CLApr 15, 2018
GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification
arXiv:1804.05408v11091 citations
Originality Synthesis-oriented
AI Analysis
This work addresses relation classification in scientific texts, but it is incremental as it applies an existing method to a new dataset.
The paper tackled relation extraction and classification in scientific literature using a tree-based LSTM network, achieving 9th out of 28 teams for subtask 1.1 and 5th out of 20 for subtask 1.2.
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.