A system to extract abbreviation-expansion pairs from biomedical literature
Public Deposited- Last Modified
- February 28, 2019
- Creator
-
Bapat, Amol J.
- Affiliation: School of Information and Library Science
- Abstract
- We present a system to identify abbreviation expansion pairs from scientific articles. We work with the Genomics track of the TREC collection. Authors report abbreviations in two places - an abbreviations section and within the body of a scientific article. Articles with an abbreviations section had fewer abbreviations than those that did not have an abbreviations section (an average of 7.1 versus 13.2 abbreviations per article). For articles that do have an abbreviations section, authors report 98.2% of the abbreviations present in the document in that section. Inspired by Schwartz & Hearst's earlier work our program identified 2.1 million abbreviations from 162,259 documents. A manual inspection of a randomly selected set of articles revealed that our system achieved 86.7% precision and 81.9% recall.
- Date of publication
- April 2009
- Subject
- DOI
- Resource type
- Rights statement
- In Copyright
- Advisor
- Blake, Catherine L.
- Degree granting institution
- University of North Carolina at Chapel Hill
- Language
- Extent
- 38
- Deposit record
- abb1808a-3405-4d7b-866b-f35807dc08b2
- Access right
- Open access
- Date uploaded
- March 6, 2013
Relations
- Parents:
This work has no parents.