A4 Refereed article in a conference publication
Deep Learning With Minimal Training Data: TurkuNLP Entry in the BioNLP Shared Task 2016
Authors: Farrokh Mehryary, Jari Bjorne, Sampo Pyysalo, Tapio Salakoski, Filip Ginter
Editors: Claire Nédellec, Robert Bossy, Jin-Dong Kim
Conference name: BioNLP Shared Task
Publishing place: Stroudsburg
Publication year: 2016
Book title : Proceedings of the 4th BioNLP Shared Task Workshop
Series title: ACL Proceedings
First page : 73
Last page: 81
Number of pages: 9
ISBN: 978-1-945626-21-0
Web address : https://aclweb.org/anthology/W/W16/W16-3009.pdf
We present the TurkuNLP entry to
the BioNLP Shared Task 2016 Bacteria
Biotopes event extraction (BB3-event)
subtask. We propose a deep learning-based
approach to event extraction using
a combination of several Long Short-Term
Memory (LSTM) networks over syntactic
dependency graphs. Features for the
proposed neural network are generated
based on the shortest path connecting the
two candidate entities in the dependency
graph. We further detail how this network
can be efficiently trained to have good generalization
performance even when only a
very limited number of training examples
are available and part-of-speech (POS)
and dependency type feature representations
must be learned from scratch. Our
method ranked second among the entries
to the shared task, achieving an F-score of
52.1% with 62.3% precision and 44.8% recall
Downloadable publication This is an electronic reprint of the original article. |  |
