Self-attention Comparison Module for Boosting Performance on Retrieval-based Open-Domain Dialog Systems
This work provides an incremental improvement for researchers working on retrieval-based open-domain dialog systems by introducing a module that considers inter-candidate comparisons.
This paper addresses the limitation of retrieval-based open-domain dialog systems that only consider the matching degree between a query and individual candidate responses. The authors propose a Self-attention Comparison Module (SCM) to leverage comparison information among candidate responses, which effectively boosts the performance of existing systems.
Since the pre-trained language models are widely used, retrieval-based open-domain dialog systems, have attracted considerable attention from researchers recently. Most of the previous works select a suitable response only according to the matching degree between the query and each individual candidate response. Although good performance has been achieved, these recent works ignore the comparison among the candidate responses, which could provide rich information for selecting the most appropriate response. Intuitively, better decisions could be made when the models can get access to the comparison information among all the candidate responses. In order to leverage the comparison information among the candidate responses, in this paper, we propose a novel and plug-in Self-attention Comparison Module for retrieval-based open-domain dialog systems, called SCM. Extensive experiment results demonstrate that our proposed self-attention comparison module effectively boosts the performance of the existing retrieval-based open-domain dialog systems. Besides, we have publicly released our source codes for future research.