Chinese UMR annotation: Can LLMs help?

Haibo Sun, Nianwen Xue, Jin Zhao, Liulu Yue, Yao Sun, Keer Xu, Jiawei Wu


Abstract
We explore using LLMs, GPT-4 specifically, to generate draft sentence-level Chinese Uniform Meaning Representations (UMRs) that human annotators can revise to speed up the UMR annotation process. In this study, we use few-shot learning and Think-Aloud prompting to guide GPT-4 to generate sentence-level graphs of UMR. Our experimental results show that compared with annotating UMRs from scratch, using LLMs as a preprocessing step reduces the annotation time by two thirds on average. This indicates that there is great potential for integrating LLMs into the pipeline for complicated semantic annotation tasks.
Anthology ID:
2024.dmr-1.14
Volume:
Proceedings of the Fifth International Workshop on Designing Meaning Representations @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Claire Bonial, Julia Bonn, Jena D. Hwang
Venues:
DMR | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
131–139
Language:
URL:
https://aclanthology.org/2024.dmr-1.14
DOI:
Bibkey:
Cite (ACL):
Haibo Sun, Nianwen Xue, Jin Zhao, Liulu Yue, Yao Sun, Keer Xu, and Jiawei Wu. 2024. Chinese UMR annotation: Can LLMs help?. In Proceedings of the Fifth International Workshop on Designing Meaning Representations @ LREC-COLING 2024, pages 131–139, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Chinese UMR annotation: Can LLMs help? (Sun et al., DMR-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.dmr-1.14.pdf