Communicating context across different components of multi-modal dialog applications
First Claim
1. A method comprising:
- receiving, by a computing system, data generated based on spoken user responses to prompts generated by the computing system that are 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 at least one processor of the computing system, a list of natural language understanding (NLU)-ranked semantic interpretations for the subsequently spoken response;
determining, by the at least one processor and based on the portion corresponding to the one or more of the spoken user responses spoken before the subsequently spoken response, a plurality of key-value pairs corresponding to different possible resolutions for an unresolved anaphora in the subsequently spoken response; and
selecting, by the at least one processor, from amongst the plurality of key-value pairs, and based on a context of the dialogue determined from the one or more of the spoken user responses spoken before the subsequently spoken response, a key-value pair corresponding to a semantic interpretation in the list that resolves the unresolved anaphora in the subsequently spoken response.
2 Assignments
0 Petitions
Accused Products
Abstract
A human-machine dialog system is described which has multiple computer-implemented dialog components. A user client delivers output prompts to a human user and receives dialog inputs including speech inputs from the human user. An automatic speech recognition (ASR) engine processes the speech inputs to determine corresponding sequences of representative text words. A natural language understanding (NLU) engine processes the text words to determine corresponding semantic interpretations. A dialog manager (DM) generates the output prompts and responds to the semantic interpretations so as to manage a dialog process with the human user. The dialog components share context information with each other using a common context sharing mechanism such that the operation of each dialog component reflects available context information.
16 Citations
20 Claims
-
1. A method comprising:
-
receiving, by a computing system, data generated based on spoken user responses to prompts generated by the computing system that are 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 at least one processor of the computing system, a list of natural language understanding (NLU)-ranked semantic interpretations for the subsequently spoken response; determining, by the at least one processor and based on the portion corresponding to the one or more of the spoken user responses spoken before the subsequently spoken response, a plurality of key-value pairs corresponding to different possible resolutions for an unresolved anaphora in the subsequently spoken response; and selecting, by the at least one processor, from amongst the plurality of key-value pairs, and based on a context of the dialogue determined from the one or more of the spoken user responses spoken before the subsequently spoken response, a key-value pair corresponding to a semantic interpretation in the list that resolves the unresolved anaphora in the subsequently spoken response. - View Dependent Claims (2, 3, 4, 5, 6, 18)
-
-
7. A system comprising:
-
at least one processor; and a memory comprising instructions that when executed by the at least one processor cause the system to; receive data generated based on spoken user responses to prompts generated by the system that are 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; determine, based on the portion corresponding to the one or more of the spoken user responses spoken before the subsequently spoken response, a plurality of key-value pairs corresponding to different possible resolutions for an unresolved anaphora in the subsequently spoken response; and select, from amongst the plurality of key-value pairs and based on a context of the dialogue determined from the one or more of the spoken user responses spoken before the subsequently spoken response, a key-value pair corresponding to a semantic interpretation in the list that resolves the unresolved anaphora in the subsequently spoken response. - View Dependent Claims (8, 9, 10, 11, 12, 19)
-
-
13. One or more non-transitory computer-readable media comprising instructions that when executed by at least one processor of a computing system cause the computing system to:
-
receive data generated based on spoken user responses to prompts generated by the computing system that are 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; determine, based on the portion corresponding to the one or more of the spoken user responses spoken before the subsequently spoken response, a plurality of key-value pairs corresponding to different possible resolutions for an unresolved anaphora in the subsequently spoken response; and select, from amongst the plurality of key-value pairs and based on a context of the dialogue determined from the one or more of the spoken user responses spoken before the subsequently spoken response, a key-value pair corresponding to a semantic interpretation in the list that resolves the unresolved anaphora in the subsequently spoken response. - View Dependent Claims (14, 15, 16, 17, 20)
-
Specification