GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification
2018-04-15SEMEVAL 2018Code Available0· sign in to hype
Sean MacAvaney, Luca Soldaini, Arman Cohan, Nazli Goharian
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/Georgetown-IR-Lab/semeval2018-task7OfficialIn papermxnet★ 0
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.