-
公开(公告)号：US20190115027A1
公开(公告)日：2019-04-18
申请号：US15782333
申请日：2017-10-12
Applicant: Google LLC
Inventor： Pararth Shah , Larry Paul Heck , Dilek Hakkani-Tur
CPC classification number: G10L15/30 , G06F16/90332 , G06F17/27 , G10L15/005 , G10L15/16 , G10L15/22 , G10L17/22 , H04L51/02
Abstract: Techniques are described related to turn-based reinforcement learning for dialog management. In various implementations, dialog states and corresponding responsive actions generated during a multi-turn human-to-computer dialog session may be obtained. A plurality of turn-level training instances may be generated, each including: a given dialog state of the plurality of dialog states at an outset of a given turn of the human-to-computer dialog session; and a given responsive action that was selected based on the given dialog state. One or more of the turn-level training instances may further include a turn-level feedback value that reflects on the given responsive action selected during the given turn. A reward value may be generated based on an outcome of the human-to-computer dialog session. The dialog management policy model may be trained based on turn-level feedback values of the turn-level training instance(s) and the reward value.
-
公开(公告)号：US20210074279A1
公开(公告)日：2021-03-11
申请号：US16952413
申请日：2020-11-19
Applicant: Google LLC
Inventor： Abhinav Rastogi , Larry Paul Heck , Dilek Hakkani-Tur
Abstract: Determining a dialog state of an electronic dialog that includes an automated assistant and at least one user, and performing action(s) based on the determined dialog state. The dialog state can be represented as one or more slots and, for each of the slots, one or more candidate values for the slot and a corresponding score (e.g., a probability) for each of the candidate values. Candidate values for a slot can be determined based on language processing of user utterance(s) and/or system utterance(s) during the dialog. In generating scores for candidate value(s) of a given slot at a given turn of an electronic dialog, various features are determined based on processing of the user utterance and the system utterance using a memory network. The various generated features can be processed using a scoring model to generate scores for candidate value(s) of the given slot at the given turn.
-
公开(公告)号：US20230419960A1
公开(公告)日：2023-12-28
申请号：US18367785
申请日：2023-09-13
Applicant: GOOGLE LLC
Inventor： Abhinav Rastogi , Larry Paul Heck , Dilek Hakkani-Tur
CPC classification number: G10L15/197 , G06N3/08 , G10L15/16 , G10L15/1815 , G10L15/22 , G10L15/30 , G10L15/1822 , G10L2015/223 , G06N3/044
Abstract: Determining a dialog state of an electronic dialog that includes an automated assistant and at least one user, and performing action(s) based on the determined dialog state. The dialog state can be represented as one or more slots and, for each of the slots, one or more candidate values for the slot and a corresponding score (e.g., a probability) for each of the candidate values. Candidate values for a slot can be determined based on language processing of user utterance(s) and/or system utterance(s) during the dialog. In generating scores for candidate value(s) of a given slot at a given turn of an electronic dialog, various features are determined based on processing of the user utterance and the system utterance using a memory network. The various generated features can be processed using a scoring model to generate scores for candidate value(s) of the given slot at the given turn.
-
公开(公告)号：US11790899B2
公开(公告)日：2023-10-17
申请号：US16952413
申请日：2020-11-19
Applicant: Google LLC
Inventor： Abhinav Rastogi , Larry Paul Heck , Dilek Hakkani-Tur
CPC classification number: G10L15/197 , G06N3/08 , G10L15/16 , G10L15/1815 , G10L15/22 , G10L15/30 , G06N3/044 , G10L15/1822 , G10L2015/223
Abstract: Determining a dialog state of an electronic dialog that includes an automated assistant and at least one user, and performing action(s) based on the determined dialog state. The dialog state can be represented as one or more slots and, for each of the slots, one or more candidate values for the slot and a corresponding score (e.g., a probability) for each of the candidate values. Candidate values for a slot can be determined based on language processing of user utterance(s) and/or system utterance(s) during the dialog. In generating scores for candidate value(s) of a given slot at a given turn of an electronic dialog, various features are determined based on processing of the user utterance and the system utterance using a memory network. The various generated features can be processed using a scoring model to generate scores for candidate value(s) of the given slot at the given turn.
