Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding
Renato Vukovic, David Arps, Carel van Niekerk, Benjamin Matthias, Ruppik, Hsien-Chin Lin, Michael Heck, Milica Ga\v{s}i\'c

TL;DR
This paper introduces a constrained Chain-of-Thought decoding method for relation extraction in dialogue ontologies, enhancing generalization and reducing hallucinations in large language models for ontology construction.
Contribution
It extends Chain-of-Thought decoding with constraints to improve relation extraction accuracy and robustness in dialogue ontology construction tasks.
Findings
Improved relation extraction performance on two datasets.
Enhanced generalization in transfer learning scenarios.
Reduced hallucination in large language model outputs.
Abstract
State-of-the-art task-oriented dialogue systems typically rely on task-specific ontologies for fulfilling user queries. The majority of task-oriented dialogue data, such as customer service recordings, comes without ontology and annotation. Such ontologies are normally built manually, limiting the application of specialised systems. Dialogue ontology construction is an approach for automating that process and typically consists of two steps: term extraction and relation extraction. In this work, we focus on relation extraction in a transfer learning set-up. To improve the generalisation, we propose an extension to the decoding mechanism of large language models. We adapt Chain-of-Thought (CoT) decoding, recently developed for reasoning problems, to generative relation extraction. Here, we generate multiple branches in the decoding space and select the relations based on a confidence…
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
TopicsService-Oriented Architecture and Web Services · Semantic Web and Ontologies · Topic Modeling
Methodstravel james · Ontology · Focus
