中文意合图语义解析评测

Guo Mengxi (郭梦溪), Li Meng (李梦), Jin Zeying (靳泽莹), Wu Xiaojing (吴晓靖), Rao Gaoqi (高琦 饶), Tang Gongbo (唐共波), Xun Endong (恩东 荀)


Abstract
“中文意合图是近年提出的中文语义表示方法。本次评测是首次基于意合图理论的语义分析评测,旨在探索面向意合图理论的语义计算方法,评估机器的语义分析能力。本次评测共有14支队伍报名,最终有7支队伍提交结果,其中有5支队伍提交技术报告与模型,均成功复现。在评测截止时间内,表现最好的队伍使用大语言模型LoRA微调方法获得了F1值为72.06%的成绩。在最终提交技术报告的5支队伍中,有4支队伍使用了大语言模型微调方法,在一定程度上表明了目前技术发展的趋势。”
Anthology ID:
2024.ccl-3.9
Volume:
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)
Month:
July
Year:
2024
Address:
Taiyuan, China
Editors:
Hongfei Lin, Hongye Tan, Bin Li
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
80–86
Language:
Chinese
URL:
https://aclanthology.org/2024.ccl-3.9/
DOI:
Bibkey:
Cite (ACL):
Guo Mengxi, Li Meng, Jin Zeying, Wu Xiaojing, Rao Gaoqi, Tang Gongbo, and Xun Endong. 2024. 中文意合图语义解析评测. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations), pages 80–86, Taiyuan, China. Chinese Information Processing Society of China.
Cite (Informal):
中文意合图语义解析评测 (Mengxi et al., CCL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.ccl-3.9.pdf