Evaluating and Improving Context Attention Distribution on Multi-Turn Response Generation using Self-Contained Distractions
This addresses the lack of reliable evaluation and effective improvement for multi-turn modeling in conversational AI, which is an incremental advancement for researchers and developers in dialogue systems.
The paper tackled the problem of evaluating and improving context attention distribution in multi-turn conversational agents by introducing a novel metric called DAS ratio and an optimization strategy using self-contained distractions. The result showed that models with similar perplexity could be distinguished by this metric, and the strategy improved both non-hierarchical and hierarchical models by about 10% from baselines.
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 a novel attention-mechanism-based metric: DAS ratio. To improve performance on this component, we propose an optimization strategy that employs self-contained distractions. Our experiments on the Ubuntu chatlogs dataset show that models with comparable perplexity can be distinguished by their ability on context attention distribution. Our proposed optimization strategy improves both non-hierarchical and hierarchical models on the proposed metric by about 10% from baselines.