Painless Relation Extraction with Kindred

Jake Lever, Steven Jones


Abstract
Relation extraction methods are essential for creating robust text mining tools to help researchers find useful knowledge in the vast published literature. Easy-to-use and generalizable methods are needed to encourage an ecosystem in which researchers can easily use shared resources and build upon each others’ methods. We present the Kindred Python package for relation extraction. It builds upon methods from the most successful tools in the recent BioNLP Shared Task to predict high-quality predictions with low computational cost. It also integrates with PubAnnotation, PubTator, and BioNLP Shared Task data in order to allow easy development and application of relation extraction models.
Anthology ID:
W17-2322
Volume:
BioNLP 2017
Month:
August
Year:
2017
Address:
Vancouver, Canada,
Editors:
Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, Junichi Tsujii
Venue:
BioNLP
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
176–183
Language:
URL:
https://aclanthology.org/W17-2322
DOI:
10.18653/v1/W17-2322
Bibkey:
Cite (ACL):
Jake Lever and Steven Jones. 2017. Painless Relation Extraction with Kindred. In BioNLP 2017, pages 176–183, Vancouver, Canada,. Association for Computational Linguistics.
Cite (Informal):
Painless Relation Extraction with Kindred (Lever & Jones, BioNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-2322.pdf