For the current REF see the REF 2021 website REF 2021 logo

Output details

11 - Computer Science and Informatics

University of Sheffield

Return to search Previous output Next output
Output 0 of 0 in the submission
Article title

Exploiting domain information for Word Sense Disambiguation of medical documents

Type
D - Journal article
Title of journal
Journal of the American Medical Informatics Association
Article number
-
Volume number
19
Issue number
2
First page of article
235
ISSN of journal
1527974X
Year of publication
2011
URL
-
Number of additional authors
2
Additional information

<22>Knowledge about the topic (domain) of a document provides important information to support its interpretation. This paper describes a novel technique for applying domain information in word sense disambiguation systems using topic models. This approach results in significantly improved performance. The research was funded by an EPSRC project (BioWSD) and led to a follow-on EPSRC grant for Stevenson in collaboration with Sheffield’s Medical School (KDisc). The work was an international collaboration with researchers at University of the Basque Country, which continues in an EU project co-ordinated by Stevenson (PATHS). JAMIA (IF:3.571) is the third highest ranked journal in medical informatics.

Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
0
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-