Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2024

Abstract

Generative models have been widely used in event extraction. However, the interpretability of event extraction has not been fully investigated. In this paper, we propose an Event Extraction framework based on LLM-generated CoT Explanation EE-LCE, which can generate chain-of-thought-style (CoT-style) explanations for events. To this end, we provide each sample of event datasets with an explanation of the reasoning process using a large language model (LLM) GPT-3.5, and fine-tune the Flan-T5 lightweight language model (LM) supervised by the augmented dataset, enhancing both interpretability and performance of the event extraction. Moreover, we use a prefix tree (trie) to normalize the decoding of generative event extraction, i.e. constraint decoding, so that it conforms to expectations. We perform experiments on three benchmark datasets for event extraction. The results of the experiments showcase the robust performance of EE-LCE in event extraction, affirming the effectiveness of both the CoT explanation and the constraint decoding function.Our code is publicly available at https://github.com/Wangyl147/EE-LCEhttps://github.com/Wangyl147/EE-LCE.

Keywords

Event extraction, Generative event extraction, Large language model, Chain of thought, Constraint decoding

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 17th International Conference, KSEM 2024, Birmingham, UK, August 16-18

First Page

28

Last Page

40

ISBN

9789819754915

Identifier

10.1007/978-981-97-5492-2_3

Publisher

Springer

City or Country

Cham

Additional URL

https://doi.org/10.1007/978-981-97-5492-2_3

Download

Share

COinS