dc.contributor.author |
KAWANO, SEIYA |
en |
dc.contributor.author |
MIZUKAMI, MASAHIRO |
en |
dc.contributor.author |
YOSHINO, KOICHIRO |
en |
dc.contributor.author |
NAKAMURA, SATOSHI |
en |
dc.date.accessioned |
2020-11-26T07:50:30Z |
en |
dc.date.available |
2020-11-26T07:50:30Z |
en |
dc.date.issued |
2020-10-08 |
en |
dc.identifier.uri |
http://hdl.handle.net/10061/14161
|
en |
dc.description.abstract |
The synchronization of words in conversation, called entrainment, is generally observed in
human-human conversations. Entrainment has a high correlation with dialogue success, naturalness, and
engagement. In this article, we de ne entrainment scores based on the word similarities in semantic space to
evaluate the entrainment of system generation.We optimized a neural conversation model to the entrainment
scores using reinforcement learning so that the system can control the degree of entrainment of the system
response. Experimental results showed that the proposed entrainable neural conversation model generated
comparable or more natural responses than conventional models and satisfactorily controlled the degree of
entrainment of the generated responses. |
en |
dc.language.iso |
en |
en |
dc.publisher |
IEEE |
en |
dc.relation.isreplacedby |
https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9206588
|
en |
dc.rights |
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.
For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ |
en |
dc.subject |
Neural conversation model |
en |
dc.subject |
conditional response generation |
en |
dc.subject |
entrainment |
en |
dc.subject |
dialogue evaluation |
en |
dc.subject |
reinforcement learning |
en |
dc.title |
Entrainable Neural Conversation Model Based on Reinforcement Learning |
en |
dc.type.nii |
Journal Article |
en |
dc.contributor.transcription |
カワノ, セイヤ |
ja |
dc.contributor.transcription |
ヨシノ, コウイチロウ |
ja |
dc.contributor.transcription |
ナカムラ, サトシ |
ja |
dc.contributor.alternative |
河野, 誠也 |
ja |
dc.contributor.alternative |
吉野, 幸一郎 |
ja |
dc.contributor.alternative |
中村, 哲 |
ja |
dc.textversion |
none |
en |
dc.identifier.eissn |
2169-3536 |
en |
dc.identifier.jtitle |
IEEE Access |
en |
dc.identifier.volume |
8 |
en |
dc.relation.doi |
10.1109/ACCESS.2020.3027099 |
en |
dc.identifier.NAIST-ID |
85620920 |
en |
dc.identifier.NAIST-ID |
74651712 |
en |
dc.identifier.NAIST-ID |
73296626 |
en |