Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vukovic, Renato, Arps, David, van Niekerk, Carel, Ruppik, Benjamin Matthias, Lin, Hsien-Chin, Heck, Michael, Gašić, Milica
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917947494105088
author Vukovic, Renato
Arps, David
van Niekerk, Carel
Ruppik, Benjamin Matthias
Lin, Hsien-Chin
Heck, Michael
Gašić, Milica
author_facet Vukovic, Renato
Arps, David
van Niekerk, Carel
Ruppik, Benjamin Matthias
Lin, Hsien-Chin
Heck, Michael
Gašić, Milica
contents 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 threshold. By constraining the decoding to ontology terms and relations, we aim to decrease the risk of hallucination. We conduct extensive experimentation on two widely used datasets and find improvements in performance on target ontology for source fine-tuned and one-shot prompted large language models.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02361
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding
Vukovic, Renato
Arps, David
van Niekerk, Carel
Ruppik, Benjamin Matthias
Lin, Hsien-Chin
Heck, Michael
Gašić, Milica
Computation and Language
Artificial Intelligence
Machine Learning
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 threshold. By constraining the decoding to ontology terms and relations, we aim to decrease the risk of hallucination. We conduct extensive experimentation on two widely used datasets and find improvements in performance on target ontology for source fine-tuned and one-shot prompted large language models.
title Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2408.02361