カテゴリ: 論文誌(論文単位)グループ名: 【C】電子・情報・システム部門発行日: 2019/12/01タイトル(英語): Dialogue Act Classification Using RNNs Introducing One-Versus-All and Attention Mechanism著者名: 泉 春乃（名古屋工業大学 大学院工学研究科 情報工学専攻），加藤 昇平（名古屋工業大学 大学院工学研究科 情報工学専攻／名古屋工業大学 情報科学フロンティア研究院）著者名(英語): Haruno Izumi (Department of Computer Science and Engineering, Graduate School of Engineering, Nagoya Institute of Technology), Shohei Kato (Department of Computer Science and Engineering, Graduate School of Engineering, Nagoya Institute of Technology/Frontier Research Institute for Information Science, Nagoya Institute of Technology)キーワード: 対話行為，LSTM，Attention機構 dialogue act，LSTM，attention mechanism要約(英語): For understanding the contents of a user's utterances, dialogue acts classification is often introduced to chat systems. This paper proposes Enhanced One-versus-All RNN (ENOVA RNN), which is a dialogue act classification model that consists of two RNN layers, one-versus-all layers, and the attention mechanism. The content of past utterances in dialogue is an important feature for dialogue acts classification models. In addition to the fact, classifiers tend to confuse dialogue acts that rarely appear in dialogue with frequent ones because the number of utterances differs greatly in each dialogue act. ENOVA RNN is a classification model to capture some features of dialogue acts that rarely appear after considering the content of past utterances in dialogues. In this study, it was confirmed that ENOVA RNN can classify dialogue acts using contexts not greater than six sentences. Moreover, ENOVA RNN improves rare dialogue acts classification performance keeping the overall quality of the performance by narrow down the dialogue acts using attention weights.本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.139 No.12 （2019） 特集：電気・電子・情報関係学会東海支部連合大会本誌掲載ページ: 1407-1414 p原稿種別: 論文／日本語電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/139/12/139_1407/_article/-char/ja/
