Relation Extraction From Biomedical and Clinical Text: Unified Multitask Learning Framework
- 27 August 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 19 (2) , 1105-1116
Abstract
To minimize the accelerating amount of time invested on the biomedical literature search, numerous approaches for automated knowledge extraction have been proposed. Relation extraction is one such task where semantic relations between the entities are identified from the free text. In the biomedical domain, extraction of regulatory pathways, metabolic processes, adverse drug reaction or disease models necessitates knowledge from the individual relations, for example, physical or regulatory interactions between proteins, drugs, disease or phenotype. We study the relation extraction from three major biomedical and clinical tasks, namely drug-drug interactions, protein-protein interaction, and medical concept relation extraction. Towards this, we model the relation extraction problem in a multi-task learning (MTL) framework, and introduce for the first time the concept of structured self-attentive network complemented with the adversarial learning approach in the prediction of relationships from the biomedical and clinical text. Additionally, we also generate the highly efficient single task model which exploits the shortest dependency path embedding learned over the attentive gated recurrent unit to compare our proposed MTL models. The framework we propose significantly improves over all the baselines (deep learning techniques) and single-task models for predicting the relationships, without compromising on the performance of all the tasks.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- Enhancing clinical concept extraction with distributional semanticsJournal of Biomedical Informatics, 2012
- Automatic extraction of relations between medical concepts in clinical textsJournal of the American Medical Informatics Association, 2011
- Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010Journal of the American Medical Informatics Association, 2011
- 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical textJournal of the American Medical Informatics Association, 2011
- PubMed and beyond: a survey of web tools for searching biomedical literatureDatabase: The Journal of Biological Databases and Curation, 2011
- Walk-weighted subsequence kernels for protein-protein interaction extractionBMC Bioinformatics, 2010
- Evaluating contributions of natural language parsers to protein–protein interaction extractionBioinformatics, 2008
- All-paths graph kernel for protein-protein interaction extraction with evaluation of cross-corpus learningBMC Bioinformatics, 2008
- Extraction of semantic biomedical relations from text using conditional random fieldsBMC Bioinformatics, 2008
- Comparative analysis of five protein-protein interaction corporaBMC Bioinformatics, 2008