Generating Informative Dialogue Responses with Keywords-Guided Networks
Heng-Da Xu, Xian-Ling Mao, Zewen Chi, Jing-Jing Zhu, Fanshu Sun, Heyan, Huang

TL;DR
This paper introduces a keywords-guided Seq2Seq model for dialogue systems that generates more informative and coherent responses by incorporating topic keywords, addressing the issue of generic replies in open-domain conversations.
Contribution
The paper proposes a novel keywords-guided Seq2Seq model that improves response informativeness and coherence in dialogue systems, validated through extensive experiments.
Findings
Produces more informative responses
Achieves higher automatic evaluation scores
Receives positive human evaluation feedback
Abstract
Recently, open-domain dialogue systems have attracted growing attention. Most of them use the sequence-to-sequence (Seq2Seq) architecture to generate responses. However, traditional Seq2Seq-based open-domain dialogue models tend to generate generic and safe responses, which are less informative, unlike human responses. In this paper, we propose a simple but effective keywords-guided Sequence-to-Sequence model (KW-Seq2Seq) which uses keywords information as guidance to generate open-domain dialogue responses. Specifically, KW-Seq2Seq first uses a keywords decoder to predict some topic keywords, and then generates the final response under the guidance of them. Extensive experiments demonstrate that the KW-Seq2Seq model produces more informative, coherent and fluent responses, yielding substantive gain in both automatic and human evaluation metrics.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Speech and dialogue systems
