English

GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification

Computation and Language 2018-04-17 v1

Abstract

SemEval 2018 Task 7 focuses on relation ex- traction and classification in scientific literature. In this work, we present our tree-based LSTM network for this shared task. Our approach placed 9th (of 28) for subtask 1.1 (relation classification), and 5th (of 20) for subtask 1.2 (relation classification with noisy entities). We also provide an ablation study of features included as input to the network.

Keywords

Cite

@article{arxiv.1804.05408,
  title  = {GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification},
  author = {Sean MacAvaney and Luca Soldaini and Arman Cohan and Nazli Goharian},
  journal= {arXiv preprint arXiv:1804.05408},
  year   = {2018}
}

Comments

5 pages, Accepted to SemEval 2018

R2 v1 2026-06-23T01:24:10.172Z