HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management
Silin Gao, Ryuichi Takanobu, Wei Peng, Qun Liu, Minlie Huang

TL;DR
HyKnow is an end-to-end task-oriented dialog system that effectively manages both structured and unstructured knowledge, improving dialog accuracy and knowledge retrieval over existing methods.
Contribution
This paper introduces HyKnow, the first end-to-end TOD model that jointly optimizes dialog management with hybrid knowledge handling, including unstructured data.
Findings
HyKnow outperforms existing TOD systems in end-to-end tasks.
It achieves higher unstructured knowledge retrieval accuracy.
Demonstrates effectiveness on a modified MultiWOZ 2.1 dataset.
Abstract
Task-oriented dialog (TOD) systems typically manage structured knowledge (e.g. ontologies and databases) to guide the goal-oriented conversations. However, they fall short of handling dialog turns grounded on unstructured knowledge (e.g. reviews and documents). In this paper, we formulate a task of modeling TOD grounded on both structured and unstructured knowledge. To address this task, we propose a TOD system with hybrid knowledge management, HyKnow. It extends the belief state to manage both structured and unstructured knowledge, and is the first end-to-end model that jointly optimizes dialog modeling grounded on these two kinds of knowledge. We conduct experiments on the modified version of MultiWOZ 2.1 dataset, where dialogs are grounded on hybrid knowledge. Experimental results show that HyKnow has strong end-to-end performance compared to existing TOD systems. It also outperforms…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Speech and dialogue systems · Natural Language Processing Techniques
