Syntactic Dependency for relation extraction from Biomedical literature

DOI

10.2991/citcs.2012.186How to use a DOI?

Keywords

syntactic parsing; Dependency; Classification; extraction

Abstract

Relation extraction is important to improve complex natural language processing (NLP) applications. The Bio-Event extraction in GE shared task is important to understand biological processes. Although some progress has made in GE research, there is still much work to do to improve the performance of the extraction system. In this paper, we build a extraction system based on syntactic dependency technique. Relying on the output of the sentence parsing, we get rich features to build a classification model to separate the candidate edges into positive class and negative class. We obtain promising results on GE develop data set. Especially the results of simple events are comparable with the state-of-the-art GE extraction systems.

Copyright

© 2012, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiaomei Wei
AU  - Jianyong Wang
AU  - Yang Li
PY  - 2012/11
DA  - 2012/11
TI  - Syntactic Dependency for relation extraction from Biomedical literature
BT  - Proceedings of the 2012 National Conference on Information Technology and Computer Science
PB  - Atlantis Press
SP  - 733
EP  - 736
SN  - 1951-6851
UR  - https://doi.org/10.2991/citcs.2012.186
DO  - 10.2991/citcs.2012.186
ID  - Wei2012/11
ER  -