JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >

このアイテムの引用には次の識別子を使用してください: http://hdl.handle.net/10119/18787

タイトル: Persona-based Dialogue Generation with Sentence Embedding for Prolonged Human-Robot Communication
著者: Yue, Chen
Elibol, Armagan
Chong, Nak Young
キーワード: Human-Robot Interaction
Dialogue generation
発行日: 2023-10
出版者: Institute of Control, Robotics and Systems (ICROS)
誌名: 2023 23rd International Conference on Control, Automation and Systems (ICCAS)
開始ページ: 1657
終了ページ: 1664
DOI: 10.23919/ICCAS59377.2023.10316939
抄録: It is one of the most fundamental and challenging problems for current dialogue generation systems to maintain the consistency of dialogue logic during the conversation. Also, the lack of an open-source annotated personabased dialogue dataset may lead to insufficient training volume for the model. Besides, the computational time and computational memory required by the attention mechanism have become drastically large. In order to overcome these problems, in this work, we propose a vertical-structure model based on the BERT model with the sentence embedding method. The model generates a raw response based on the sentence embeddings of context and persona and finally revises the raw response according to the persona. Moreover, an understanding task is designed for the BERT decoder to have a better revision ability. Considering the difference between the generation and the understanding models, three kinds of input methods are designed for each part of the model. Comparative and experimental results are presented using publicly available datasets.
Rights: This is the author's version of the work. Copyright (C) ICROS. 2023 23rd International Conference on Control, Automation and Systems (ICCAS 2023), 2023, pp. 1657-1664. DOI: 10.23919/ICCAS59377.2023.10316939. Personal use of this material is permitted. This material is posted here with permission of Institute of Control, Robotics and Systems (ICROS).
URI: http://hdl.handle.net/10119/18787
資料タイプ: author
出現コレクション:b11-1. 会議発表論文・発表資料 (Conference Papers)

このアイテムのファイル:

ファイル 記述 サイズ形式
N-CHONG-I-1122-1.pdf878KbAdobe PDF見る/開く

当システムに保管されているアイテムはすべて著作権により保護されています。

 


お問い合わせ先 : 北陸先端科学技術大学院大学 研究推進課図書館情報係