English

Content Selection Network for Document-grounded Retrieval-based Chatbots

Computation and Language 2021-01-22 v1

Abstract

Grounding human-machine conversation in a document is an effective way to improve the performance of retrieval-based chatbots. However, only a part of the document content may be relevant to help select the appropriate response at a round. It is thus crucial to select the part of document content relevant to the current conversation context. In this paper, we propose a document content selection network (CSN) to perform explicit selection of relevant document contents, and filter out the irrelevant parts. We show in experiments on two public document-grounded conversation datasets that CSN can effectively help select the relevant document contents to the conversation context, and it produces better results than the state-of-the-art approaches. Our code and datasets are available at https://github.com/DaoD/CSN.

Keywords

Cite

@article{arxiv.2101.08426,
  title  = {Content Selection Network for Document-grounded Retrieval-based Chatbots},
  author = {Yutao Zhu and Jian-Yun Nie and Kun Zhou and Pan Du and Zhicheng Dou},
  journal= {arXiv preprint arXiv:2101.08426},
  year   = {2021}
}

Comments

ECIR 2021 Camera Ready

R2 v1 2026-06-23T22:22:28.138Z