Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks

• Item type: SIG Technical Reports(1)
• 公開日: 2017-12-14
• タイトル: Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks
• タイトル / 言語: en
• タイトル: Joint Learning of Dialog Act Segmentation and Recognition in Spoken Dialog Using Neural Networks
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: ポスターセッション
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: School of Informatics, Kyoto University
• 著者所属: School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): School of Informatics, Kyoto University
• 著者名: Tianyu, Zhao; Tatsuya, Kawahara
• 著者名(英): Tianyu, Zhao; Tatsuya, Kawahara
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Dialog act segmentation and recognition are basic natural language understanding tasks in spoken dialog systems. This paper investigates a unified architecture for these two tasks, which aims to improve the model's performance on both of the tasks. Compared with past joint models, the proposed architecture can (1) incorporate contextual information in dialog act recognition, and (2) integrate models for tasks of different levels as a whole, i.e. dialog act segmentation on the word level and dialog act recognition on the segment level. Experimental results show that the joint training system outperforms the simple cascading system and the joint coding system on both dialog act segmentation and recognition tasks.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Dialog act segmentation and recognition are basic natural language understanding tasks in spoken dialog systems. This paper investigates a unified architecture for these two tasks, which aims to improve the model's performance on both of the tasks. Compared with past joint models, the proposed architecture can (1) incorporate contextual information in dialog act recognition, and (2) integrate models for tasks of different levels as a whole, i.e. dialog act segmentation on the word level and dialog act recognition on the segment level. Experimental results show that the joint training system outperforms the simple cascading system and the joint coding system on both dialog act segmentation and recognition tasks.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10442647
• 書誌情報: 研究報告音声言語情報処理（SLP）; 巻 2017-SLP-119, 号 12, p. 1-6, 発行日 2017-12-14
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8663
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会