Presentation 2018-09-14
A Study on Interaction Analysis Using Japanese Learner's Conversation Data and the Tendency of Dialogue Breaking
Hiromitsu Ota,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, the introduction of chat bots to call centers and the like has become popular, more accurate, dialogue response with less breakdown is required. On the other hand, in the field of natural language processing using deep learning, expression learning such as word 2 vec spreads, the responses and utterances between utterances are emphasized and challenged. Therefore, we examined application of qualitative mutual action framework in sociology's ethnomethodology and conversation analysis. We examined effectiveness by using the Japanese language learner conversation data of the National Institute of Japanese Language and examined the characteristics of dialog crash and the applicability of automatic dialogue generation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) chatbot / Seq2Seq / word2vec / automatic dialogue generation / Ethnomethodology / conversation analysis / Dialogue collapse / Dialogue response
Paper # DE2018-9
Date of Issue 2018-09-05 (DE)

Conference Information
Conference Date 2018/9/12(3days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Akiyo Nadamoto(Konan Univ.)
Vice Chair Jun Miyazaki(Tokyo Inst. of Tech.) / Shingo Otsuka(Kanagawa Inst. of Tech.)
Secretary Jun Miyazaki(Univ. of Hyogo) / Shingo Otsuka(Univ. of Marketing and Distrbution Science)
Assistant Kazuo Goda(Univ. of Tokyo) / Hiroaki Shiokawa(Tsukuba Univ.)

Paper Information
Registration To Technical Committee on Data Engineering / Special Interest Group on Database System / Special Interest Group on Information Fundamentals and Access Technologies
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study on Interaction Analysis Using Japanese Learner's Conversation Data and the Tendency of Dialogue Breaking
Sub Title (in English)
Keyword(1) chatbot
Keyword(2) Seq2Seq
Keyword(3) word2vec
Keyword(4) automatic dialogue generation
Keyword(5) Ethnomethodology
Keyword(6) conversation analysis
Keyword(7) Dialogue collapse
Keyword(8) Dialogue response
1st Author's Name Hiromitsu Ota
1st Author's Affiliation The Open University of Japan(OUJ)
Date 2018-09-14
Paper # DE2018-9
Volume (vol) vol.118
Number (no) DE-213
Page pp.pp.1-6(DE),
#Pages 6
Date of Issue 2018-09-05 (DE)