-
Patent Agency Ranking
5.发明公开公开(公告)号：US20230206911A1
公开(公告)日：2023-06-29
申请号：US18116201
申请日：2023-03-01
Applicant: GOOGLE LLC
Inventor： Ankur Bapna , Larry Paul Heck
CPC classification number: G10L15/1815 , G06F16/3329 , G06N3/08 , G06N3/048 , G10L15/16 , G10L15/22
Abstract: Determining slot value(s) based on received natural language input and based on descriptor(s) for the slot(s). In some implementations, natural language input is received as part of human-to-automated assistant dialog. A natural language input embedding is generated based on token(s) of the natural language input. Further, descriptor embedding(s) are generated (or received), where each of the descriptor embeddings is generated based on descriptor(s) for a corresponding slot that is assigned to a domain indicated by the dialog. The natural language input embedding and the descriptor embedding(s) are applied to layer(s) of a neural network model to determine, for each of the slot(s), which token(s) of the natural language input correspond to the slot. A command is generated that includes slot value(s) for slot(s), where the slot value(s) for one or more of the slot(s) are determined based on the token(s) determined to correspond to the slot(s).
-
公开(公告)号：US10424302B2
公开(公告)日：2019-09-24
申请号：US15782333
申请日：2017-10-12
Applicant: Google LLC
Inventor： Pararth Shah , Larry Paul Heck , Dilek Hakkani-Tur
Abstract: Techniques are described related to turn-based reinforcement learning for dialog management. In various implementations, dialog states and corresponding responsive actions generated during a multi-turn human-to-computer dialog session may be obtained. A plurality of turn-level training instances may be generated, each including: a given dialog state of the plurality of dialog states at an outset of a given turn of the human-to-computer dialog session; and a given responsive action that was selected based on the given dialog state. One or more of the turn-level training instances may further include a turn-level feedback value that reflects on the given responsive action selected during the given turn. A reward value may be generated based on an outcome of the human-to-computer dialog session. The dialog management policy model may be trained based on turn-level feedback values of the turn-level training instance(s) and the reward value.
-
公开(公告)号：US11610579B2
公开(公告)日：2023-03-21
申请号：US16622404
申请日：2017-06-18
Applicant: Google LLC
Inventor： Ankur Bapna , Larry Paul Heck
Abstract: Determining slot value(s) based on received natural language input and based on descriptor(s) for the slot(s). In some implementations, natural language input is received as part of human-to-automated assistant dialog. A natural language input embedding is generated based on token(s) of the natural language input. Further, descriptor embedding(s) are generated (or received), where each of the descriptor embeddings is generated based on descriptor(s) for a corresponding slot that is assigned to a domain indicated by the dialog. The natural language input embedding and the descriptor embedding(s) are applied to layer(s) of a neural network model to determine, for each of the slot(s), which token(s) of the natural language input correspond to the slot. A command is generated that includes slot value(s) for slot(s), where the slot value(s) for one or more of slot(s) are determined based on the token(s) determined to correspond to the slot(s).
-
公开(公告)号：US20200320988A1
公开(公告)日：2020-10-08
申请号：US16321294
申请日：2017-10-12
Applicant: Google LLC
Inventor： Abhinav Rastogi , Larry Paul Heck , Dilek Hakkani-Tur
Abstract: Determining a dialog state of an electronic dialog that includes an automated assistant and at least one user, and performing action(s) based on the determined dialog state. The dialog state can be represented as one or more slots and, for each of the slots, one or more candidate values for the slot and a corresponding score (e.g., a probability) for each of the candidate values. Candidate values for a slot can be determined based on language processing of user utterance(s) and/or system utterance(s) during the dialog. In generating scores for candidate value(s) of a given slot at a given turn of an electronic dialog, various features are determined based on processing of the user utterance and the system utterance using a memory network. The various generated features can be processed using a scoring model to generate scores for candidate value(s) of the given slot at the given turn.
-
公开(公告)号：US10083169B1
公开(公告)日：2018-09-25
申请号：US15248966
申请日：2016-08-26
Applicant: Google LLC
Inventor： Shalini Ghosh , Oriol Vinyals , Brian Patrick Strope , Howard Scott Roy , Thomas L. Dean , Larry Paul Heck
CPC classification number: G06F17/279 , G06F17/2881 , G06N3/0445 , G06N3/084
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing word sequences using neural networks. One of the methods includes receiving a first sequence of words arranged according to a first order; and for each word in the first sequence, beginning with a first word in the first order: determining a topic vector that is associated with the word; generating a combined input from the word and the topic vector, and processing the combined input through one or more sequence modeling layers to generate a sequence modeling output for the word; and processing one or more of the sequence modeling outputs through an output layer to generate a neural network output for the first sequence of words.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.015 seconds)
