Convolutional neural networks for chemical-disease relation extraction are improved with character-based word embeddings
This work improves relation extraction for biomedical text, but it is incremental as it builds on existing neural methods.
The authors tackled chemical-disease relation extraction by incorporating character-based word embeddings into CNN models, achieving state-of-the-art results on the BioCreative-V CDR corpus.
We investigate the incorporation of character-based word representations into a standard CNN-based relation extraction model. We experiment with two common neural architectures, CNN and LSTM, to learn word vector representations from character embeddings. Through a task on the BioCreative-V CDR corpus, extracting relationships between chemicals and diseases, we show that models exploiting the character-based word representations improve on models that do not use this information, obtaining state-of-the-art result relative to previous neural approaches.