LLM-supertagger: Categorial Grammar Supertagging via Large Language Models

Jinman Zhao, Gerald Penn


Abstract
Supertagging is an essential task in Categorical grammar parsing and is crucial for dissecting sentence structures. Our research explores the capacity of Large Language Models (LLMs) in supertagging for both Combinatory Categorial Grammar (CCG) and Lambek Categorial Grammar (LCG). We also present a simple method that significantly boosts LLMs, enabling them to outperform LSTM and encoder-based models and achieve state-of-the-art performance. This advancement highlights LLMs’ potential in classification tasks, showcasing their adaptability beyond generative capabilities. Our findings demonstrate the evolving utility of LLMs in natural language processing, particularly in complex tasks like supertagging.
Anthology ID:
2024.findings-emnlp.39
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
697–705
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.39
DOI:
10.18653/v1/2024.findings-emnlp.39
Bibkey:
Cite (ACL):
Jinman Zhao and Gerald Penn. 2024. LLM-supertagger: Categorial Grammar Supertagging via Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 697–705, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
LLM-supertagger: Categorial Grammar Supertagging via Large Language Models (Zhao & Penn, Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.39.pdf