IMPROVING BIOMEDICAL NAMED ENTITY RECOGNITION WITH A UNIFIED MULTI-TASK MRC FRAMEWORK

The prior knowledge, such as expert rules and knowledge base, has been proven effective in the traditional Biomedical Named Entity Recognition (BioNER). Most current neural BioNER systems use this external knowledge for pre-processing or post-editing instead of incorporate it into the training process, which cannot be learned by the model. To encode prior knowledge into the model, we present a unified multi-task Machine Reading Comprehension (MRC) framework for BioNER. Specifically, in the MRC task, the question sequences are derived from the standard BioNER dataset. We introduce different prior knowledge at query sequences, including Wikipedia, annotation scheme, entity dictionary. Then, our model adopts a multi-task learning strategy to joint training the main task BioNER and the auxiliary task MRC. Finally, experimental results on three benchmark datasets validate the superiority of our BioNER model compared with various state-of-the-art baselines.