the confidence score, an element of the plurality of elements corresponding to the key-value pair within the list.

8. A computing system comprising:

at least one processor; and

a memory storing instructions that when executed by the at least one processor cause the computing system to;

receive data generated based on spoken user responses to prompts associated with a dialogue, the data comprising a portion corresponding to one or more of the spoken user responses spoken before a subsequently spoken response of the spoken user responses;

generate a list of natural language understanding (NLU)-ranked semantic interpretations for the subsequently spoken response; and

re-rank, based on their relative similarity and a context of the dialogue determined from the one or more of the spoken user responses, the list of NLU-ranked semantic interpretations to identify a semantic interpretation that resolves an unresolved anaphora in the subsequently spoken response.

9. The computing system of claim 8, wherein the instructions, when executed by the at least one processor, cause the computing system to determine a plurality of key-value pairs corresponding to different possible resolutions for the unresolved anaphora.

10. The computing system of claim 9, wherein the instructions, when executed by the at least one processor, cause the computing system to determine that a key-value pair of the plurality of key-value pairs corresponds to the semantic interpretation that resolves the unresolved anaphora based on a determination that the key-value pair comprises:

a context type corresponding to the context of the dialogue; and

a context value indicating that the semantic interpretation is context based.

11. The computing system of claim 9, wherein the instructions, when executed by the at least one processor, cause the computing system to determine, for each element of a plurality of elements of the list, a key-value pair comprising a context type and a context value.

12. The computing system of claim 11, wherein the instructions, when executed by the at least one processor, cause the computing system to determine the key-value pair based on at least one of a state of the dialogue, an expectation of the dialogue, a focus of the dialogue, or a selection based on the one or more of the spoken user responses.

13. The computing system of claim 11, wherein the instructions, when executed by the at least one processor, cause the computing system to determine, for each key-value pair of the plurality of key-value pairs, a confidence score indicating a level of confidence that a possible resolution of the different possible resolutions corresponding to the key-value pair resolves the unresolved anaphora.

14. The computing system of claim 13, wherein the instructions, when executed by the at least one processor, cause the computing system to re-rank, for each key-value pair of the plurality of key-value pairs and based on the confidence score, an element of the plurality of elements corresponding to the key-value pair within the list.

15. One or more non-transitory computer-readable media comprising instructions that when executed by one or more computers cause the one or more computers to:

receive data generated based on spoken user responses to prompts associated with a dialogue, the data comprising a portion corresponding to one or more of the spoken user responses spoken before a subsequently spoken response of the spoken user responses;

generate a list of natural language understanding (NLU)-ranked semantic interpretations for the subsequently spoken response; and

re-rank, based on their relative similarity and a context of the dialogue determined from the one or more of the spoken user responses, the list of NLU-ranked semantic interpretations to identify a semantic interpretation that resolves an unresolved anaphora in the subsequently spoken response.

16. The one or more non-transitory computer-readable media of claim 15, wherein the instructions, when executed by the one or more computers, cause the one or more computers to determine a plurality of key-value pairs corresponding to different possible resolutions for the unresolved anaphora.

17. The one or more non-transitory computer-readable media of claim 16, wherein the instructions, when executed by the one or more computers, cause the one or more computers to determine that a key-value pair of the plurality of key-value pairs corresponds to the semantic interpretation that resolves the unresolved anaphora based on a determination that the key-value pair comprises:

a context type corresponding to the context of the dialogue;

and a context value indicating that the semantic interpretation is context based.

18. The one or more non-transitory computer-readable media of claim 16, wherein the instructions, when executed by the one or more computers, cause the one or more computers to determine, for each element of a plurality of elements of the list, a key-value pair comprising a context type and a context value.

19. The one or more non-transitory computer-readable media of claim 18, wherein the instructions, when executed by the one or more computers, cause the one or more computers to determine the key-value pair based on at least one of a state of the dialogue, an expectation of the dialogue, a focus of the dialogue, or a selection based on the one or more of the spoken user responses.

20. The one or more non-transitory computer-readable media of claim 18, wherein the instructions, when executed by the one or more computers, cause the one or more computers to:

determine, for each key-value pair of the plurality of key-value pairs, a confidence score indicating a level of confidence that a possible resolution of the different possible resolutions corresponding to the key-value pair resolves the unresolved anaphora; and

re-rank, for each key-value pair of the plurality of key-value pairs and based on the confidence score, an element of the plurality of elements corresponding to the key-value pair within the list.