---
title: "Investigating Backtranslation in Neural — Poncelas 2018"
description: "Neural MT needs large parallel corpora. When these are scarce, practitioners routinely enlarge the training data by back-translating monolingual text…"
authors: ["Alberto Poncelas", "Dimitar Shterionov", "Andy Way", "Gideon Maillette de Buy Wenniger", "Peyman Passban"]
year: 2018
venue: "Proceedings of the 21st Annual Conference of the European Association for Machine Translation"
source: "https://aclanthology.org/2018.eamt-main.25/"
licence: "CC BY-ND 4.0 (EAMT)"
licence_url: "https://creativecommons.org/licenses/by-nd/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/poncelas-2018-investigating-backtranslation-neural-machine-translation/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/poncelas-2018-investigating-backtranslation-neural-machine-translation/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2018](https://md.research.elamur.ai/free/papers/2018/page/2/) / Investigating Backtranslation in Neural Machine Translation

# Investigating Backtranslation in Neural Machine Translation

**Authors:** Alberto Poncelas, [Dimitar Shterionov](https://md.research.elamur.ai/free/authors/dimitar-shterionov/), [Andy Way](https://md.research.elamur.ai/free/authors/andy-way/), Gideon Maillette de Buy Wenniger, Peyman Passban · **Year:** 2018 · **Venue:** Proceedings of the 21st Annual Conference of the European Association for Machine Translation · **Licence:** [CC BY-ND 4.0 (EAMT)](https://creativecommons.org/licenses/by-nd/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2018.eamt-main.25/) · [PDF](https://aclanthology.org/2018.eamt-main.25.pdf) · [OpenAlex](https://openalex.org/W2797913374)

**Citations:** 124 citations (openalex-snapshot · 2026-10-14) · [60](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Neural MT needs large parallel corpora. When these are scarce, practitioners routinely enlarge the training data by back-translating monolingual text into synthetic sentence pairs. The authors argue that this habit spread without careful study of its limits, so they test it systematically for German-to-English. They use the WMT 2015 German–English data and train OpenNMT-py systems with standard settings and word-level vocabularies. BPE is deliberately avoided so that sub-word segmentation cannot confound the comparisons. Training corpora of growing size come in three kinds: human-translated only, back-translated only, and mixtures of both. Systems are scored with BLEU, TER, METEOR and chrF.

Surprisingly, purely synthetic training gets close to authentic-only quality, and at small data sizes synthetic or mixed corpora even do better. Synthetic-only quality eventually levels off, however. Mixed corpora begin to lose quality once machine-translated data outweighs human data by roughly two to one. The findings suggest that any existing reverse-direction system can bootstrap NMT for low-resource pairs, but the synthetic share should be limited.

## Key points
- **Data:** WMT 2015 German–English parallel corpus, cleaned of sentences longer than 126 words, totalling 4.48M sentence pairs (225M words). Models were built with OpenNMT-py using word-based dictionaries rather than BPE.
- **Synthetic-only growth:** These models start at BLEU 0.229 with 1M pairs and peak at 0.2363 with 3.5M pairs, a 3.2% relative gain. The final step from 3M to 3.5M is not statistically significant at p = 0.01.
- **Vocabulary coverage:** Synthetic-data models stay near 61% coverage regardless of corpus size, while authentic-data models exceed 66%. The authors attribute this to the limited vocabulary and errors of the system that produced the back-translations.
- **Hybrid degradation:** Hybrid training degrades once synthetic data reaches about a 2:1 ratio to authentic data. The 3.5M hybrid model scores 1.2% below the 3M hybrid model.
- **Synthetic beats authentic on METEOR:** With 1M sentence pairs, the synthetic-only engine outscores the authentic-only engine of the same size on METEOR.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) · [Machine translation](https://md.research.elamur.ai/free/shelves/machine-translation/)

Topics: [Machine translation](https://md.research.elamur.ai/free/topics/machine-translation/)

## Cited by

Cited by

60 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 57 not yet.

