Presentation information

International Session

International Session » E-2 Machine learning

[3F5-ES-2] Machine learning: Conversation and emotions

Thu. Jun 11, 2020 3:40 PM - 5:20 PM Room F (jsai2020online-6)

Chair: Rafik Hadfi (Nagoya Institute of Technology)

4:20 PM - 4:40 PM

[3F5-ES-2-03] A Transfer Learning Method of Data Collection for Dialogue Response Generation concerning Causal Relation

〇Bo Yang1, Jianming Wu1, Gen Hattori1 (1. KDDI Research, Inc.)

Keywords:Deep Learning, Machine Learning, Causal Relation, Transfer Learning, Dialog Response Generation

In order to generate more content-rich responses, as well as avoid monotonous or irrelevant ones, some researchers set off to focus on dialogue generation models in which causal relation is also taken into consideration. However, it is hard to distinguish whether there is causal relation between speaker’s and responder’s utterances from dialogue automatically, which makes collecting such utterance pairs even harder. In this paper, a transfer learning method for dialogue generation training data collection is proposed: the sentence with causal relation feature is learned from web contents such as Wikipedia in the first place and further used to detect utterance pairs containing causal relation from dialogs. Subsequently, the collected utterance pairs can be used for dialogue response generation, which can make agent’s response retain pre-learned causal relation feature in sentence level according to user’s utterance. It is shown that the proposed method yields good performance by using BERT embedding in detecting causal relation from utterance turn in dialogs corpus.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.