A4 Article in conference proceedings
Deep Learning With Minimal Training Data: TurkuNLP Entry in the BioNLP Shared Task 2016




List of Authors: Farrokh Mehryary, Jari Bjorne, Sampo Pyysalo, Tapio Salakoski, Filip Ginter
Place: Stroudsburg
Publication year: 2016
Book title *: Proceedings of the 4th BioNLP Shared Task Workshop
Title of series: ACL Proceedings
Number of pages: 9
ISBN: 978-1-945626-21-0

Abstract

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.
This reprint may differ from the original in pagination and typographic detail. Please cite the original version.




Last updated on 2019-29-01 at 13:34