Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Data set entity recognition based on distant supervision

Data set entity recognition based on distant supervision This paper aims to identify data set entities in scientific literature. To address poor recognition caused by a lack of training corpora in existing studies, a distant supervised learning-based approach is proposed to identify data set entities automatically from large-scale scientific literature in an open domain.Design/methodology/approachFirstly, the authors use a dictionary combined with a bootstrapping strategy to create a labelled corpus to apply supervised learning. Secondly, a bidirectional encoder representation from transformers (BERT)-based neural model was applied to identify data set entities in the scientific literature automatically. Finally, two data augmentation techniques, entity replacement and entity masking, were introduced to enhance the model generalisability and improve the recognition of data set entities.FindingsIn the absence of training data, the proposed method can effectively identify data set entities in large-scale scientific papers. The BERT-based vectorised representation and data augmentation techniques enable significant improvements in the generality and robustness of named entity recognition models, especially in long-tailed data set entity recognition.Originality/valueThis paper provides a practical research method for automatically recognising data set entities in scientific literature. To the best of the authors’ knowledge, this is the first attempt to apply distant learning to the study of data set entity recognition. The authors introduce a robust vectorised representation and two data augmentation strategies (entity replacement and entity masking) to address the problem inherent in distant supervised learning methods, which the existing research has mostly ignored. The experimental results demonstrate that our approach effectively improves the recognition of data set entities, especially long-tailed data set entities. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png The Electronic Library Emerald Publishing

Data set entity recognition based on distant supervision

Li, Pengcheng; Liu, Qikai; Cheng, Qikai; Lu, Wei
The Electronic Library , Volume 39 (3): 15 – Nov 4, 2021
Download PDF
15 pages

Loading next page...
 
/lp/emerald-publishing/data-set-entity-recognition-based-on-distant-supervision-J0yz0zHLHQ

References (41)

Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
0264-0473
eISSN
0264-0473
DOI
10.1108/el-10-2020-0301
Publisher site
See Article on Publisher Site

Abstract

This paper aims to identify data set entities in scientific literature. To address poor recognition caused by a lack of training corpora in existing studies, a distant supervised learning-based approach is proposed to identify data set entities automatically from large-scale scientific literature in an open domain.Design/methodology/approachFirstly, the authors use a dictionary combined with a bootstrapping strategy to create a labelled corpus to apply supervised learning. Secondly, a bidirectional encoder representation from transformers (BERT)-based neural model was applied to identify data set entities in the scientific literature automatically. Finally, two data augmentation techniques, entity replacement and entity masking, were introduced to enhance the model generalisability and improve the recognition of data set entities.FindingsIn the absence of training data, the proposed method can effectively identify data set entities in large-scale scientific papers. The BERT-based vectorised representation and data augmentation techniques enable significant improvements in the generality and robustness of named entity recognition models, especially in long-tailed data set entity recognition.Originality/valueThis paper provides a practical research method for automatically recognising data set entities in scientific literature. To the best of the authors’ knowledge, this is the first attempt to apply distant learning to the study of data set entity recognition. The authors introduce a robust vectorised representation and two data augmentation strategies (entity replacement and entity masking) to address the problem inherent in distant supervised learning methods, which the existing research has mostly ignored. The experimental results demonstrate that our approach effectively improves the recognition of data set entities, especially long-tailed data set entities.

Journal

The Electronic Library – Emerald Publishing

Published: Nov 4, 2021

Keywords: Data set entity recognition; Distant supervision; Scientific literature; Data augmentation; Long-tailed entities; Library automation; Distance learning; Database management

There are no references for this article.