CEAMC: Corpus and Empirical Study of Argument Analysis in Education via LLMs
Yupei Ren, Hongyi Wu, Zhaoguang Long, Shangqing Zhao, Xinyi Zhou, Zheqin Yin, Xinlin Zhuang, Xiaopeng Bai
Abstract
This paper introduces the Chinese Essay Argument Mining Corpus (CEAMC), a manually annotated dataset designed for argument component classification on multiple levels of granularity. Existing argument component types in education remain simplistic and isolated, failing to encapsulate the complete argument information. Originating from authentic examination settings, CEAMC categorizes argument components into 4 coarse-grained and 10 fine-grained delineations, surpassing previous simple representations to capture the subtle nuances of argumentation in the real world, thus meeting the needs of complex and diverse argumentative scenarios. Our contributions include the development of CEAMC, the establishment of baselines for further research, and a thorough exploration of the performance of Large Language Models (LLMs) on CEAMC. The results indicate that our CEAMC can serve as a challenging benchmark for the development of argument analysis in education.
BibTeX
@inproceedings{ren-etal-2024-ceamc,
title = "{CEAMC}: Corpus and Empirical Study of Argument Analysis in Education via {LLM}s",
author = "Ren, Yupei and
Wu, Hongyi and
Long, Zhaoguang and
Zhao, Shangqing and
Zhou, Xinyi and
Yin, Zheqin and
Zhuang, Xinlin and
Bai, Xiaopeng and
Lan, Man",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.408/",
doi = "10.18653/v1/2024.findings-emnlp.408",
pages = "6949--6966"
}