BERT-based response selection in dialogue systems using utterance attention mechanisms

作者：

Highlights：

• BERT-based response selection in dialogue systems.

• Utterance attention to comprehend relationships between utterances and response.

• Proposed method achieved a performance improvement in DSTC8 datasets.

摘要

•BERT-based response selection in dialogue systems.•Utterance attention to comprehend relationships between utterances and response.•Proposed method achieved a performance improvement in DSTC8 datasets.

论文关键词：Dialogue system,Natural language processing,Deep learning,Response selection,Attention mechanism,BERT

论文评审过程：Received 12 May 2020, Revised 22 July 2022, Accepted 22 July 2022, Available online 27 July 2022, Version of Record 1 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118277