Construction of CFSP Model Based on Non-Finetuning Large Language Model

Huang Fugeng, Guo Zhongbin, Li Wenting, Cheng Haibo


Abstract
“Chinese Frame Semantic Parsing (CFSP) is an important task in the field of Chinese Natural Language Processing(NLP). Its goal is to extract the frame semantic structure from the sentence and realize the deep understanding of the events or situations involved in the sentence. This paper mainly studies the application of Large Language Model (LLM) for reasoning through Prompt Engineering without fine-tuning the model, and completes three subtasks of Chinese Framework Semantic Parsing tasks: frame identification, argument Identification and role identification. This paper proposes a Retrieval Augmented Generation (RAG) method for target words, and constructs more refined sample Few-Shot method. We achieved the second place on the B rankings in the open track in the “CCL2024-Eval The Second Chinese Frame Semantic Parsing”competition*.”
Anthology ID:
2024.ccl-3.1
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:
1–9
Language:
English
URL:
https://aclanthology.org/2024.ccl-3.1/
DOI:
Bibkey:
Cite (ACL):
Huang Fugeng, Guo Zhongbin, Li Wenting, and Cheng Haibo. 2024. Construction of CFSP Model Based on Non-Finetuning Large Language Model. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations), pages 1–9, Taiyuan, China. Chinese Information Processing Society of China.
Cite (Informal):
Construction of CFSP Model Based on Non-Finetuning Large Language Model (Fugeng et al., CCL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.ccl-3.1.pdf