Automatic Intent-Slot Induction for Dialogue Systems
Zengfeng Zeng, Dan Ma, Haiqin Yang, Zhen Gou, Jianping Shen

TL;DR
This paper introduces RCAP, a novel three-step, domain-independent method for automatic intent-slot induction in dialogue systems, reducing manual effort and improving schema generation and generalization to new domains.
Contribution
The paper proposes a new coarse-to-fine approach for automatic intent-slot induction that outperforms supervised methods and applies effectively to out-of-domain datasets.
Findings
RCAP outperforms state-of-the-art supervised methods.
Achieves at least 76% improvement in intent detection F1-score.
Gains 41% improvement in slot filling F1-score.
Abstract
Automatically and accurately identifying user intents and filling the associated slots from their spoken language are critical to the success of dialogue systems. Traditional methods require manually defining the DOMAIN-INTENT-SLOT schema and asking many domain experts to annotate the corresponding utterances, upon which neural models are trained. This procedure brings the challenges of information sharing hindering, out-of-schema, or data sparsity in open-domain dialogue systems. To tackle these challenges, we explore a new task of {\em automatic intent-slot induction} and propose a novel domain-independent tool. That is, we design a coarse-to-fine three-step procedure including Role-labeling, Concept-mining, And Pattern-mining (RCAP): (1) role-labeling: extracting keyphrases from users' utterances and classifying them into a quadruple of coarsely-defined intent-roles via sequence…
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 · Advanced Text Analysis Techniques
