Generating a Variety of Backchannel Forms Based on Linguistic and Prosodic Features for Attentive Listening Agents
-
- Yamaguchi Takashi
- Graduate School of Informatics, Kyoto University
-
- Inoue Koji
- Graduate School of Informatics, Kyoto University
-
- Koichiro Yoshino
- Graduate School of Information Science, Nara Institute of Science and Technology
-
- Takanashi Katsuya
- Graduate School of Informatics, Kyoto University
-
- Ward Nigel G.
- Department of Computer Science, University of Texas at El Paso / Academic Center for Computing and Media Studies, Kyoto University
-
- Kawahara Tatsuya
- Graduate School of Informatics / Academic Center for Computing and Media Studies, Kyoto University
Bibliographic Information
- Other Title
-
- 傾聴対話システムのための言語情報と韻律情報に基づく多様な形態の相槌の生成
- ” Generating a Variety of Backchannel Forms Based on Linguistic and Prosodic Features for Listening Agents.”
Abstract
There is a growing interest in conversation agents and robots which conduct attentive listening. However, the current systems always generate the same or limited forms of backchannels every time, giving a monotonous impression. This study investigates the generation of a variety of backchannel forms appropriate for the dialogue context, using the corpus of counseling dialogue. At first, we annotate all acceptable backchannel form categories considering the permissible variation in backchannels. Second, we analyze how the morphological form of backchannels relates to linguistic features of the preceding utterance such as the utterance boundary type and the linguistic complexity. Based on this analysis, we conduct machine learning to predict backchannel form from the linguistic and prosodic features of the preceding context. This model outperformed a baseline which always outputs the same form of backchannels and another baseline which randomly generates backchannels. Finally, subjective evaluations by human listeners show that the proposed method generates backchannels more naturally and gives a feeling of understanding and empathy.
Journal
-
- Transactions of the Japanese Society for Artificial Intelligence
-
Transactions of the Japanese Society for Artificial Intelligence 31 (4), C-G31_1-10, 2016
The Japanese Society for Artificial Intelligence
- Tweet
Details 詳細情報について
-
- CRID
- 1390282680083880832
-
- NII Article ID
- 130005254929
-
- ISSN
- 13468030
- 13460714
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed