A transition-based model for jointly extracting drugs, diseases and adverse drug events

Extracting adverse drug events (a.k.a. drug-induced diseases or drug side effects) from the raw text has been widely studied in the biomedical area. It is usually assumed that entities of drugs and diseases are given by a separated named entity recognition model. In this paper, we propose a joint model to extract drugs, diseases and adverse drug events simultaneously. In our model, the structured perceptron is leveraged for training and multiple-beam search algorithm is used for decoding. The search algorithm is transition-based, i.e., an input sentence is processed in left-to-right order and predefined actions transit the sentence from one state to another which corresponds to a predicted result about drugs, diseases and adverse drug events in that sentence. Experimental results show that our joint approach obtains comparable performance compared with the baseline or state-of-the-art approaches and achieves 55.20% precision, 47.97% recall and 51.14% F₁-measure in extraction of adverse drug events. We demonstrate that the joint approach is effective and can be easily extended to other entity-relation extraction systems such as protein-protein interactions and gene-disease relations. To facilitate the related research, our code is available online at: https://github.com/foxlf823/ade.