公开(公告)号：US20210142794A1

公开(公告)日：2021-05-13

申请号：US17099875

申请日：2020-11-17

申请人： Amazon Technologies, Inc.

发明人： Lambert Leo Mathias ,  Bala Murali Krishna Ummaneni ,  Ryan Scott Aldrich ,  Diamond Bishop ,  Ruhi Sarikaya ,  Chetan Nagaraj Naik

IPC分类号： G10L15/18 ,  G10L15/22 ,  G06F40/30 ,  G06F40/295 ,  G06F16/9032

摘要： A system for processing user utterances and/or text based queries that tracks entities and other context data of a current dialog between the system and the user and can fill slots for new intents of the dialog by performing statistical processing on previously mentioned entities with respect to current slots to be filled. The system may compare a previously mentioned entity to a current slot to be filled using vector representations, such as word embeddings, of the current utterance, dialog history, current intent, name of an entity under consideration, category of the current slot to be filled, distance between the current dialog turn and the dialog turn that mentioned the entity, and other considerations. The individual vectors may be weighted according to an attention operation and processed by a trained decoder to output a score indicating whether the entity in consideration is relevant to the particular slot. In this manner, slots may be filled using entities from previous dialog turns, thus performing statistical anaphora resolution and leading to improved system performance.

公开(公告)号：US20230089285A1

公开(公告)日：2023-03-23

申请号：US17853013

申请日：2022-06-29

申请人： Amazon Technologies, Inc.

发明人： Xing Fan ,  Zheng Chen ,  Yuan Ling ,  Lambert Leo Mathias ,  Chenlei Guo

IPC分类号： G10L15/197 ,  G10L15/22 ,  G10L15/30 ,  G10L15/18

摘要： A system is provided for reducing friction during user interactions with a natural language processing system, such as voice assistant systems. The system determines a pre-trained model using dialog session data corresponding to multiple user profiles. The system determines a fine-tuned model using the pre-trained model and a fine-tuning dataset that corresponds to a particular task, such as query rewriting. The system uses the fine-tuned model to process a user input and determine an alternative representation of the input that can result in a desired response from the natural language processing system.

公开(公告)号：US11386890B1

公开(公告)日：2022-07-12

申请号：US16788085

申请日：2020-02-11

申请人： Amazon Technologies, Inc.

发明人： Xing Fan ,  Zheng Chen ,  Yuan Ling ,  Lambert Leo Mathias ,  Chenlei Guo

IPC分类号： G10L15/197 ,  G10L15/22 ,  G10L15/30 ,  G10L15/18

摘要： A system is provided for reducing friction during user interactions with a natural language processing system, such as voice assistant systems. The system determines a pre-trained model using dialog session data corresponding to multiple user profiles. The system determines a fine-tuned model using the pre-trained model and a fine-tuning dataset that corresponds to a particular task, such as query rewriting. The system uses the fine-tuned model to process a user input and determine an alternative representation of the input that can result in a desired response from the natural language processing system.