Effectively Modeling Sentence Interactions With Factorization Machines for Fact Verification

IF 5.6 3区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE IEEE Intelligent Systems Pub Date : 2023-09-01 DOI:10.1109/MIS.2023.3301170
Zhen-Heng Chen, Fuzhen Zhuang, Lejian Liao, Meihuizi Jia, Jiaqi Li, Heyan Huang
{"title":"Effectively Modeling Sentence Interactions With Factorization Machines for Fact Verification","authors":"Zhen-Heng Chen, Fuzhen Zhuang, Lejian Liao, Meihuizi Jia, Jiaqi Li, Heyan Huang","doi":"10.1109/MIS.2023.3301170","DOIUrl":null,"url":null,"abstract":"Fact verification is a very challenging task that requires retrieving multiple evidence sentences from a reliable corpus to authenticate claims. Many claims require the simultaneous integration and reasoning of several pieces of evidence for verification. Existing models exhibit limitations in two aspects: 1) during the sentence selection stage, they only consider the interaction between the claim and the evidence, disregarding the intersentence information, and 2) most fusion strategies employed in current research, such as addition, concatenation, or simple neural networks, fail to capture the relationships and logical information among the evidence. To alleviate these problems, we propose select and fact verification modeling (SFVM). Our model utilizes a multihead self-attention mechanism combined with a gating mechanism to facilitate sentence interaction and enhance sentence embeddings. Then, we utilize factorization machines to effectively express the compressed alignment vectors, which are then used to expand the representations of the base evidence. To distinguish the importance of features, we use the evidence fusion network to determine the importance of various feature interactions. Results from experiments on the two public datasets showed that SFVM can utilize richer information between the claim and the evidence for fact verification and achieve competitive performance on the FEVER dataset.","PeriodicalId":13160,"journal":{"name":"IEEE Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":5.6000,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Intelligent Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/MIS.2023.3301170","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Fact verification is a very challenging task that requires retrieving multiple evidence sentences from a reliable corpus to authenticate claims. Many claims require the simultaneous integration and reasoning of several pieces of evidence for verification. Existing models exhibit limitations in two aspects: 1) during the sentence selection stage, they only consider the interaction between the claim and the evidence, disregarding the intersentence information, and 2) most fusion strategies employed in current research, such as addition, concatenation, or simple neural networks, fail to capture the relationships and logical information among the evidence. To alleviate these problems, we propose select and fact verification modeling (SFVM). Our model utilizes a multihead self-attention mechanism combined with a gating mechanism to facilitate sentence interaction and enhance sentence embeddings. Then, we utilize factorization machines to effectively express the compressed alignment vectors, which are then used to expand the representations of the base evidence. To distinguish the importance of features, we use the evidence fusion network to determine the importance of various feature interactions. Results from experiments on the two public datasets showed that SFVM can utilize richer information between the claim and the evidence for fact verification and achieve competitive performance on the FEVER dataset.
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
利用因子分解机对句子交互进行有效建模以进行事实验证
事实验证是一项非常具有挑战性的任务,需要从可靠的语料库中检索多个证据句子来验证索赔。许多主张需要同时整合和推理若干证据来验证。现有模型存在两个方面的局限性:1)在句子选择阶段,它们只考虑主张与证据之间的相互作用,而忽略了句子间的信息;2)目前研究中采用的大多数融合策略,如加法、串联或简单的神经网络,未能捕捉证据之间的关系和逻辑信息。为了解决这些问题,我们提出了选择和事实验证建模(SFVM)。我们的模型利用多头自注意机制结合门控机制来促进句子交互和增强句子嵌入。然后,我们利用因式分解机有效地表示压缩的对齐向量,然后将其用于扩展基本证据的表示。为了区分特征的重要性,我们使用证据融合网络来确定各种特征交互的重要性。在两个公共数据集上的实验结果表明,SFVM可以利用更丰富的声明和证据之间的信息进行事实验证,并在FEVER数据集上取得具有竞争力的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
IEEE Intelligent Systems
IEEE Intelligent Systems 工程技术-工程:电子与电气
CiteScore
13.80
自引率
3.10%
发文量
122
审稿时长
1 months
期刊介绍: IEEE Intelligent Systems serves users, managers, developers, researchers, and purchasers who are interested in intelligent systems and artificial intelligence, with particular emphasis on applications. Typically they are degreed professionals, with backgrounds in engineering, hard science, or business. The publication emphasizes current practice and experience, together with promising new ideas that are likely to be used in the near future. Sample topic areas for feature articles include knowledge-based systems, intelligent software agents, natural-language processing, technologies for knowledge management, machine learning, data mining, adaptive and intelligent robotics, knowledge-intensive processing on the Web, and social issues relevant to intelligent systems. Also encouraged are application features, covering practice at one or more companies or laboratories; full-length product stories (which require refereeing by at least three reviewers); tutorials; surveys; and case studies. Often issues are theme-based and collect articles around a contemporary topic under the auspices of a Guest Editor working with the EIC.
期刊最新文献
FL4SDN: A Fast-Convergent Federated Learning for Distributed and Heterogeneous SDN Large-scale Package Deliveries with Unmanned Aerial Vehicles using Collective Learning AdaCLF: An Adaptive Curriculum Learning Framework for Emotional Support Conversation IEEE CS Call for Papers IEEE Annals of the History of Computing
×
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