论文标题
减轻混合对话系统中的负面样式转移
Mitigating Negative Style Transfer in Hybrid Dialogue System
论文作者
论文摘要
随着对话系统的功能，可以实现特定于用户的目标并参与用户参与开放式chitchat的混合对话系统正在吸引日益增长的关注。现有研究都学会了同时利用多任务融合技术的两项任务，但忽略了由独特的文本样式差异引起的负面转移现象。因此，基于潜在变量模型的对比学习用于将潜在空间中的各种文本类型解脱。我们为各种数据集设计了有监督和自我监督的正面和负面样本结构。此外，要利用脱钩的潜在变量中包含的样式信息，我们采用了样式前缀，该样式前缀进一步结合了潜在变量，以通过不同的样式控制响应的产生。我们对三个对话数据集进行了广泛的实验，包括混合对话数据集和两个面向任务的对话数据集。实验结果表明，我们的方法可以减轻负面样式转移问题，并在多个对话数据集中实现最先进的性能。
As the functionality of dialogue systems evolves, hybrid dialogue systems that accomplish user-specific goals and participate in open-topic chitchat with users are attracting growing attention. Existing research learns both tasks concurrently utilizing a multi-task fusion technique but ignores the negative transfer phenomenon induced by the unique textual style differences. Therefore, contrastive learning based on the latent variable model is used to decouple the various textual genres in the latent space. We devise supervised and self-supervised positive and negative sample constructions for diverse datasets. In addition, to capitalize on the style information contained in the decoupled latent variables, we employ a style prefix that incorporates latent variables further to control the generation of responses with varying styles. We performed extensive experiments on three dialogue datasets, including a hybrid dialogue dataset and two task-oriented dialogue datasets. The experimental results demonstrate that our method can mitigate the negative style transfer issue and achieves state-of-the-art performance on multiple dialogue datasets.
