Loading...
Loading...

Go to the content (press return)

Coin_flipper at eHealth-KD challenge 2019: voting LSTMs for key phrases and semantic relation identification applied to spanish eHealth texts

Author
Català Roig, N.; Martin, M.
Type of activity
Presentation of work at congresses
Name of edition
Iberian Languages Evaluation Forum 2019
Date of publication
2019
Presentation's date
2019-09-24
Book of congress proceedings
Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2019): co-located with 35th Conference of the Spanish Society for Natural Language Processing (SEPLN 2019): Bilbao, Spain, September 24th, 2019
First page
17
Last page
25
Repository
http://hdl.handle.net/2117/168801 Open in new window
URL
http://ceur-ws.org/Vol-2421/ Open in new window
Abstract
This paper describes our approach presented for the eHealthKD 2019 challenge. Our participation was aimed at testing how far we could go using generic tools for Text-Processing but, at the same time, using common optimization techniques in the field of Data Mining. The architecture proposed for both tasks of the challenge is a standard stacked 2-layer bi-LSTM. The main particularities of our approach are: (a) The use of a surrogate function of F1 as loss function to close the gap between the min...
Keywords
Detection of semantic relations, F1 loss function, Key phrase detection, LSTMs, Majority Voting
Group of research
GPLN - Natural Language Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
KEMLG - Knowledge Engineering and Machine Learning Group
TALP - Centre for Language and Speech Technologies and Applications

Participants