Loading...
Loading...

Go to the content (press return)

Semi-supervised learning for disabilities detection on English and Spanish biomedical text

Author
Medina, S.; Turmo, J.; Loharja, H.; Padro, L.
Type of activity
Presentation of work at congresses
Name of edition
Third Workshop on Evaluation of Human Language Technologies for Iberian Languages
Date of publication
2018
Presentation's date
2018-09-18
Book of congress proceedings
CEUR Workshop Proceedings
First page
66
Last page
73
Repository
http://hdl.handle.net/2117/124272 Open in new window
URL
http://ceur-ws.org/Vol-2150/DIANN_paper8.pdf Open in new window
Abstract
This paper describes the disability detection model approaches presented by UPC’s TALP 3 team for the DIANN 2018 shared task. The best of those approaches was ranked in 3rd place for exact-matching of disability detection. The models combine a semi-supervised learning model using CRFs and LSTM with word embedding features with a supervised CRF model for the detection of disabilities and negations respectively. This paper describes the disability detection model approaches presented by UPC’s ...
Citation
Medina, S., Turmo, J., Loharja, H., Padro, L. Semi-supervised learning for disabilities detection on English and Spanish biomedical text. A: Workshop on Evaluation of Human Language Technologies for Iberian Languages. "CEUR Workshop Proceedings". 2018, p. 66-73.
Keywords
Biomedical abstracts, Biomedical text, Crf models, Detection models, Disabilities detection, Exact matching, Long short-term memory, Natural language processing systems, Semi- supervised learning, Semi-supervised learning Learning algorithms, Supervised learning, Word embedding
Group of research
GPLN - Natural Language Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications

Participants

Attachments