Regularization techniques for fine-tuning in neural machine translation

Antonio Valerio Miceli Barone, Barry Haddow, Ulrich Germann, Rico Sennrich


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.
Anthology ID:
D17-1156
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1489–1494
Language:
URL:
https://www.aclweb.org/anthology/D17-1156
DOI:
10.18653/v1/D17-1156
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1156.pdf