- [On The Evaluation of Machine Translation Systems Trained With Back-Translation](https://md.research.elamur.ai/free/papers/edunov-2020-evaluation-machine-translation-systems-trained/)
- [APE at Scale and Its Implications on MT Evaluation Biases](https://md.research.elamur.ai/free/papers/freitag-2019-ape-scale-its-implications-mt/)
- [Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation](https://md.research.elamur.ai/free/papers/vanmassenhove-2019-lost-translation-loss-decay-linguistic/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{poncelas2018investigating,
  title = {{Investigating Backtranslation in Neural Machine Translation}},
  author = {Poncelas, Alberto and Shterionov, Dimitar and Way, Andy and Wenniger, Gideon Maillette de Buy and Passban, Peyman},
  booktitle = {Proceedings of the 21st Annual Conference of the European Association for Machine Translation},
  year = {2018},
  url = {https://aclanthology.org/2018.eamt-main.25/}
}
```

- [← previous Integrating Transformer and Paraphrase Rules for Sentence Simplification](https://md.research.elamur.ai/free/papers/zhao-2018-integrating-transformer-paraphrase-rules-sentence/)
- [next → Investigating NP-Chunking with Universal Dependencies for English](https://md.research.elamur.ai/free/papers/ud-2018-lacroix-investigating-np-chunking-universal-dependencies/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/papers/2018/page/2/)

## References

36 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. In Proceedings of the International Conference on Learning Representations (ICLR) 2015, San Diego, CA, USA, 2015. 15pp. [find](https://scholar.google.com/scholar?q=Dzmitry+Bahdanau%2C+Kyunghyun+Cho%2C+and+Yoshua+Bengio%2E+Neural+machine+translation+by+jointly+learning+to+align+and+translate%2E+In+Proceedings+of+the+International+Conference+on+Learning+Representations+%28I) [our card](https://md.research.elamur.ai/free/papers/bahdanau-2014-neural-machine-translation-jointly-learning/)
2. Satanjeev Banerjee and Alon Lavie. Meteor: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization, pages 65–72, Ann Arbor, Michigan, 2005. [find](https://scholar.google.com/scholar?q=Satanjeev+Banerjee+and+Alon+Lavie%2E+Meteor%3A+An+automatic+metric+for+MT+evaluation+with+improved+correlation+with+human+judgments%2E+In+Proceedings+of+the+ACL+workshop+on+intrinsic+and+extrinsic+evaluatio) [our card](https://md.research.elamur.ai/free/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/)
3. Yonatan Belinkov and Yonatan Bisk. Synthetic and natural noise both break neural machine translation. arXiv preprint arXiv:1711.02173, 2017. [find](https://scholar.google.com/scholar?q=Yonatan+Belinkov+and+Yonatan+Bisk%2E+Synthetic+and+natural+noise+both+break+neural+machine+translation%2E+arXiv+preprint+arXiv%3A1711%2E02173%2C+2017%2E)
4. Luisa Bentivogli, Arianna Bisazza, Mauro Cettolo, and Marcello Federico. Neural versus Phrase-Based Machine Translation Quality: a Case Study. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 257–267, Austin, Texas, USA, 2016. [find](https://scholar.google.com/scholar?q=Luisa+Bentivogli%2C+Arianna+Bisazza%2C+Mauro+Cettolo%2C+and+Marcello+Federico%2E+Neural+versus+Phrase%2DBased+Machine+Translation+Quality%3A+a+Case+Study%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Method) [our card](https://md.research.elamur.ai/free/papers/bentivogli-2016-neural-versus-phrase-based-machine/)
5. Ondrej Bojar and Ales Tamchyna. Improving translation model by monolingual data. In Proceedings of the Sixth Workshop on Statistical Machine Translation, WMT@EMNLP 2011, pages 330–336, Edinburgh, Scotland, 2011. [find](https://scholar.google.com/scholar?q=Ondrej+Bojar+and+Ales+Tamchyna%2E+Improving+translation+model+by+monolingual+data%2E+In+Proceedings+of+the+Sixth+Workshop+on+Statistical+Machine+Translation%2C+WMT%40EMNLP+2011%2C+pages+330%E2%80%93336%2C+Edinburgh%2C+Scot)
