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

• Main Authors: Wang, Xuren, Xiong, Mengbo, Luo, Yali, Li, Ning, Jiang, Zhengwei, Xiong, Zihan
• Format: Conference Proceeding
• Language: English
• Subjects: APT intelligence entities; APTERC-DOC; Conferences; coreference dataset; coreference relation; coreference resolution; document-level text; document-level threat intelligence relation extraction; feature extraction; GCN; inter-sentence relation extraction; inter-sentence relations; intra-sentence relations; joint learning framework; learning (artificial intelligence); natural language processing; pattern classification; predefined relations; previous threat events; Privacy; public document-level threat intelligence dataset; relation extraction; SDP-VP-SET; Security; sentence set; Task analysis; text analysis; threat intelligence; threat intelligence document-level relation extraction; threat intelligence text analysis; Transforms; trees (mathematics)
• ISSN: 2324-9013
• DOI: 10.1109/TrustCom50675.2020.00083

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%.