LSTM-Based End-to-End Framework for Biomedical Event Extraction

Biomedical event extraction plays an important role in the extraction of biological information from large-scale scientific publications. However, most state-of-the-art systems separate this task into several steps, which leads to cascading errors. In addition, it is complicated to generate features from syntactic and dependency analysis separately. Therefore, in this paper, we propose an end-to-end model based on long short-term memory (LSTM) to optimize biomedical event extraction. Experimental results demonstrate that our approach improves the performance of biomedical event extraction. We achieve average F1-scores of 59.68, 58.23, and 57.39 percent on the BioNLP09, BioNLP11, and BioNLP13's Genia event datasets, respectively. The experimental study has shown our proposed model's potential in biomedical event extraction.

1 Introduction

For several years, biology and information communities have been working towards the goal of extracting complex information from large volumes of biological publications, especially information related to the behavior of bio-molecules containing event information in a structured form [1]. The structured descriptions of biomedical events consisting of “event category,” “trigger,” and “argument” [2]. Fig. 1 presents a typical instance describing the phosphorylation and negative regulation behaviors between proteins “TRAF2” and “CD40.” The trigger for the phosphorylation event is “phosphorylation” and the argument is “TRAF2.” The word “inhibits” indicates that a negative regulation event is also included. These two events can be annotated as follows: 1) Event1: Phosphorylation, Trigger: phosphorylation, Theme1: TRF2; 2) Event2: Negative Regulation, Trigger: inhibits, Theme1: CD40, Cause1: Event1.