Data augmentation for morphological reinflection

Abstract

This paper presents the submission of the Linguistics Department of the University of Colorado at Boulder for the 2017 CoNLL-SIGMORPHON Shared Task on Universal Morphological Reinflection. The system is implemented as an RNN Encoder-Decoder. It is specifically geared toward a low-resource setting. To this end, it employs data augmentation for counteracting overfitting and a copy symbol for processing characters unseen in the training data. The system is an ensemble of ten models combined using a weighted voting scheme. It delivers substantial improvement in accuracy compared to a non-neural baseline system in presence of varying amounts of training data.