6. Ondrej Bojar, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Aurelie Neveol, Mariana Neves, Martin Popel, Matt Post, Raphael Rubino, Carolina Scarton, Lucia Specia, Marco Turchi,… [find](https://scholar.google.com/scholar?q=Ondrej+Bojar%2C+Rajen+Chatterjee%2C+Christian+Federmann%2C+Yvette+Graham%2C+Barry+Haddow%2C+Matthias+Huck%2C+Antonio+Jimeno+Yepes%2C+Philipp+Koehn%2C+Varvara+Logacheva%2C+Christof+Monz%2C+Matteo+Negri%2C+Aurelie+Neveol%2C+Ma) [our card](https://md.research.elamur.ai/free/papers/bojar-2016-findings-2016-conference-machine-translation/)
7. Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Barry Haddow, Matthias Huck, Chris Hokamp, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Matt Post, Carolina Scarton, Lucia Specia, and Marco Turchi. Findings of the 2015 Workshop on Statistical Machine Translation. In Proceeding… [find](https://scholar.google.com/scholar?q=Ondr%CC%8Cej+Bojar%2C+Rajen+Chatterjee%2C+Christian+Federmann%2C+Barry+Haddow%2C+Matthias+Huck%2C+Chris+Hokamp%2C+Philipp+Koehn%2C+Varvara+Logacheva%2C+Christof+Monz%2C+Matteo+Negri%2C+Matt+Post%2C+Carolina+Scarton%2C+Lucia+Speci) [our card](https://md.research.elamur.ai/free/papers/bojar-2015-findings-2015-workshop-statistical-machine/)
8. Sheila Castilho, Joss Moorkens, Federico Gaspari, Iacer Calixto, John Tinsley, and Andy Way. Is neural machine translation the new state of the art? The Prague Bulletin of Mathematical Linguistics, 108(1):109–120, 2017. [find](https://scholar.google.com/scholar?q=Sheila+Castilho%2C+Joss+Moorkens%2C+Federico+Gaspari%2C+Iacer+Calixto%2C+John+Tinsley%2C+and+Andy+Way%2E+Is+neural+machine+translation+the+new+state+of+the+art%3F+The+Prague+Bulletin+of+Mathematical+Linguistics%2C+10)
9. Kyunghyun Cho, Bart van Merriënboer, Çağlar Gülçehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using RNN encoder– decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Langua… [find](https://scholar.google.com/scholar?q=Kyunghyun+Cho%2C+Bart+van+Merrie%CC%88nboer%2C+C%CC%A7ag%CC%86lar+Gu%CC%88lc%CC%A7ehre%2C+Dzmitry+Bahdanau%2C+Fethi+Bougares%2C+Holger+Schwenk%2C+and+Yoshua+Bengio%2E+Learning+phrase+representations+using+RNN+encoder%E2%80%93+decoder+for+statistic)
10. Jonathan H. Clark, Chris Dyer, Alon Lavie, and Noah A. Smith. Better hypothesis testing for statistical machine translation: Controlling for optimizer instability. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short… [find](https://scholar.google.com/scholar?q=Jonathan+H%2E+Clark%2C+Chris+Dyer%2C+Alon+Lavie%2C+and+Noah+A%2E+Smith%2E+Better+hypothesis+testing+for+statistical+machine+translation%3A+Controlling+for+optimizer+instability%2E+In+Proceedings+of+the+49th+Annual+Me)
11. Mattia Antonino Di Gangi, Nicola Bertoldi, and Marcello Federico. FBK’s participation to the English-to-German News Translation Task of WMT 2017. In Proceedings of the Second Conference on Machine Translation, pages 271– 275, Copenhagen, Denmark, 2017. [find](https://scholar.google.com/scholar?q=Mattia+Antonino+Di+Gangi%2C+Nicola+Bertoldi%2C+and+Marcello+Federico%2E+FBK%E2%80%99s+participation+to+the+English%2Dto%2DGerman+News+Translation+Task+of+WMT+2017%2E+In+Proceedings+of+the+Second+Conference+on+Machine+Tra)
