Book chapter
Automatic Extraction for Creating a Lexical Repository of Abbreviations in the Biomedical Literature
Data Warehousing and Knowledge Discovery, pp 384-393
2006
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
The sheer volume of biomedical text is growing at an exponential rate. This growth creates challenges for both human readers and automatic text processing algorithms. One such challenge arises from common and uncontrolled usages of abbreviations in the biomedical literature. This, in turn, requires that biomedical lexical ontologies be continuously updated. In this paper, we propose a hybrid approach combining lexical analysis techniques and the Support Vector Machine (SVM) to create an automatically generated and maintained lexicon of abbreviations. The proposed technique is differentiated from others in the following aspects: 1) It incorporates lexical analysis techniques to supervised learning for extracting abbreviations. 2) It makes use of text chunking techniques to identify long forms of abbreviations. 3) It significantly improves Recall compared to other techniques. The experimental results show that our approach outperforms the leading abbreviation algorithms, ExtractAbbrev and ALICE, at least by 6% and 13.9%, respectively, in both Precision and Recall on the Gold Standard Development corpus.
Metrics
Details
- Title
- Automatic Extraction for Creating a Lexical Repository of Abbreviations in the Biomedical Literature
- Creators
- Min Song - New Jersey Institute of TechnologyIl-Yeol Song - Drexel UniversityKi Jung Lee - Drexel University
- Publication Details
- Data Warehousing and Knowledge Discovery, pp 384-393
- Series
- Lecture Notes in Computer Science
- Publisher
- Springer Berlin Heidelberg; Berlin, Heidelberg
- Resource Type
- Book chapter
- Language
- English
- Academic Unit
- Information Science (Informatics)
- Web of Science ID
- WOS:000241158200037
- Scopus ID
- 2-s2.0-33751383258
- Other Identifier
- 991019170402204721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Theory & Methods