Regularization techniques for fine-tuning in neural machine translation
Abstract
We investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset. In this scenario, overfitting is a major challenge. We investigate a number of techniques to reduce overfitting and improve transfer learning, including regularization techniques such as dropout and L2-regularization towards an out-of-domain prior. In addition, we introduce tuneout, a novel regularization technique inspired by dropout. We apply these techniques, alone and in combination, to neural machine translation, obtaining improvements on IWSLT datasets for English->German and English->Russian. We also investigate the amounts of in-domain training data needed for domain adaptation in NMT, and find a logarithmic relationship between the amount of training data and gain in BLEU score.
Cite
@article{arxiv.1707.09920,
title = {Regularization techniques for fine-tuning in neural machine translation},
author = {Antonio Valerio Miceli Barone and Barry Haddow and Ulrich Germann and Rico Sennrich},
journal= {arXiv preprint arXiv:1707.09920},
year = {2017}
}
Comments
EMNLP 2017 short paper; for bibtex, see http://homepages.inf.ed.ac.uk/rsennric/bib.html#micelibarone2017b