论文标题
使用风格的未配对文本进行程式化的对话响应生成
Stylized Dialogue Response Generation Using Stylized Unpaired Texts
论文作者
论文摘要
生成风格化的响应对于建立智能和引人入胜的对话系统至关重要。但是，由于难以在连贯的响应中呈现特定样式的困难，尤其是当目标样式仅嵌入不成对话的文本中时，该任务远非探索。本文提出了一种风格化的对话生成方法，该方法可以捕获嵌入未配对文本的风格特征。具体而言，我们的方法可以产生对话响应，这些响应既与给定上下文都一致，又符合目标样式。在这项研究中，首先引入了一个反话模型，以预测输入响应的可能帖子，然后使用此逆模型来基于这些风格的未配对文本来生成风格化的伪对话对。此外，使用这些伪对通过联合培训过程来训练风格化的对话模型，并提出了一种样式的路由方法来增强解码器中的风格功能。两个数据集上的自动和手动评估表明，我们的方法在产生连贯和风格的对话响应方面优于竞争基准。
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, and 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, and 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.
