Character-Level Embedding using FastText and LSTM for Biomedical Named Entity Recognition

Abstract

Extracting biomedical entities has caught many researchers’ attention in which the recent technique of word embedding is employed for such a task. Yet, the traditional word embedding architectures of Word2vec or Glove are still suffering from the ‘out-of-vocabulary’ (OOV) problem. This problem occurs when an unseen term might be encountered during the testing which leads to absence of embedding vector. Hence, this study aims to propose a character-level embedding through FastText architecture. In fact, handling the character-level seems a promising solution for the OOV problem. To this end, the proposed FastText architecture has been used to generate embedding vectors for the possible N-gram combinations of each word. Consequentially, these vectors have been fed to a Long Short Term Memory (LSTM) architecture for classifying the words into its biomedical classes. Using two benchmark datasets of BioCreative-II and NCBI, the proposed method was able to produce an f-measure of 0.912 and 0.918 respectively. Comparing these results with the baseline studies demonstrates the superiority of the proposed character-level embedding of FastText in terms of Biomedical Named Entity Recognition (BNER) task.