Existing conversational systems tend to generate generic responses. Recently, Background Based Conversations (BBCs) have been introduced to address this issue. Here, the generated responses are grounded in some background information. The proposed methods for BBCs are able to generate more informative responses, they either cannot generate natural responses or have difficulty in locating the right background information. In this paper, we propose a Reference-aware Network (RefNet) to address the two issues. Unlike existing methods that generate responses token by token, RefNet incorporates a novel reference decoder that provides an alternative way to learn to directly cite a semantic unit (e.g., a span containing complete semantic information) from the background. Experimental results show that RefNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, indicating that RefNet can generate more appropriate and human-like responses.
@article{arxiv.1908.06449,
title = {RefNet: A Reference-aware Network for Background Based Conversation},
author = {Chuan Meng and Pengjie Ren and Zhumin Chen and Christof Monz and Jun Ma and Maarten de Rijke},
journal= {arXiv preprint arXiv:1908.06449},
year = {2019}
}