U-CORE:用于开放关系提取的统一深度聚类对比框架

IF 4.2 1区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Jie Zhou, Shenpo Dong, Yunxin Huang, Meihan Wu, Haili Li, Jingnan Wang, Hongkui Tu, Xiaodong Wang
{"title":"U-CORE:用于开放关系提取的统一深度聚类对比框架","authors":"Jie Zhou, Shenpo Dong, Yunxin Huang, Meihan Wu, Haili Li, Jingnan Wang, Hongkui Tu, Xiaodong Wang","doi":"10.1162/tacl_a_00604","DOIUrl":null,"url":null,"abstract":"Abstract Within Open Relation Extraction (ORE) tasks, the Zero-shot ORE method is to generalize undefined relations from predefined relations, while the Unsupervised ORE method is to extract undefined relations without the need for annotations. However, despite the possibility of overlap between predefined and undefined relations in the training data, a unified framework for both Zero-shot and Unsupervised ORE has yet to be established. To address this gap, we propose U-CORE: A Unified Deep Cluster-wise Contrastive Framework for both Zero-shot and Unsupervised ORE, by leveraging techniques from Contrastive Learning (CL) and Clustering.1 U-CORE overcomes the limitations of CL-based Zero-shot ORE methods by employing Cluster-wise CL that preserves both local smoothness as well as global semantics. Additionally, we employ a deep-cluster-based updater that optimizes the cluster center, thus enhancing the accuracy and efficiency of the model. To increase the stability of the model, we adopt Adaptive Self-paced Learning that effectively addresses the data-shifting problems. Experimental results on three well-known datasets demonstrate that U-CORE significantly improves upon existing methods by showing an average improvement of 7.35% ARI on Zero-shot ORE tasks and 15.24% ARI on Unsupervised ORE tasks.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":null,"pages":null},"PeriodicalIF":4.2000,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"U-CORE: A Unified Deep Cluster-wise Contrastive Framework for Open Relation Extraction\",\"authors\":\"Jie Zhou, Shenpo Dong, Yunxin Huang, Meihan Wu, Haili Li, Jingnan Wang, Hongkui Tu, Xiaodong Wang\",\"doi\":\"10.1162/tacl_a_00604\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Within Open Relation Extraction (ORE) tasks, the Zero-shot ORE method is to generalize undefined relations from predefined relations, while the Unsupervised ORE method is to extract undefined relations without the need for annotations. However, despite the possibility of overlap between predefined and undefined relations in the training data, a unified framework for both Zero-shot and Unsupervised ORE has yet to be established. To address this gap, we propose U-CORE: A Unified Deep Cluster-wise Contrastive Framework for both Zero-shot and Unsupervised ORE, by leveraging techniques from Contrastive Learning (CL) and Clustering.1 U-CORE overcomes the limitations of CL-based Zero-shot ORE methods by employing Cluster-wise CL that preserves both local smoothness as well as global semantics. Additionally, we employ a deep-cluster-based updater that optimizes the cluster center, thus enhancing the accuracy and efficiency of the model. To increase the stability of the model, we adopt Adaptive Self-paced Learning that effectively addresses the data-shifting problems. Experimental results on three well-known datasets demonstrate that U-CORE significantly improves upon existing methods by showing an average improvement of 7.35% ARI on Zero-shot ORE tasks and 15.24% ARI on Unsupervised ORE tasks.\",\"PeriodicalId\":33559,\"journal\":{\"name\":\"Transactions of the Association for Computational Linguistics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2023-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Transactions of the Association for Computational Linguistics\",\"FirstCategoryId\":\"98\",\"ListUrlMain\":\"https://doi.org/10.1162/tacl_a_00604\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transactions of the Association for Computational Linguistics","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1162/tacl_a_00604","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

摘要 在开放关系抽取(ORE)任务中,零点抽取(Zero-shot ORE)方法是从预定义关系中归纳出未定义关系,而无监督抽取(Unsupervised ORE)方法则是在不需要注释的情况下抽取未定义关系。然而,尽管训练数据中的预定义关系和未定义关系之间可能存在重叠,但目前还没有为 "零点 "和 "无监督 "ORE 建立统一的框架。为了填补这一空白,我们提出了 U-CORE:U-CORE 克服了基于对比学习(Contrastive Learning,CL)的零拍摄 ORE 方法的局限性,采用了既能保持局部平滑性又能保持全局语义的集群对比学习(Cluster-wise CL)。此外,我们还采用了基于深度簇的更新器,优化了簇中心,从而提高了模型的准确性和效率。为了提高模型的稳定性,我们采用了自适应自步调学习(Adaptive Self-paced Learning)技术,有效地解决了数据转移问题。在三个知名数据集上的实验结果表明,U-CORE 显著提高了现有方法的性能,在 "Zero-shot ORE "任务中平均提高了 7.35% 的 ARI,在 "Unsupervised ORE "任务中平均提高了 15.24% 的 ARI。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
U-CORE: A Unified Deep Cluster-wise Contrastive Framework for Open Relation Extraction
Abstract Within Open Relation Extraction (ORE) tasks, the Zero-shot ORE method is to generalize undefined relations from predefined relations, while the Unsupervised ORE method is to extract undefined relations without the need for annotations. However, despite the possibility of overlap between predefined and undefined relations in the training data, a unified framework for both Zero-shot and Unsupervised ORE has yet to be established. To address this gap, we propose U-CORE: A Unified Deep Cluster-wise Contrastive Framework for both Zero-shot and Unsupervised ORE, by leveraging techniques from Contrastive Learning (CL) and Clustering.1 U-CORE overcomes the limitations of CL-based Zero-shot ORE methods by employing Cluster-wise CL that preserves both local smoothness as well as global semantics. Additionally, we employ a deep-cluster-based updater that optimizes the cluster center, thus enhancing the accuracy and efficiency of the model. To increase the stability of the model, we adopt Adaptive Self-paced Learning that effectively addresses the data-shifting problems. Experimental results on three well-known datasets demonstrate that U-CORE significantly improves upon existing methods by showing an average improvement of 7.35% ARI on Zero-shot ORE tasks and 15.24% ARI on Unsupervised ORE tasks.
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
CiteScore
32.60
自引率
4.60%
发文量
58
审稿时长
8 weeks
期刊介绍: The highly regarded quarterly journal Computational Linguistics has a companion journal called Transactions of the Association for Computational Linguistics. This open access journal publishes articles in all areas of natural language processing and is an important resource for academic and industry computational linguists, natural language processing experts, artificial intelligence and machine learning investigators, cognitive scientists, speech specialists, as well as linguists and philosophers. The journal disseminates work of vital relevance to these professionals on an annual basis.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信