Neural machine translation (NMT) is typically domain-dependent and style-dependent, and it requires lots of training data. State-of-the-art NMT models often fall short in handling colloquial variations of its source language and the lack of parallel data in this regard is a challenging hurdle in systematically improving the existing models. In this work, we develop a novel colloquial Indonesian-English test-set collected from YouTube transcript and Twitter. We perform synthetic style augmentation to the source of formal Indonesian language and show that it improves the baseline Id-En models (in BLEU) over the new test data.
@article{arxiv.2012.15178,
title = {Synthetic Source Language Augmentation for Colloquial Neural Machine Translation},
author = {Asrul Sani Ariesandy and Mukhlis Amien and Alham Fikri Aji and Radityo Eko Prasojo},
journal= {arXiv preprint arXiv:2012.15178},
year = {2021}
}