OhioState at SemEval-2018 Task 7: Exploiting Data Augmentation for Relation Classification in Scientific Papers using Piecewise Convolutional Neural Networks

TL;DR

This paper presents a neural network-based system for classifying semantic relations in scientific papers, demonstrating that data augmentation significantly improves performance, with competitive results in a shared task.

Contribution

The authors introduce a simple piecewise convolutional neural network combined with data augmentation to enhance relation classification in scientific texts.

Findings

Data augmentation significantly boosts model performance.

The system achieved top-10 rankings in the shared task.

A straightforward neural encoder performs competitively in relation classification.

Abstract

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.