公开(公告)号：US11604925B1

公开(公告)日：2023-03-14

申请号：US16881520

申请日：2020-05-22

Applicant: Amazon Technologies, Inc.

Inventor： Kyung Jae Lee ,  Charlotte Alizerine Dzialo ,  Lan Ma ,  Liu Yang ,  Yi Qin ,  Prathap Ramachandra ,  Wenbo Yan ,  Darshan Ashok Fofadiya

IPC: G06F17/00 ,  G06F40/295 ,  G10L15/16 ,  G06N3/04 ,  G10L15/197 ,  G06F40/30 ,  G06N3/08 ,  G06F17/18

Abstract: Features are disclosed for training and using named entity recognition models based on gazetteer information. A named entity recognition model can be trained with a gazetteer output at a layer of the model to provide deterministic data in the probabilistic model. The named entity recognition model can recognize named entities based on the word embedding and the gazetteer output. The named entity recognition model can tune the gazetteer output to include false positive name entities such that the gazetteer output is not deterministic of the output of the model. In some embodiments, the named entity recognition model can be tuned so as to adjust the gazetteer output.

公开(公告)号：US11823671B1

公开(公告)日：2023-11-21

申请号：US16872047

申请日：2020-05-11

Applicant: Amazon Technologies, Inc.

Inventor： Prathap Ramachandra ,  Lan Ma ,  Liu Yang ,  Yi Qin ,  Kyung Jae Lee ,  Wenbo Yan ,  Charlotte Alizerine Dzialo ,  Darshan Ashok Fofadiya

IPC: G10L15/22 ,  G06F40/279

CPC classification number: G10L15/22 ,  G06F40/279

Abstract: Features are disclosed for training and using a word embedding model configured to receive textual and context data associated with an utterance of a user. A word embedding model can be trained with text data and context data to account for context associated with the text data. The word embedding model can receive an input vector including text data and one or more sets of context data associated with the text data and perform word embedding based on the input vector. In some embodiments, the input vector can include an automatic speech recognition (“ASR”) confidence score generated by an ASR model and one or more labels generated by an NLU model. In some embodiments, the input vector can include user information associated with the user.