融合主题和实体嵌入的双向提示调优事件论元抽取

doi:10.11896/jsjkx.250100046

计算机科学 ›› 2026, Vol. 53 ›› Issue (1): 278-284.doi: 10.11896/jsjkx.250100046

融合主题和实体嵌入的双向提示调优事件论元抽取

陈千¹, 成凯璇¹, 郭鑫¹, 张晓霞², 王素格¹, 李艳红¹

1 山西大学计算机与信息技术学院太原 030006;
2 武汉设计工程学院武汉 430074

收稿日期:2025-01-09 修回日期:2025-04-28 发布日期:2026-01-08
通讯作者: 郭鑫(guoxinjsj@sxu.edu.cn)
作者简介:(chenqian857@163.com)
基金资助:
山西省基础研究计划(202203021221021,202203021221001,202303021211021,20210302123468);国家自然科学基金(62376143)

Bidirectional Prompt-Tuning for Event Argument Extraction with Topic and Entity Embeddings

CHEN Qian¹, CHENG Kaixuan¹, GUO Xin¹, ZHANG Xiaoxia², WANG Suge¹, LI Yanhong¹

1 School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China;
2 Wuhan Institute of Design and Sciences, Wuhan 430074, China

Received:2025-01-09 Revised:2025-04-28 Online:2026-01-08
About author:CHEN Qian,born in 1983,Ph.D,professor,is a member of CCF(No.E200048750M).His main research interests include information extraction and natural language processing.
GUO Xin,born in 1983,Ph.D,professor.Her main research interest is data mining.
Supported by:
Basic Research Project of Shanxi Province(202203021221021,202203021221001,202303021211021,20210302123468) and National Natural Science Foundation of China(62376143).

摘要/Abstract

摘要： 近年来,提示学习在自然语言处理领域得到了广泛应用。据调研,论元角色与文本中的主题往往有高度的语义相关性,且现有的提示调优方法忽略了实体信息和论元之间的交互。为此,提出一种融合主题和实体嵌入的双向提示调优事件论元抽取模型(TEPEAE)。首先,使用主题模型提取主题特征并进行主题嵌入化表示;其次,基于触发词、论元和实体信息构建提示模板,并将主题嵌入融入模板;然后,利用掩码语言模型预测每个实体的角色标签;最后,将标签从标签词空间映射到论元角色空间。在ACE2005-EN和ERE-EN数据集上的实验结果表明,TEPEAE优于基线模型,F1值分别达到79.53%和78.60%,验证了TEPEAE的有效性。此外,其在低资源场景下依然展现出卓越的性能,进一步证明其具有更强的鲁棒性。

关键词: 提示学习, 事件论元抽取, 实体嵌入, 主题嵌入, 注意力机制

Abstract: In recent years,prompt learning has been widely applied in the field of natural language processing.According to research,argument roles are highly semantically related to topics in text,and existing prompt tuning methods overlook entity information and interactions between arguments.Therefore,this paper proposes a bidirectional prompt tuning event argument extraction model(TEPEAE) that integrates topic and entity embeddings.Firstly,topic features are extracted using a topic model and embedded into a topic representation.Secondly,prompt templates are constructed based on trigger words,arguments,and entity information,incorporating topic embeddings into the template.Thirdly,masked language model(MLM) is utilized to predict the role label for each entity.Finally,labels are mapped from the label word space to the argument role space.Experiments on ACE2005-EN and ERE-EN datasets show that TEPEAE outperforms baseline models and achieves 79.53% and 78.60% in terms of F1,respectively,which demonstrates the effectiveness of TEPEAE.Moreover,it continues to demonstrate exceptional performance in low-resource scenarios,further proving its enhanced robustness.

Key words: Prompt learning, Event argument extraction, Entity embedding, Topic embedding, Attention mechanism

中图分类号:

TP391

陈千, 成凯璇, 郭鑫, 张晓霞, 王素格, 李艳红. 融合主题和实体嵌入的双向提示调优事件论元抽取[J]. 计算机科学, 2026, 53(1): 278-284. https://doi.org/10.11896/jsjkx.250100046

CHEN Qian, CHENG Kaixuan, GUO Xin, ZHANG Xiaoxia, WANG Suge, LI Yanhong. Bidirectional Prompt-Tuning for Event Argument Extraction with Topic and Entity Embeddings[J]. Computer Science, 2026, 53(1): 278-284. https://doi.org/10.11896/jsjkx.250100046

参考文献

[1]HU R J,ZHOU H,LIU H,et al.Survey on Document-LevelEvent Extraction Based on Deep Learning[J].Computer Engineering and Applications,2022,58(24):47-60.
[2]WADDEN D,WENNBERG U,LUAN Y,et al.Entity,relation,and event extraction with contextualized span representations[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.2019:5783-5788.
[3]PAOLINI G,ATHIWARATKUN B,KRONE J,et al.Structured prediction as translation between augmented natural languages[J].arXiv:2101.05779,2021.
[4]WANG X,WANG Z,HAN X,et al.HMEAE:Hierarchicalmodular event argument extraction[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.2019:5777-5783.
[5]LU Y,LIN H,XU J,et al.Text2Event:Controllable sequence-to-structure generation for end-to-end event extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.2021:2795-2806.
[6]CUI J M,LI D M,TIAN X,et al.Survey on Prompt Learning[J].Computer Engineering and Applications,2024,60(23):1-27.
[7]MA Y,WANG Z,CAO Y,et al.Prompt for extraction? PAIE:Prompting argument interaction for event argument extraction[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.2022:6759-6774.
[8]LIN Y,JI H,HUANG F,et al.A joint neural model for information extraction with global features[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:7999-8009.
[9]DU X,CARDIE C.Event extraction by answering(almost) na-tural questions[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.2020:671-683.
[10]LI F,PENG W,CHEN Y,et al.Event extraction as multi-turn question answering[C]//Findings of the Association for Computational Linguistics.2020:829-838.
[11]LI S,JI H,HAN J.Document-level event argument extractionby conditional generation[C]//Proceedings of the 2021 Confe-rence of the North American Chapter of the Association for Computational Linguistics.2021:894-908.
[12]HSU H,HUANG K H,BOSCHEE E,et al. Degree:A data-efficient generative event extraction model[C]//Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics.2022:1890-1908.
[13]HE Y,HU J,TANG B.Revisiting event argument extraction:can EAE models learn better when being aware of event co-occurrences?[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.2023:12542-12556.
[14]HSU I H,XIE Z,HUANG K H,et al.AMPERE:AMR-Aware Prefix for Generation-Based Event Argument Extraction Model[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.2023:10976-10993.
[15]DAI L,WANG B,XIANG W,et al.Bidirectional iterativeprompt-tuning for event argument extraction[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing.2022:6251-6263.
[16]DEVLIN J,CHANG M W,LEE K,et al. BERT:Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics.2019:4171-4186.
[17]LIU Y,OTT M,GOYAL N,et al.Roberta:A robustly opti-mized bert pretraining approach[J].arXiv:1907.116 92,2019.
[18]MENG Z,LIU T,ZHANG H,et al.CEAN:Contrastive event aggregation network with LLM-based augmentation for event extraction[C]//Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics.2024:321-333.
[19]YANG Y,GUO J Y,SHUANG K,et al.Scented-EAE:Stage-Customized Entity Type Embedding for Event Argument Extraction[C]//Findings of the Association for Computational Linguistics.2024:5222-5235.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

融合主题和实体嵌入的双向提示调优事件论元抽取

Bidirectional Prompt-Tuning for Event Argument Extraction with Topic and Entity Embeddings

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0