Corpus ID: 4898660

Investigating Backtranslation in Neural Machine Translation

@article{Poncelas2018InvestigatingBI,
  title={Investigating Backtranslation in Neural Machine Translation},
  author={Alberto Poncelas and D. Shterionov and A. Way and G. M. D. B. Wenniger and P. Passban},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.06189}
}
A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT has been shown in many studies to outperform SMT, but mostly when large parallel corpora are available; in cases where data is limited, SMT can still outperform NMT. Recently researchers have shown that back-translating monolingual data can be used to… Expand
Using Monolingual Data in Neural Machine Translation: a Systematic Study
Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation
Domain Adaptation for NMT via Filtered Iterative Back-Translation
Simple Fusion: Return of the Language Model
Improving Neural Machine Translation with Pre-trained Representation
Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation
Neural Machine Translation for translating into Croatian and Serbian
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 37 REFERENCES
Neural versus Phrase-Based Machine Translation Quality: a Case Study
Using Target-side Monolingual Data for Neural Machine Translation through Multi-task Learning
Neural Machine Translation by Jointly Learning to Align and Translate
...
1
2
3
4
...