12. Tobias Domhan and Felix Hieber. Using target-side monolingual data for neural machine translation through multi-task learning. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1500–1505, Copenhagen, Denmark, 2017. [find](https://scholar.google.com/scholar?q=Tobias+Domhan+and+Felix+Hieber%2E+Using+target%2Dside+monolingual+data+for+neural+machine+translation+through+multi%2Dtask+learning%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+Natural+Lan)
13. Çaglar Gülçehre, Orhan Firat, Kelvin Xu, Kyunghyun Cho, Loı̈c Barrault, Huei-Chi Lin, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. On using monolingual corpora in neural machine translation. CoRR, abs/1503.03535, 2015. [find](https://scholar.google.com/scholar?q=C%CC%A7aglar+Gu%CC%88lc%CC%A7ehre%2C+Orhan+Firat%2C+Kelvin+Xu%2C+Kyunghyun+Cho%2C+Lo%C4%B1%CC%88c+Barrault%2C+Huei%2DChi+Lin%2C+Fethi+Bougares%2C+Holger+Schwenk%2C+and+Yoshua+Bengio%2E+On+using+monolingual+corpora+in+neural+machine+translation%2E+) [our card](https://md.research.elamur.ai/free/papers/gulcehre-2015-using-monolingual-corpora-neural-machine/)
14. Sepp Hochreiter, Jürgen Schmidhuber, and Corso Elvezia. Long short-term memory. Neural Computation, 9(8):1735–1780, 1997. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter%2C+Ju%CC%88rgen+Schmidhuber%2C+and+Corso+Elvezia%2E+Long+short%2Dterm+memory%2E+Neural+Computation%2C+9%288%29%3A1735%E2%80%931780%2C+1997%2E)
15. Marcin Junczys-Dowmunt, Tomasz Dwojak, and Hieu Hoang. Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions. In Proceedings of the 9th International Workshop on Spoken Language Translation (IWSLT), Seattle, WA, 2016. 8pp. [find](https://scholar.google.com/scholar?q=Marcin+Junczys%2DDowmunt%2C+Tomasz+Dwojak%2C+and+Hieu+Hoang%2E+Is+Neural+Machine+Translation+Ready+for+Deployment%3F+A+Case+Study+on+30+Translation+Directions%2E+In+Proceedings+of+the+9th+International+Workshop+o) [our card](https://md.research.elamur.ai/free/papers/dowmunt-2016-is-neural-machine-translation-ready/)
16. Alina Karakanta, Jon Dehdari, and Josef van Genabith. Neural machine translation for low-resource languages without parallel corpora. Machine Translation, 32, 2018. 23pp. [find](https://scholar.google.com/scholar?q=Alina+Karakanta%2C+Jon+Dehdari%2C+and+Josef+van+Genabith%2E+Neural+machine+translation+for+low%2Dresource+languages+without+parallel+corpora%2E+Machine+Translation%2C+32%2C+2018%2E+23pp%2E)
17. Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander M. Rush. OpenNMT: Open-Source Toolkit for Neural Machine Translation. In Proceedings of ACL 2017, System Demonstrations, pages 67–72, Vancouver, Canada, 2017. [find](https://scholar.google.com/scholar?q=Guillaume+Klein%2C+Yoon+Kim%2C+Yuntian+Deng%2C+Jean+Senellart%2C+and+Alexander+M%2E+Rush%2E+OpenNMT%3A+Open%2DSource+Toolkit+for+Neural+Machine+Translation%2E+In+Proceedings+of+ACL+2017%2C+System+Demonstrations%2C+pages+67) [our card](https://md.research.elamur.ai/free/papers/klein-2017-opennmt-open-source-toolkit-neural/)
18. Philipp Koehn. Statistical significance tests for machine translation evaluation. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pages 388–395, Barcelona, Spain, 2004. [find](https://scholar.google.com/scholar?q=Philipp+Koehn%2E+Statistical+significance+tests+for+machine+translation+evaluation%2E+In+Proceedings+of+the+2004+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+388%E2%80%93395%2C+Barcelona%2C+S)
19. Philipp Koehn. Statistical Machine Translation. Cambridge University Press, New York, NY, USA, 1st edition, 2010. [find](https://scholar.google.com/scholar?q=Philipp+Koehn%2E+Statistical+Machine+Translation%2E+Cambridge+University+Press%2C+New+York%2C+NY%2C+USA%2C+1st+edition%2C+2010%2E)
