Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm

Hexuan Deng, Xin Zhang, Meishan Zhang, Xuebo Liu, Min Zhang

Abstract
In this paper, we conduct a holistic exploration of Universal Decompositional Semantic (UDS) parsing, aiming to provide a more efficient and effective solution for semantic parsing and to envision the development prospects after the emergence of large language models (LLMs). To achieve this, we first introduce a cascade model for UDS parsing that decomposes the complex task into semantically appropriate subtasks. Our approach outperforms prior models while significantly reducing inference time. Furthermore, to further exploit the hierarchical and automated annotation process of UDS, we explore the use of syntactic information and pseudo-labels, both of which enhance UDS parsing. Lastly, we investigate ChatGPT’s efficacy in handling the UDS task, highlighting its proficiency in attribute parsing but struggles in relation parsing, revealing that small parsing models still hold research significance. Our code is available at https://github.com/hexuandeng/HExp4UDS.
Anthology ID:
2024.sighan-1.6
Volume:
Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Kam-Fai Wong, Min Zhang, Ruifeng Xu, Jing Li, Zhongyu Wei, Lin Gui, Bin Liang, Runcong Zhao
Venues:
SIGHAN | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
45–57
Language:
URL:
https://aclanthology.org/2024.sighan-1.6
DOI:
Bibkey:
Cite (ACL):
Hexuan Deng, Xin Zhang, Meishan Zhang, Xuebo Liu, and Min Zhang. 2024. Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm. In Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10), pages 45–57, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm (Deng et al., SIGHAN-WS 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/2024.sighan-1.6.pdf
PDF Search Fix metadata