Clinical information extraction using word representations

Malmasi, Shervin, Hassanzadeh, Hamed and Dras, Mark (2015). Clinical information extraction using word representations. In: Ben Hachey and Kellie Webster, Australasian Language Technology Association Workshop 2015: Proceedings of the Workshop. Australasian Language Technology Association Workshop, Parramatta, NSW, Australia, (66-74). 8-9 December 2015.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
Author Malmasi, Shervin
Hassanzadeh, Hamed
Dras, Mark
Title of paper Clinical information extraction using word representations
Conference name Australasian Language Technology Association Workshop
Conference location Parramatta, NSW, Australia
Conference dates 8-9 December 2015
Proceedings title Australasian Language Technology Association Workshop 2015: Proceedings of the Workshop
Publisher ALTA
Publication Year 2015
Sub-type Fully published paper
ISSN 1834-7037
Editor Ben Hachey
Kellie Webster
Volume 13
Start page 66
End page 74
Total pages 9
Collection year 2016
Language eng
Formatted Abstract/Summary
A central task in clinical information extraction is the classification of sentences to identify key information in publications, such as intervention and outcomes. Surface tokens and part-of-speech tags have been the most commonly used feature types for this task. In this paper we evaluate the use of word representations, induced from approximately 100m tokens of unlabelled in domain data, as a form of semi-supervised learning for this task. We take an approach based on unsupervised word clusters, using the Brown clustering algorithm, with results showing that this method outperforms the standard features. We inspect the induced word representations and the resulting discriminative model features to gain further insights about this approach.
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ
Additional Notes http://www.alta.asn.au/events/alta2015/proceedings/

 
Versions
Version Filter Type
Citation counts: Google Scholar Search Google Scholar
Created: Fri, 11 Mar 2016, 15:13:32 EST by Anthony Yeates on behalf of School of Communication and Arts