20. Philipp Koehn and Rebecca Knowles. Six challenges for neural machine translation. In Proceedings of the First Workshop on Neural Machine Translation, pages 28–39, Vancouver, Canada, 2017. [find](https://scholar.google.com/scholar?q=Philipp+Koehn+and+Rebecca+Knowles%2E+Six+challenges+for+neural+machine+translation%2E+In+Proceedings+of+the+First+Workshop+on+Neural+Machine+Translation%2C+pages+28%E2%80%9339%2C+Vancouver%2C+Canada%2C+2017%2E)
21. Chi-kiu Lo, Boxing Chen, Colin Cherry, George Foster, Samuel Larkin, Darlene Stewart, and Roland Kuhn. NRC Machine Translation System for WMT 2017. In Proceedings of the Second Conference on Machine Translation, pages 330–337, Copenhagen, Denmark, 2017. [find](https://scholar.google.com/scholar?q=Chi%2Dkiu+Lo%2C+Boxing+Chen%2C+Colin+Cherry%2C+George+Foster%2C+Samuel+Larkin%2C+Darlene+Stewart%2C+and+Roland+Kuhn%2E+NRC+Machine+Translation+System+for+WMT+2017%2E+In+Proceedings+of+the+Second+Conference+on+Machine+T)
22. Association for Machine Translation (EAMT), pages 74–79, Prague, Czech Republic, 2017. [find](https://scholar.google.com/scholar?q=Association+for+Machine+Translation+%28EAMT%29%2C+pages+74%E2%80%9379%2C+Prague%2C+Czech+Republic%2C+2017%2E)
23. Thang Luong, Hieu Pham, and Christopher D. Manning. Effective approaches to attention-based neural machine translation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1412–1421, Lisbon, Portugal, 2015. [find](https://scholar.google.com/scholar?q=Thang+Luong%2C+Hieu+Pham%2C+and+Christopher+D%2E+Manning%2E+Effective+approaches+to+attention%2Dbased+neural+machine+translation%2E+In+Proceedings+of+the+2015+Conference+on+Empirical+Methods+in+Natural+Language+P)
24. Matthew Snover, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, and John Makhoul. A study of translation edit rate with targeted human annotation. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas, pages 223–231, Cambridge, Massachusetts, USA, 2006. [find](https://scholar.google.com/scholar?q=Matthew+Snover%2C+Bonnie+Dorr%2C+Richard+Schwartz%2C+Linnea+Micciulla%2C+and+John+Makhoul%2E+A+study+of+translation+edit+rate+with+targeted+human+annotation%2E+In+Proceedings+of+the+7th+Conference+of+the+Associat) [our card](https://md.research.elamur.ai/free/papers/snover-2006-study-translation-edit-rate-targeted/)
25. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for automatic evaluation of machine translation. In Proceedings of 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA, 2002. [find](https://scholar.google.com/scholar?q=Kishore+Papineni%2C+Salim+Roukos%2C+Todd+Ward%2C+and+Wei%2DJing+Zhu%2E+Bleu%3A+a+method+for+automatic+evaluation+of+machine+translation%2E+In+Proceedings+of+40th+Annual+Meeting+of+the+Association+for+Computational+) [our card](https://md.research.elamur.ai/free/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
26. Jaehong Park, Byunggook Na, and Sungroh Yoon. Building a neural machine translation system using only synthetic parallel data. arXiv preprint arXiv:1704.00253, 2017. — [arXiv:1704.00253](https://arxiv.org/abs/1704.00253) [find](https://scholar.google.com/scholar?q=Jaehong+Park%2C+Byunggook+Na%2C+and+Sungroh+Yoon%2E+Building+a+neural+machine+translation+system+using+only+synthetic+parallel+data%2E+arXiv+preprint+arXiv%3A1704%2E00253%2C+2017%2E+%E2%80%94+%5BarXiv%3A1704%2E00253%5D%28https%3A%2F%2Farxiv)
27. Maja Popovic. chrF: character n-gram F-score for automatic MT evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 392–395, Lisbon, Portugal, 2015. [find](https://scholar.google.com/scholar?q=Maja+Popovic%2E+chrF%3A+character+n%2Dgram+F%2Dscore+for+automatic+MT+evaluation%2E+In+Proceedings+of+the+Tenth+Workshop+on+Statistical+Machine+Translation%2C+pages+392%E2%80%93395%2C+Lisbon%2C+Portugal%2C+2015%2E) [our card](https://md.research.elamur.ai/free/papers/popovic-2015-chrf-character-n-gram-f/)
