人工知能学会論文誌
Online ISSN : 1346-8030
Print ISSN : 1346-0714
ISSN-L : 1346-0714
原著論文
Controlled Neural Response Generation by Given Dialogue Acts Based on Label-aware Adversarial Learning
Seiya KawanoKoichiro YoshinoSatoshi Nakamura
著者情報
ジャーナル フリー

2021 年 36 巻 4 号 p. E-KC9_1-14

詳細
抄録

Building a controllable neural conversation model (NCM) is an important task. In this paper, we focus on controlling the responses of NCMs using dialogue act labels of responses as conditions. We introduce a reinforcement learning framework involving adversarial learning for conditional response generation. Our proposed method has a new label-aware objective that encourages the generation of discriminative responses by the given dialogue act label while maintaining the naturalness of the generated responses. We compared the proposed method with conventional methods that generate conditional responses. The experimental results showed that our proposed method has higher controllability conditioned by the dialogue acts even though it has higher or comparable naturalness to the conventional models.

著者関連情報
© The Japanese Society for Artificial Intelligence 2021
前の記事
feedback
Top