Self-attention Comparison Module for Boosting Performance on Retrieval-based Open-Domain Dialog Systems

TL;DR

This paper introduces a Self-attention Comparison Module (SCM) that enhances retrieval-based open-domain dialog systems by leveraging comparison information among candidate responses, leading to improved performance.

Contribution

The paper proposes a novel plug-in self-attention comparison module (SCM) that utilizes response comparisons to boost dialog system effectiveness.

Findings

SCM effectively improves dialog system performance

Extensive experiments validate the effectiveness of SCM

Source code is publicly released for future research

Abstract

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.