A Hybrid Neural Network Model with Entity-related Knowledge for Adverse Drug Reaction Detection

As an important research topic in biomedical field, adverse drug reaction detection has received extensive research attention in the past ten years. Recent studies begin to design various neural frameworks with external knowledge to improve the task performance. However, these efforts mainly focus on extracting contextual information or knowledge according to the whole input text, which may introduce a lot of redundant information. In this paper, we propose a hybrid neural network model, which automatically integrates entity-related keywords from external knowledge base, for predicting adverse drug reaction. Experimental results on the publicly available dataset show our proposed model can achieve 93.71% and 88.07% F1 score on entity recognition and relationship extraction, respectively, outperforming the existing methods and strong neural baselines by a large margin.