Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
Wenya Zhu, Kaixiang Mo, Yu Zhang, Zhangbin Zhu, Xuezheng Peng, Qiang, Yang

TL;DR
This paper introduces GenDS, a data-driven dialogue system capable of generating knowledge-grounded responses with multiple or no entities, handling out-of-vocabulary entities, and outperforming baselines on music and QA datasets.
Contribution
The paper presents a novel dynamic knowledge enquirer for dialogue generation that handles multiple entities and out-of-vocabulary cases without relying on entity representations.
Findings
GenDS outperforms baseline methods in BLEU, entity accuracy, and recall.
The system effectively generates responses with multiple or no entities.
GenDS performs well even on small datasets.
Abstract
In knowledge grounded conversation, domain knowledge plays an important role in a special domain such as Music. The response of knowledge grounded conversation might contain multiple answer entities or no entity at all. Although existing generative question answering (QA) systems can be applied to knowledge grounded conversation, they either have at most one entity in a response or cannot deal with out-of-vocabulary entities. We propose a fully data-driven generative dialogue system GenDS that is capable of generating responses based on input message and related knowledge base (KB). To generate arbitrary number of answer entities even when these entities never appear in the training set, we design a dynamic knowledge enquirer which selects different answer entities at different positions in a single response, according to different local context. It does not rely on the representations…
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
