REflex: Flexible Framework for Relation Extraction in Multiple Domains

Geeticka Chauhan, Matthew B.A. McDermott, Peter Szolovits

[How to correct problems with metadata yourself]


Abstract
Systematic comparison of methods for relation extraction (RE) is difficult because many experiments in the field are not described precisely enough to be completely reproducible and many papers fail to report ablation studies that would highlight the relative contributions of their various combined techniques. In this work, we build a unifying framework for RE, applying this on three highly used datasets (from the general, biomedical and clinical domains) with the ability to be extendable to new datasets. By performing a systematic exploration of modeling, pre-processing and training methodologies, we find that choices of preprocessing are a large contributor performance and that omission of such information can further hinder fair comparison. Other insights from our exploration allow us to provide recommendations for future research in this area.
Anthology ID:
W19-5004
Volume:
Proceedings of the 18th BioNLP Workshop and Shared Task
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Dina Demner-Fushman, Kevin Bretonnel Cohen, Sophia Ananiadou, Junichi Tsujii
Venue:
BioNLP
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
30–47
Language:
URL:
https://aclanthology.org/W19-5004
DOI:
10.18653/v1/W19-5004
Bibkey:
Cite (ACL):
Geeticka Chauhan, Matthew B.A. McDermott, and Peter Szolovits. 2019. REflex: Flexible Framework for Relation Extraction in Multiple Domains. In Proceedings of the 18th BioNLP Workshop and Shared Task, pages 30–47, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
REflex: Flexible Framework for Relation Extraction in Multiple Domains (Chauhan et al., BioNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/W19-5004.pdf
Code
 geetickachauhan/relation-extraction
Data
DDISemEval-2010 Task-8