HyperED:基于双曲几何的事件检测分层感知网络

IF 1.8 4区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Computational Intelligence Pub Date : 2024-01-04 DOI:10.1111/coin.12627
Meng Zhang, Zhiwen Xie, Jin Liu, Xiao Liu, Xiao Yu, Bo Huang
{"title":"HyperED:基于双曲几何的事件检测分层感知网络","authors":"Meng Zhang,&nbsp;Zhiwen Xie,&nbsp;Jin Liu,&nbsp;Xiao Liu,&nbsp;Xiao Yu,&nbsp;Bo Huang","doi":"10.1111/coin.12627","DOIUrl":null,"url":null,"abstract":"<p>Event detection plays an essential role in the task of event extraction. It aims at identifying event trigger words in a sentence and classifying event types. Generally, multiple event types are usually well-organized with a hierarchical structure in real-world scenarios, and hierarchical correlations between event types can be used to enhance event detection performance. However, such kind of hierarchical information has received insufficient attention which can lead to misclassification between multiple event types. In addition, the most existing methods perform event detection in Euclidean space, which cannot adequately represent hierarchical relationships. To address these issues, we propose a novel event detection network HyperED which embeds the event context and types in Poincaré ball of hyperbolic geometry to help learn hierarchical features between events. Specifically, for the event detection context, we first leverage the pre-trained BERT or BiLSTM in Euclidean space to learn the semantic features of ED sentences. Meanwhile, to make full use of the dependency knowledge, a GNN-based model is applied when encoding event types to learn the correlations between events. Then we use a simple neural-based transformation to project the embeddings into the Poincaré ball to capture hierarchical features, and a distance score in hyperbolic space is computed for prediction. The experiments on MAVEN and ACE 2005 datasets indicate the effectiveness of the HyperED model and prove the natural advantages of hyperbolic spaces in expressing hierarchies in an intuitive way.</p>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"40 1","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"HyperED: A hierarchy-aware network based on hyperbolic geometry for event detection\",\"authors\":\"Meng Zhang,&nbsp;Zhiwen Xie,&nbsp;Jin Liu,&nbsp;Xiao Liu,&nbsp;Xiao Yu,&nbsp;Bo Huang\",\"doi\":\"10.1111/coin.12627\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Event detection plays an essential role in the task of event extraction. It aims at identifying event trigger words in a sentence and classifying event types. Generally, multiple event types are usually well-organized with a hierarchical structure in real-world scenarios, and hierarchical correlations between event types can be used to enhance event detection performance. However, such kind of hierarchical information has received insufficient attention which can lead to misclassification between multiple event types. In addition, the most existing methods perform event detection in Euclidean space, which cannot adequately represent hierarchical relationships. To address these issues, we propose a novel event detection network HyperED which embeds the event context and types in Poincaré ball of hyperbolic geometry to help learn hierarchical features between events. Specifically, for the event detection context, we first leverage the pre-trained BERT or BiLSTM in Euclidean space to learn the semantic features of ED sentences. Meanwhile, to make full use of the dependency knowledge, a GNN-based model is applied when encoding event types to learn the correlations between events. Then we use a simple neural-based transformation to project the embeddings into the Poincaré ball to capture hierarchical features, and a distance score in hyperbolic space is computed for prediction. The experiments on MAVEN and ACE 2005 datasets indicate the effectiveness of the HyperED model and prove the natural advantages of hyperbolic spaces in expressing hierarchies in an intuitive way.</p>\",\"PeriodicalId\":55228,\"journal\":{\"name\":\"Computational Intelligence\",\"volume\":\"40 1\",\"pages\":\"\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2024-01-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computational Intelligence\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/coin.12627\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computational Intelligence","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/coin.12627","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

事件检测在事件提取任务中发挥着至关重要的作用。它旨在识别句子中的事件触发词,并对事件类型进行分类。一般来说,在现实世界的场景中,多个事件类型通常具有良好的组织层次结构,事件类型之间的层次相关性可用于提高事件检测性能。然而,这类分层信息没有得到足够重视,可能导致多种事件类型之间的错误分类。此外,现有的大多数方法都是在欧几里得空间中进行事件检测,无法充分体现层次关系。为了解决这些问题,我们提出了一种新颖的事件检测网络 HyperED,它将事件上下文和类型嵌入双曲几何的波恩卡莱球中,以帮助学习事件之间的层次特征。具体来说,对于事件检测上下文,我们首先利用欧几里得空间中预先训练好的 BERT 或 BiLSTM 来学习 ED 句子的语义特征。同时,为了充分利用依赖性知识,我们在对事件类型进行编码时采用了基于 GNN 的模型来学习事件之间的相关性。然后,我们使用基于神经的简单变换将嵌入投影到波恩卡莱球中,以捕捉分层特征,并计算双曲空间中的距离得分,从而进行预测。在 MAVEN 和 ACE 2005 数据集上的实验表明了 HyperED 模型的有效性,并证明了双曲空间在直观表达层次结构方面的天然优势。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
HyperED: A hierarchy-aware network based on hyperbolic geometry for event detection

Event detection plays an essential role in the task of event extraction. It aims at identifying event trigger words in a sentence and classifying event types. Generally, multiple event types are usually well-organized with a hierarchical structure in real-world scenarios, and hierarchical correlations between event types can be used to enhance event detection performance. However, such kind of hierarchical information has received insufficient attention which can lead to misclassification between multiple event types. In addition, the most existing methods perform event detection in Euclidean space, which cannot adequately represent hierarchical relationships. To address these issues, we propose a novel event detection network HyperED which embeds the event context and types in Poincaré ball of hyperbolic geometry to help learn hierarchical features between events. Specifically, for the event detection context, we first leverage the pre-trained BERT or BiLSTM in Euclidean space to learn the semantic features of ED sentences. Meanwhile, to make full use of the dependency knowledge, a GNN-based model is applied when encoding event types to learn the correlations between events. Then we use a simple neural-based transformation to project the embeddings into the Poincaré ball to capture hierarchical features, and a distance score in hyperbolic space is computed for prediction. The experiments on MAVEN and ACE 2005 datasets indicate the effectiveness of the HyperED model and prove the natural advantages of hyperbolic spaces in expressing hierarchies in an intuitive way.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Computational Intelligence
Computational Intelligence 工程技术-计算机:人工智能
CiteScore
6.90
自引率
3.60%
发文量
65
审稿时长
>12 weeks
期刊介绍: This leading international journal promotes and stimulates research in the field of artificial intelligence (AI). Covering a wide range of issues - from the tools and languages of AI to its philosophical implications - Computational Intelligence provides a vigorous forum for the publication of both experimental and theoretical research, as well as surveys and impact studies. The journal is designed to meet the needs of a wide range of AI workers in academic and industrial research.
期刊最新文献
Issue Information Comprehensive analysis of feature-algorithm interactions for fall detection across age groups via machine learning An Efficient and Robust 3D Medical Image Classification Approach Based on 3D CNN, Time-Distributed 2D CNN-BLSTM Models, and mRMR Feature Selection Modified local Granger causality analysis based on Peter-Clark algorithm for multivariate time series prediction on IoT data A Benchmark Proposal for Non-Generative Fair Adversarial Learning Strategies Using a Fairness-Utility Trade-off Metric
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1