Joint Learning for Document-Level Threat Intelligence Relation Extraction and Coreference Resolution Based on GCN

Xuren Wang, Mengbo Xiong, Yali Luo, Ning Li, Zhengwei Jiang, Zihan Xiong
{"title":"Joint Learning for Document-Level Threat Intelligence Relation Extraction and Coreference Resolution Based on GCN","authors":"Xuren Wang, Mengbo Xiong, Yali Luo, Ning Li, Zhengwei Jiang, Zihan Xiong","doi":"10.1109/TrustCom50675.2020.00083","DOIUrl":null,"url":null,"abstract":"In order to help researchers quickly understand the connection between new threat events and previous threat events, threat intelligence document-level relation extraction plays a very important role in threat intelligence text analysis and processing. Because there is no public document-level threat intelligence dataset, we create APTERC-DOC, an APT intelligence entities, relations and coreference dataset. We treat the relation extraction as a multi-classification task. Treating the coreference relation as a kind of predefined relations, we develop a joint learning framework called TIRECO, a model which can simultaneously complete threat intelligence relation extraction and coreference resolution. In order to solve the problem of document-level text being too long to extract feature, we propose the concept of sentence set, which transforms document-level relation extraction into inter-sentence relation extraction. To incorporate relevant information with maximally removing irrelevant content in sentence set, we further apply a novel pruning strategy (SDP-VP-SET) to the input trees considering that verbs are crucial in determining the relation between entities in sentence set. With retaining the shortest path and nodes that are K hops away from the shortest path, we give the edge connected to the verb nodes a weight of w times. Experimental results show that our model not only performs well in the extraction of inter-sentence relations, it is also effective in intra-sentence relations, and the F1 value has increased by 15.694%.","PeriodicalId":221956,"journal":{"name":"2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TrustCom50675.2020.00083","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

In order to help researchers quickly understand the connection between new threat events and previous threat events, threat intelligence document-level relation extraction plays a very important role in threat intelligence text analysis and processing. Because there is no public document-level threat intelligence dataset, we create APTERC-DOC, an APT intelligence entities, relations and coreference dataset. We treat the relation extraction as a multi-classification task. Treating the coreference relation as a kind of predefined relations, we develop a joint learning framework called TIRECO, a model which can simultaneously complete threat intelligence relation extraction and coreference resolution. In order to solve the problem of document-level text being too long to extract feature, we propose the concept of sentence set, which transforms document-level relation extraction into inter-sentence relation extraction. To incorporate relevant information with maximally removing irrelevant content in sentence set, we further apply a novel pruning strategy (SDP-VP-SET) to the input trees considering that verbs are crucial in determining the relation between entities in sentence set. With retaining the shortest path and nodes that are K hops away from the shortest path, we give the edge connected to the verb nodes a weight of w times. Experimental results show that our model not only performs well in the extraction of inter-sentence relations, it is also effective in intra-sentence relations, and the F1 value has increased by 15.694%.
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
基于GCN的联合学习文档级威胁情报关系提取与关联解析
为了帮助研究人员快速了解新的威胁事件和以前的威胁事件之间的联系,威胁情报文档级关系提取在威胁情报文本分析和处理中起着非常重要的作用。由于没有公开的文档级威胁情报数据集,我们创建了APTERC-DOC,一个APT情报实体、关系和共同参考数据集。我们把关系抽取看作是一个多分类的任务。将共参考关系视为一种预定义关系,开发了TIRECO联合学习框架,该模型可以同时完成威胁情报关系提取和共参考解决。为了解决文档级文本太长而无法提取特征的问题,我们提出了句子集的概念,将文档级关系提取转化为句子间关系提取。考虑到动词在决定句子集中实体之间的关系中起着至关重要的作用,我们进一步对输入树应用了一种新的剪枝策略(SDP-VP-SET),以在最大程度上去除句子集中不相关的内容的同时整合相关信息。在保留最短路径和距离最短路径K跳的节点的情况下,我们给连接到动词节点的边赋予w次权值。实验结果表明,我们的模型不仅在句间关系提取方面表现良好,在句内关系提取方面也很有效,F1值提高了15.694%。
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
自引率
0.00%
发文量
0
期刊最新文献
Research on Stitching and Alignment of Mouse Carcass EM Images One Covert Channel to Rule Them All: A Practical Approach to Data Exfiltration in the Cloud MAUSPAD: Mouse-based Authentication Using Segmentation-based, Progress-Adjusted DTW Finding Geometric Medians with Location Privacy Multi-Input Functional Encryption: Efficient Applications from Symmetric Primitives
×
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