OhioState at SemEval-2018 Task 7: Exploiting Data Augmentation for Relation Classification in Scientific Papers using Piecewise Convolutional Neural Networks
This work addresses relation extraction for scientific text analysis, but it is incremental as it applies existing methods with minor enhancements to a specific competition.
The paper tackled relation classification in scientific papers by using a piecewise convolutional neural network with data augmentation, achieving 8th out of 20 teams on noisy data and 12th out of 28 teams on clean data in the SemEval-2018 shared task.
We describe our system for SemEval-2018 Shared Task on Semantic Relation Extraction and Classification in Scientific Papers where we focus on the Classification task. Our simple piecewise convolution neural encoder performs decently in an end to end manner. A simple inter-task data augmentation signifi- cantly boosts the performance of the model. Our best-performing systems stood 8th out of 20 teams on the classification task on noisy data and 12th out of 28 teams on the classification task on clean data.