Xuan Wang1, Yu Zhang1, Xiang Ren2, Yuhao Zhang3, Marinka Zitnik4, Jingbo Shang1, Curtis Langlotz3, Jiawei Han1. 1. Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA. 2. Department of Computer Science, University of Southern California, Los Angeles, CA, USA. 3. Department of Radiology, School of Medicine, Stanford University, Stanford, CA, USA. 4. Department of Computer Science, Stanford University, Stanford, CA, USA.
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. AVAILABILITY AND IMPLEMENTATION: Our source code is available at https://github.com/yuzhimanhua/lm-lstm-crf. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
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. AVAILABILITY AND IMPLEMENTATION: Our source code is available at https://github.com/yuzhimanhua/lm-lstm-crf. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Authors: Camilo Espinosa; Martin Becker; Ivana Marić; Ronald J Wong; Gary M Shaw; Brice Gaudilliere; Nima Aghaeepour; David K Stevenson Journal: Trends Mol Med Date: 2021-02-08 Impact factor: 15.272