Joint Learning for Document-Level Threat Intelligence Relation Extraction and Coreference Resolution Based on GCN
Authors:
- 1 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 584-591
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%.Keywords
Funding Information
- National Key Research and Development Program of China (2019QY1302,2016YFB0801004)
This publication has 14 references indexed in Scilit:
- Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction2018
- Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extraction2018
- Position-aware Attention and Supervised Data Improve Slot Filling2017
- CyberTwitter: Using Twitter to generate alerts for cybersecurity threats and vulnerabilities2016
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures2016
- Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification2016
- Towards a Relation Extraction Framework for Cyber-Security Concepts2015
- Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths2015
- The Stanford CoreNLP Natural Language Processing Toolkit2014
- Glove: Global Vectors for Word Representation2014