Improvement of n-ary Relation Extraction by Adding Lexical Semantics to Distant-Supervision Rule Learning

Hong Li, Sebastian Krause, Feiyu Xu, Andrea Moro, Hans Uszkoreit, Roberto Navigli

2015

Abstract

A new method is proposed and evaluated that improves distantly supervised learning of pattern rules for n-ary relation extraction. The new method employs knowledge from a large lexical semantic repository to guide the discovery of patterns in parsed relation mentions. It extends the induced rules to semantically relevant material outside the minimal subtree containing the shortest paths connecting the relation entities and also discards rules without any explicit semantic content. It significantly raises both recall and precision with roughly 20% f-measure boost in comparison to the baseline system which does not consider the lexical semantic information.

Paper Citation

in Harvard Style

Li H., Krause S., Xu F., Moro A., Uszkoreit H. and Navigli R. (2015). Improvement of n-ary Relation Extraction by Adding Lexical Semantics to Distant-Supervision Rule Learning . In Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-074-1, pages 317-324. DOI: 10.5220/0005187303170324

in Bibtex Style

@conference{icaart15,
author={Hong Li and Sebastian Krause and Feiyu Xu and Andrea Moro and Hans Uszkoreit and Roberto Navigli},
title={Improvement of n-ary Relation Extraction by Adding Lexical Semantics to Distant-Supervision Rule Learning},
booktitle={Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2015},
pages={317-324},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005187303170324},
isbn={978-989-758-074-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Improvement of n-ary Relation Extraction by Adding Lexical Semantics to Distant-Supervision Rule Learning
SN - 978-989-758-074-1
AU - Li H.
AU - Krause S.
AU - Xu F.
AU - Moro A.
AU - Uszkoreit H.
AU - Navigli R.
PY - 2015
SP - 317
EP - 324
DO - 10.5220/0005187303170324