Robust QA System with xEDA : Final Report

Data augmentation is often used in machine learning to reduce overfitting. However, data augmentation has not been thoroughly explored in NLP in the context of improving robustness on shifts in data domains. We present xEDA: extended easy data augmentation techniques for boosting performance on question answering tasks. xEDA extends existing data augmentation techniques by drawing inspirations from techniques in computer vision. We evaluate its performance on out-of-domain question answering tasks and show that xEDA can improve performance and robustness to domain shifts when a small subset of the out-of-domain data is available at train time.