NTNU at SemEval-2018 Task 7: Classifier Ensembling for Semantic Relation Identification and Classification in Scientific Papers
Biswanath Barik, Utpal Kumar Sikdar, Björn Gambäck · 2018
The paper presents NTNU's contribution to SemEval-2018 Task 7 on relation identification and classification.The class weights and parameters of five alternative supervised classifiers were optimized through grid search and cross-validation.The outputs of the classifiers were combined through voting for the final prediction.A wide variety of features were explored, with the most informative identified by feature selection.The best setting achieved F 1 scores of 47.4% and 66.0% in the relation classification subtasks 1.1 and 1.2.For relation identification and classification in subtask 2, it achieved F 1 scores of 33.9% and 17.0%,