期刊文献+

基于先验提示模板的冲突事件抽取方法研究

Few-Shot Conflict Event Extraction Method Based on Prior Prompt Templates
原文传递
导出
摘要 【目的/意义】针对冲突事件领域数据集较少,现有事件抽取方法强依赖于大量数据,在低资源场景上面临着训练效果差、泛化能力不足的问题,本文提出了一种基于先验提示模板的小样本事件抽取方法PriorPromptEE。【方法/过程】本文首先基于“政治、军事”维度,完善冲突事件表示框架,采用人机协同方式,构建冲突事件小样本数据集。其次,本文为提示模板设计构造策略,在模型编码层嵌入基于先验知识的提示模板,输出层采用双指针实现事件元素的预测。【结果/结论】实验结果表明,PriorPromptEE能够在冲突事件小样本数据集上取得较好效果。对比序列模型,提升42%至45%,对比传统事件抽取模型,提升19%至45%,对比提示学习零样本抽取模型,提升19%,PriorPromptEE达到0.85,验证了该方法的有效性。【创新/局限】本文从“政治、军事”维度完善了冲突事件表示框架,采用提示学习的方式为冲突事件的核心元素抽取提供了新的思路,未来可从经济、舆情等维度完善表示框架,强化冲突事件抽取模型框架。 【Purpose/significance】In the field of conflict events,there is a lack of datasets,and existing event extraction methods heavily rely on large amounts of data,leading to poor training effectiveness and insufficient generalization ability in low-resource scenarios.To address these issues,this paper proposes a few-shot event extraction method,PriorPromptEE,based on prior prompt templates.【Method/process】Firstly,this paper improves the conflict event representation framework based on the political and military dimension,and constructs a few-shot conflict event extraction dataset using a semi-automatic labeling method.Secondly,a pipeline is used to design and construct strategies for prompt template generation.The prompt templates are embedded in the model's encoding layer based on prior knowledge,and the output layer employs a double-pointer mechanism to extract entity start and end positions,thus achieving event argument prediction.【Result/conclusion】Experimental results show that the proposed event extraction method,which incorporates prior prompt templates,performs well on few-shot conflict event dataset.Compared to sequence models,the score is improved by 42%to 45%,compared to traditional event extraction models,the score is improved by 19%to 45%,and compared to zeroshot event extraction models,the score is improved by 19%.The score of the proposed model,PriorPromptEE,reaches up to 0.85,validating the effectiveness of this approach.【Innovation/limitation】This paper improves the framework for representing conflict events from the perspective of international relations of political and military,and provides a new approach for identifying conflict types and extracting core elements based on prior prompt templates.In the future,the framework for representing conflict events could be further enhanced from economic,public opinion,and other dimensions to strengthen the model framework for conflict event extraction.
作者 陆伟 冯子琨 程齐凯 石湘 熊资 LU Wei;FENG Zikun;CHENG Qikai;SHI Xiang;XIONG Zi(School of Information Management,Wuhan University,Wuhan 430072,China;Wuhan University Information Retrieval and Knowledge Mining Laboratory,Wuhan University,Wuhan 430072,China)
出处 《情报科学》 CSSCI 北大核心 2024年第4期1-8,共8页 Information Science
基金 国家自然科学基金面上项目“基于机器阅读理解的科学命题文本论证逻辑识别”(72174157)。
关键词 冲突事件 事件抽取 小样本 提示学习 提示模板构造 conflict event event extraction few-shot prompt learning prompt template construction
  • 相关文献

参考文献7

二级参考文献52

  • 1张晓艳,王挺,陈火旺.命名实体识别研究[J].计算机科学,2005,32(4):44-48. 被引量:67
  • 2姜吉发.一种事件信息抽取模式获取方法[J].计算机工程,2005,31(15):96-98. 被引量:27
  • 3俞鸿魁,张华平,刘群,吕学强,施水才.基于层叠隐马尔可夫模型的中文命名实体识别[J].通信学报,2006,27(2):87-94. 被引量:160
  • 4Wikipedia:Message Understanding Conference[EB/OL].2013-12-27.http://en.wikipedia.org/wiki/Message_Understanding_Conference. 被引量:1
  • 5Wikipedia:Named Entity Recognition[EB/OL].2013-12-28.http://en.wikipedia.org/wiki/Named_Entity_Recognition. 被引量:1
  • 6Rizzo G,Troncy R.NERD:Evaluating Named Entity Recognition Toolsinthe Web of Data[J].Lecture Notesin Computer Science,2012(7295):39-55. 被引量:1
  • 7Rizzo G,Troncy R.NERD:A Framework for Unifying Named Entity Recognition and Disam biguation Extraction Tools[C]∥13th Conference ofthe European Chapter of the Association for ComputationalL inguistics.2012:73-76. 被引量:1
  • 8Li Chen-liang,Weng Jian-shu.TwiNER:Named Entity Recognition in Targeted Twitter Stream[C]∥SIGIR.2012:721-730. 被引量:1
  • 9Liu Xiao-hua,Zhang Shao-dian,et al.Recognizing Named Entitiesin Tweets[C]∥ACL.2011:359-367. 被引量:1
  • 10Finin T,Murnane W.Annotating Named Entitiesin TwitterDatawith Crowdsourcing[C]∥ACL.2010. 被引量:1

共引文献145

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部