arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.04562cs.CL
收藏

TIAGE:一个话题转移感知对话建模的基准

TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling

University of Cambridge(剑桥大学);Northeastern University(东北大学);Microsoft Research(微软研究院);Tsinghua University(清华大学)

Huiyuan Xie, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu, Ann Copestake

摘要:

人类的对话自然会围绕不同的主题发展,并在它们之间流畅地移动。在对话系统的研究中,主动平滑地转换到新话题的能力往往被忽视。在本文中,我们介绍了TIAGE,一个新的主题转移意识的对话基准构建利用人类注释的主题转移。基于TIAGE,我们介绍了三个任务来研究不同的场景中的话题转移模型的对话设置:话题转移检测,话题转移触发响应生成和话题感知对话生成。对这些任务的实验表明,TIAGE中的主题转换信号对主题转换反应的产生是有用的。另一方面,对话系统仍然难以决定何时改变话题。这表明,主题转移感知对话建模需要进一步的研究。

英文摘要:

Human conversations naturally evolve around different topics and fluently move between them. In research on dialog systems, the ability to actively and smoothly transition to new topics is often ignored. In this paper we introduce TIAGE, a new topic-shift aware dialog benchmark constructed utilizing human annotations on topic shifts. Based on TIAGE, we introduce three tasks to investigate different scenarios of topic-shift modeling in dialog settings: topic-shift detection, topic-shift triggered response generation and topic-aware dialog generation. Experiments on these tasks show that the topic-shift signals in TIAGE are useful for topic-shift response generation. On the other hand, dialog systems still struggle to decide when to change topic. This indicates further research is needed in topic-shift aware dialog modeling.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