Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning
This addresses the need for more efficient BioNER systems in biomedical research by reducing reliance on handcrafted features and improving accuracy across multiple entity types.
The paper tackles the problem of limited training data for biomedical named entity recognition (BioNER) by proposing a multi-task learning framework that uses data across different entity types, achieving substantially better performance on 15 benchmark datasets compared to state-of-the-art systems.
Motivation: State-of-the-art biomedical named entity recognition (BioNER) systems often require handcrafted features specific to each entity type, such as genes, chemicals and diseases. Although recent studies explored using neural network models for BioNER to free experts from manual feature engineering, the performance remains limited by the available training data for each entity type. Results: We propose a multi-task learning framework for BioNER to collectively use the training data of different types of entities and improve the performance on each of them. In experiments on 15 benchmark BioNER datasets, our multi-task model achieves substantially better performance compared with state-of-the-art BioNER systems and baseline neural sequence labeling models. Further analysis shows that the large performance gains come from sharing character- and word-level information among relevant biomedical entities across differently labeled corpora.