RT Journal Article
SR Electronic
T1 Binary Relation Extraction from Biomedical Literature using Dependency Trees and SVMs
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 082479
DO 10.1101/082479
A1 Anuj Sharma
A1 Vassilis Virvilis
A1 Tina Lekka
A1 Christos Andronis
YR 2016
UL http://biorxiv.org/content/early/2016/10/21/082479.abstract
AB The goal of Biomedical relation extraction is to uncover high-quality relations from life science literature with diverse applications in the fields of Biology and Medicine. In the last decade, several methods can be found in published literature ranging from binary to complex relation extraction. In this work, we present a binary relation extraction system that relies on sentence level dependency features. We use a novel approach to map dependency tree based rules to feature vectors that can be used to train a classifier. We build a SVM classifier using these feature vectors and our experimental results show that it outperforms simple co-occurrence and rule-based systems. Through our experiments, using two ‘real-world’ examples, we quantify the positive impact of improved relation extraction on Literature Based Discovery.