-
Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020
Recent advancements in Neural Machine Translation (NMT) models have prov...
read it
-
Unsupervised Domain Adaptation for Neural Machine Translation with Iterative Back Translation
State-of-the-art neural machine translation (NMT) systems are data-hungr...
read it
-
Word-based Domain Adaptation for Neural Machine Translation
In this paper, we empirically investigate applying word-level weights to...
read it
-
Domain Adaptive Inference for Neural Machine Translation
We investigate adaptive ensemble weighting for Neural Machine Translatio...
read it
-
Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem
Training data for NLP tasks often exhibits gender bias in that fewer sen...
read it
-
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
To better understand the effectiveness of continued training, we analyze...
read it
-
The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task
We describe the University of Maryland machine translation systems submi...
read it
Regularization techniques for fine-tuning in neural machine translation
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.
READ FULL TEXT
Comments
There are no comments yet.