Leveraging pre-trained language models for linguistic analysis: A case of argument structure constructions

Hakyung Sung, Kristopher Kyle


Abstract
This study evaluates the effectiveness of pre-trained language models in identifying argument structure constructions, important for modeling both first and second language learning. We examine three methodologies: (1) supervised training with RoBERTa using a gold-standard ASC treebank, including by-tag accuracy evaluation for sentences from both native and non-native English speakers, (2) prompt-guided annotation with GPT-4, and (3) generating training data through prompts with GPT-4, followed by RoBERTa training. Our findings indicate that RoBERTa trained on gold-standard data shows the best performance. While data generated through GPT-4 enhances training, it does not exceed the benchmarks set by gold-standard data.
Anthology ID:
2024.emnlp-main.415
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7302–7314
Language:
URL:
https://aclanthology.org/2024.emnlp-main.415
DOI:
10.18653/v1/2024.emnlp-main.415
Bibkey:
Cite (ACL):
Hakyung Sung and Kristopher Kyle. 2024. Leveraging pre-trained language models for linguistic analysis: A case of argument structure constructions. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7302–7314, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Leveraging pre-trained language models for linguistic analysis: A case of argument structure constructions (Sung & Kyle, EMNLP 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.emnlp-main.415.pdf