LightRel at SemEval-2018 Task 7: Lightweight and Fast Relation Classification

Tyler Renslow, Günter Neumann


Abstract
We present LightRel, a lightweight and fast relation classifier. Our goal is to develop a high baseline for different relation extraction tasks. By defining only very few data-internal, word-level features and external knowledge sources in the form of word clusters and word embeddings, we train a fast and simple linear classifier
Anthology ID:
S18-1123
Volume:
Proceedings of The 12th International Workshop on Semantic Evaluation
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
SemEval
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
778–782
Language:
URL:
https://aclanthology.org/S18-1123
DOI:
10.18653/v1/S18-1123
Bibkey:
Cite (ACL):
Tyler Renslow and Günter Neumann. 2018. LightRel at SemEval-2018 Task 7: Lightweight and Fast Relation Classification. In Proceedings of The 12th International Workshop on Semantic Evaluation, pages 778–782, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
LightRel at SemEval-2018 Task 7: Lightweight and Fast Relation Classification (Renslow & Neumann, SemEval 2018)
Copy Citation:
PDF:
https://aclanthology.org/S18-1123.pdf
Data
SemEval-2010 Task 8