论文标题
通过动态主题跟踪的多方对话的响应选择
Response Selection for Multi-Party Conversations with Dynamic Topic Tracking
论文作者
论文摘要
当多方多转交谈的参与者同时参与了多个对话主题，但现有的响应选择方法主要集中在两党单转换场景上。因此，当前方法忽略了对话主题的延长和过渡。在这项工作中，我们将响应选择作为动态主题跟踪任务，以匹配响应和相关对话上下文之间的主题。通过这种新的配方，我们提出了一个新型的多任务学习框架，该框架通过仅使用两种话语的大型模型来支持有效编码，以执行动态主题分解和响应选择。我们还建议主题 - 伯特一个必不可少的预处理步骤，将主题信息纳入BERT中，并通过自我监督的学习。 DSTC-8 Ubuntu IRC数据集的实验结果显示了最先进的结果，结果选择了响应选择和主题分离任务，使现有方法的差距良好。
While participants in a multi-party multi-turn conversation simultaneously engage in multiple conversation topics, existing response selection methods are developed mainly focusing on a two-party single-conversation scenario. Hence, the prolongation and transition of conversation topics are ignored by current methods. In this work, we frame response selection as a dynamic topic tracking task to match the topic between the response and relevant conversation context. With this new formulation, we propose a novel multi-task learning framework that supports efficient encoding through large pretrained models with only two utterances at once to perform dynamic topic disentanglement and response selection. We also propose Topic-BERT an essential pretraining step to embed topic information into BERT with self-supervised learning. Experimental results on the DSTC-8 Ubuntu IRC dataset show state-of-the-art results in response selection and topic disentanglement tasks outperforming existing methods by a good margin.
