A Neural Relation Extraction Model for Distant Supervision in Counter-Terrorism Scenario

Abstract

Natural language processing (NLP) is the best solution to extensive, unstructured, complex, and diverse network big data for counter-terrorism. Through the text analysis, it is the basis and the most critical step to quickly extract the relationship between the relevant entities pairs in terrorism. Relation extraction lays a foundation for constructing a knowledge graph (KG) of terrorism and provides technical support for intelligence analysis and prediction. This paper takes the distant-supervised relation extraction as the starting point, breaks the limitation of artificial data annotation. Combining the Bidirectional Encoder Representation from Transformers (BERT) pre-training model and the sentence-level attention over multiple instances, we proposed the relation extraction model named BERT-att. Experiments show that our model is more efficient and better than the current leading baseline model over each evaluative metrics. Our model applied to the construction of anti-terrorism knowledge map, it used in regional security risk assessment, terrorist event prediction and other scenarios.