In human conversations, the emergence of new topics is a key factor in enabling dialogues to last longer. Additional information brought by new topics can make the conversation more diverse and interesting. Chat-bots also need to be equipped with this ability to proactively elicit new chatting topics. However, previous studies have neglected the elicitation of new topics in open-domain conversations. At the same time, previous works have represented topics with word-level keywords or entities. However, a topic is open to multiple keywords and a keyword can reflect multiple potential topics. To move towards a fine-grained topic representation, we represent topic with topically related words. In this paper, we design a novel model, named CMTE, which focuses not only on coherence with context, but also brings up new chatting topics. In order to extract topic information from conversational utterances, a Topic Fetcher module is designed to fetch semantic-coherent topics with the help of topic model. To equip model with the ability to elicit new topics, a Topic Manager module is designed to associate the new topic with context. Finally, responses are generated by a well-designed fusion decoding mechanism to explicitly distinguish between topic words and general words. Experiment results show that our model is better than state of the art in automatic metrics and manual evaluations.

在人类对话中，新话题的出现是让对话持续更长时间的关键因素。新话题带来的附加信息可以使对话更加多样化和有趣。聊天机器人还需要具备这种主动引发新聊天话题的能力。然而，之前的研究忽略了在开放域对话中引出新话题。同时，之前的作品已经用词级关键字或实体来表示主题。但是，一个主题对多个关键字开放，一个关键字可以反映多个潜在的主题。为了向细粒度的主题表示迈进，我们用与主题相关的词来表示主题。在本文中，我们设计了一个名为 CMTE 的新模型，它不仅关注与上下文的连贯性，而且还提出了新的聊天话题。为了从会话话语中提取主题信息，设计了一个 Topic Fetcher 模块来在主题模型的帮助下获取语义一致的主题。为了使模型具备引出新主题的能力，主题管理器模块旨在将新主题与上下文相关联。最后，通过精心设计的融合解码机制生成响应，以明确区分主题词和一般词。实验结果表明，我们的模型在自动度量和手动评估方面优于最先进的模型。响应由精心设计的融合解码机制生成，以明确区分主题词和一般词。实验结果表明，我们的模型在自动度量和手动评估方面优于最先进的模型。响应由精心设计的融合解码机制生成，以明确区分主题词和一般词。实验结果表明，我们的模型在自动度量和手动评估方面优于最先进的模型。