Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning

TL;DR

This paper introduces a multi-task learning framework for biomedical named entity recognition that leverages data across multiple entity types to improve overall performance, reducing reliance on handcrafted features and enhancing accuracy.

Contribution

The paper presents a novel multi-task learning approach that effectively combines training data from different biomedical entity types to boost NER performance.

Findings

Significantly outperforms state-of-the-art BioNER systems.

Sharing character- and word-level information improves recognition accuracy.

Achieves better results across 15 benchmark datasets.

Abstract

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.