Evaluating and Improving Context Attention Distribution on Multi-Turn Response Generation using Self-Contained Distractions. (arXiv:2211.04943v1 [cs.CL])

Despite the rapid progress of open-domain generation-based conversational
agents, most deployed systems treat dialogue contexts as single-turns, while
systems dealing with multi-turn contexts are less studied. There is a lack of a
reliable metric for evaluating multi-turn modelling, as well as an effective
solution for improving it. In this paper, we focus on an essential component of
multi-turn generation-based conversational agents: context attention
distribution, i.e. how systems distribute their attention on dialogue's
context. For evaluation of this component, We introduce …

arxiv attention context distractions distribution