3.8 Proceedings Paper

Stylized Dialogue Response Generation Using Stylized Unpaired Texts

Publisher

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE

Keywords

-

Funding

  1. Major Project of the New Generation of Artificial Intelligence [2018AAA0102900]
  2. NSFC [61936010, 61876096]
  3. Guoqiang Institute of Tsinghua University [2019GQG1]
  4. THUNUS NExT Joint-Lab

Ask authors/readers for more resources

This study proposes a stylized dialogue generation method that can capture stylistic features embedded in unpaired texts, which outperforms competitive baselines in producing coherent and style-intensive dialogue responses through joint training with an inverse dialogue model and stylized pseudo dialogue pairs.
Generating stylized responses is essential to build intelligent and engaging dialogue systems. However, this task is far from well-explored due to the difficulties of rendering a particular style in coherent responses, especially when the target style is embedded only in unpaired texts that cannot be directly used to train the dialogue model. This paper proposes a stylized dialogue generation method that can capture stylistic features embedded in unpaired texts. Specifically, our method can produce dialogue responses that are both coherent to the given context and conform to the target style. In this study, an inverse dialogue model is first introduced to predict possible posts for the input responses. Then this inverse model is used to generate stylized pseudo dialogue pairs based on these stylized unpaired texts. Further, these pseudo pairs are employed to train the stylized dialogue model with a joint training process. A style routing approach is proposed to intensify stylistic features in the decoder. Automatic and manual evaluations on two datasets demonstrate that our method outperforms competitive baselines in producing coherent and style-intensive dialogue responses.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available