Neural Multi-Task Learning for Adverse Drug Reaction Extraction. Liu, F., Zheng, X., Yu, H., & Tjia, J. AMIA ... Annual Symposium proceedings. AMIA Symposium, 2020:756–762, 2020.
![Neural Multi-Task Learning for Adverse Drug Reaction Extraction [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex
Paper abstract bibtex A reliable and searchable knowledge database of adverse drug reactions (ADRs) is highly important and valuable for improving patient safety at the point of care. In this paper, we proposed a neural multi-task learning system, NeuroADR, to extract ADRs as well as relevant modifiers from free-text drug labels. Specifically, the NeuroADR system exploited a hierarchical multi-task learning (HMTL) framework to perform named entity recognition (NER) and relation extraction (RE) jointly, where interactions among the learned deep encoder representations from different subtasks are explored. Different from the conventional HMTL approach, NeuroADR adopted a novel task decomposition strategy to generate auxiliary subtasks for more inter-task interactions and integrated a new label encoding schema for better handling discontinuous entities. Experimental results demonstrate the effectiveness of the proposed system.
@article{liu_neural_2020,
title = {Neural {Multi}-{Task} {Learning} for {Adverse} {Drug} {Reaction} {Extraction}},
volume = {2020},
issn = {1942-597X},
url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8075418/pdf/110_3417286.pdf},
abstract = {A reliable and searchable knowledge database of adverse drug reactions (ADRs) is highly important and valuable for improving patient safety at the point of care. In this paper, we proposed a neural multi-task learning system, NeuroADR, to extract ADRs as well as relevant modifiers from free-text drug labels. Specifically, the NeuroADR system exploited a hierarchical multi-task learning (HMTL) framework to perform named entity recognition (NER) and relation extraction (RE) jointly, where interactions among the learned deep encoder representations from different subtasks are explored. Different from the conventional HMTL approach, NeuroADR adopted a novel task decomposition strategy to generate auxiliary subtasks for more inter-task interactions and integrated a new label encoding schema for better handling discontinuous entities. Experimental results demonstrate the effectiveness of the proposed system.},
language = {eng},
journal = {AMIA ... Annual Symposium proceedings. AMIA Symposium},
author = {Liu, Feifan and Zheng, Xiaoyu and Yu, Hong and Tjia, Jennifer},
year = {2020},
pmid = {33936450},
pmcid = {PMC8075418},
keywords = {Data Mining, Databases, Factual, Deep Learning, Drug-Related Side Effects and Adverse Reactions, Humans, Machine Learning},
pages = {756--762},
}Downloads: 0
{"_id":"HZ38fgZcoB4n7pX3s","bibbaseid":"liu-zheng-yu-tjia-neuralmultitasklearningforadversedrugreactionextraction-2020","author_short":["Liu, F.","Zheng, X.","Yu, H.","Tjia, J."],"bibdata":{"bibtype":"article","type":"article","title":"Neural Multi-Task Learning for Adverse Drug Reaction Extraction","volume":"2020","issn":"1942-597X","url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8075418/pdf/110_3417286.pdf","abstract":"A reliable and searchable knowledge database of adverse drug reactions (ADRs) is highly important and valuable for improving patient safety at the point of care. In this paper, we proposed a neural multi-task learning system, NeuroADR, to extract ADRs as well as relevant modifiers from free-text drug labels. Specifically, the NeuroADR system exploited a hierarchical multi-task learning (HMTL) framework to perform named entity recognition (NER) and relation extraction (RE) jointly, where interactions among the learned deep encoder representations from different subtasks are explored. Different from the conventional HMTL approach, NeuroADR adopted a novel task decomposition strategy to generate auxiliary subtasks for more inter-task interactions and integrated a new label encoding schema for better handling discontinuous entities. Experimental results demonstrate the effectiveness of the proposed system.","language":"eng","journal":"AMIA ... Annual Symposium proceedings. AMIA Symposium","author":[{"propositions":[],"lastnames":["Liu"],"firstnames":["Feifan"],"suffixes":[]},{"propositions":[],"lastnames":["Zheng"],"firstnames":["Xiaoyu"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]},{"propositions":[],"lastnames":["Tjia"],"firstnames":["Jennifer"],"suffixes":[]}],"year":"2020","pmid":"33936450","pmcid":"PMC8075418","keywords":"Data Mining, Databases, Factual, Deep Learning, Drug-Related Side Effects and Adverse Reactions, Humans, Machine Learning","pages":"756–762","bibtex":"@article{liu_neural_2020,\n\ttitle = {Neural {Multi}-{Task} {Learning} for {Adverse} {Drug} {Reaction} {Extraction}},\n\tvolume = {2020},\n\tissn = {1942-597X},\n\turl = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8075418/pdf/110_3417286.pdf},\n\tabstract = {A reliable and searchable knowledge database of adverse drug reactions (ADRs) is highly important and valuable for improving patient safety at the point of care. In this paper, we proposed a neural multi-task learning system, NeuroADR, to extract ADRs as well as relevant modifiers from free-text drug labels. Specifically, the NeuroADR system exploited a hierarchical multi-task learning (HMTL) framework to perform named entity recognition (NER) and relation extraction (RE) jointly, where interactions among the learned deep encoder representations from different subtasks are explored. Different from the conventional HMTL approach, NeuroADR adopted a novel task decomposition strategy to generate auxiliary subtasks for more inter-task interactions and integrated a new label encoding schema for better handling discontinuous entities. Experimental results demonstrate the effectiveness of the proposed system.},\n\tlanguage = {eng},\n\tjournal = {AMIA ... Annual Symposium proceedings. AMIA Symposium},\n\tauthor = {Liu, Feifan and Zheng, Xiaoyu and Yu, Hong and Tjia, Jennifer},\n\tyear = {2020},\n\tpmid = {33936450},\n\tpmcid = {PMC8075418},\n\tkeywords = {Data Mining, Databases, Factual, Deep Learning, Drug-Related Side Effects and Adverse Reactions, Humans, Machine Learning},\n\tpages = {756--762},\n}\n\n","author_short":["Liu, F.","Zheng, X.","Yu, H.","Tjia, J."],"key":"liu_neural_2020","id":"liu_neural_2020","bibbaseid":"liu-zheng-yu-tjia-neuralmultitasklearningforadversedrugreactionextraction-2020","role":"author","urls":{"Paper":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8075418/pdf/110_3417286.pdf"},"keyword":["Data Mining","Databases","Factual","Deep Learning","Drug-Related Side Effects and Adverse Reactions","Humans","Machine Learning"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"http://fenway.cs.uml.edu/papers/pubs-all.bib","dataSources":["TqaA9miSB65nRfS5H"],"keywords":["data mining","databases","factual","deep learning","drug-related side effects and adverse reactions","humans","machine learning"],"search_terms":["neural","multi","task","learning","adverse","drug","reaction","extraction","liu","zheng","yu","tjia"],"title":"Neural Multi-Task Learning for Adverse Drug Reaction Extraction","year":2020}