基于动态提示学习和依存关系的生成式结构化情感分析模型(Dynamic Prompt Learning and Dependency Relation based Generative Structured Sentiment Analysis Model)

Jia Yintao (贾银涛), Cui Jiajia (崔佳佳), Mu Lingling (穆玲玲), Zan Hongying (昝红英)


Abstract
“结构化情感分析旨在从文本中抽取所有由情感持有者、目标事物、观点表示和情感极性构成的情感元组,是较为全面的细粒度情感分析任务。针对目前结构化情感分析方法错误传递,提示模版适应性不足和情感要素构成复杂的问题,本文提出了基于动态提示学习和依存关系的生成式结构化情感分析模型,根据不同的情感元组构成情况分别设计提示模版,并用模板增强生成式预训练模型的输入,用依存关系增强生成效果。实验结果显示,本文提出的模型在SemEval20221数据集上的SF1值优于所对比的基线模型。”
Anthology ID:
2024.ccl-1.34
Volume:
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
Month:
July
Year:
2024
Address:
Taiyuan, China
Editors:
Maosong Sun, Jiye Liang, Xianpei Han, Zhiyuan Liu, Yulan He
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
442–453
Language:
Chinese
URL:
https://aclanthology.org/2024.ccl-1.34/
DOI:
Bibkey:
Cite (ACL):
Jia Yintao, Cui Jiajia, Mu Lingling, and Zan Hongying. 2024. 基于动态提示学习和依存关系的生成式结构化情感分析模型(Dynamic Prompt Learning and Dependency Relation based Generative Structured Sentiment Analysis Model). In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), pages 442–453, Taiyuan, China. Chinese Information Processing Society of China.
Cite (Informal):
基于动态提示学习和依存关系的生成式结构化情感分析模型(Dynamic Prompt Learning and Dependency Relation based Generative Structured Sentiment Analysis Model) (Yintao et al., CCL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.ccl-1.34.pdf