Using word embedding for bio-event extraction

Abstract

Bio-event extraction is an important phase towards the goal of extracting biological networks from the scientific literature. Recent advances in word embedding make computation of word distribution more efficient and possible. In this study, we investigate methods bringing distributional characteristics of words in the text into event extraction by using the latest word embedding methods. By using bag-of-words (BOW) features as the baseline, the result has been improved by the introduction of word-embedding features, and is comparable to the state-of-the-art solution.