28. Spencer Rarrick, Chris Quirk, and Will Lewis. Mt detection in web-scraped parallel corpora. In Proceedings of MT Summit XIII, pages 422– 429, Xiamen, China, 2011. [find](https://scholar.google.com/scholar?q=Spencer+Rarrick%2C+Chris+Quirk%2C+and+Will+Lewis%2E+Mt+detection+in+web%2Dscraped+parallel+corpora%2E+In+Proceedings+of+MT+Summit+XIII%2C+pages+422%E2%80%93+429%2C+Xiamen%2C+China%2C+2011%2E)
29. Rico Sennrich, Barry Haddow, and Alexandra Birch. Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1715–1725, Berlin, Germany, 2016a. [find](https://scholar.google.com/scholar?q=Rico+Sennrich%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+Neural+machine+translation+of+rare+words+with+subword+units%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Computational+Linguistic)
30. Rico Sennrich, Barry Haddow, and Alexandra Birch. Improving neural machine translation models with monolingual data. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 86–96, Berlin, Germany, 2016b. [find](https://scholar.google.com/scholar?q=Rico+Sennrich%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+Improving+neural+machine+translation+models+with+monolingual+data%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Computational+Ling)
31. Rico Sennrich, Barry Haddow, and Alexandra Birch. Edinburgh Neural Machine Translation Systems for WMT 16. In Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, pages 371–376, Berlin, Germany, 2016c. [find](https://scholar.google.com/scholar?q=Rico+Sennrich%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+Edinburgh+Neural+Machine+Translation+Systems+for+WMT+16%2E+In+Proceedings+of+the+First+Conference+on+Machine+Translation%3A+Volume+2%2C+Shared+Task+Papers%2C+) [our card](https://md.research.elamur.ai/free/papers/sennrich-2016-edinburgh-neural-machine-translation-systems/)
32. Dimitar Shterionov, Pat Nagle, Laura Casanellas, Riccardo Superbo, and Tony O’Dowd. Empirical evaluation of nmt and pbsmt quality for large-scale translation production. In User track of the 20th Annual Conference of the European Harold Somers. Round-trip translation: What is it good for? In Proceed… [find](https://scholar.google.com/scholar?q=Dimitar+Shterionov%2C+Pat+Nagle%2C+Laura+Casanellas%2C+Riccardo+Superbo%2C+and+Tony+O%E2%80%99Dowd%2E+Empirical+evaluation+of+nmt+and+pbsmt+quality+for+large%2Dscale+translation+production%2E+In+User+track+of+the+20th+Annu)
33. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. Sequence to sequence learning with neural networks. In Proceedings of Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, pages 3104–3112, Montreal, Quebec, Canada, 2014. [find](https://scholar.google.com/scholar?q=Ilya+Sutskever%2C+Oriol+Vinyals%2C+and+Quoc+V%2E+Le%2E+Sequence+to+sequence+learning+with+neural+networks%2E+In+Proceedings+of+Advances+in+Neural+Information+Processing+Systems+27%3A+Annual+Conference+on+Neural+I)
34. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Proceedings of the Thirty-first Annual Conference on Neural Information Processing Systems, pages 5998–6008, Long Beach, CA., USA, 2017. [find](https://scholar.google.com/scholar?q=Ashish+Vaswani%2C+Noam+Shazeer%2C+Niki+Parmar%2C+Jakob+Uszkoreit%2C+Llion+Jones%2C+Aidan+N+Gomez%2C+Lukasz+Kaiser%2C+and+Illia+Polosukhin%2E+Attention+is+all+you+need%2E+In+Proceedings+of+the+Thirty%2Dfirst+Annual+Confer)
35. Andy Way. Traditional and emerging use-cases for machine translation. In Proceedings of Translating and the Computer 35, London, 2013. 12pp. [find](https://scholar.google.com/scholar?q=Andy+Way%2E+Traditional+and+emerging+use%2Dcases+for+machine+translation%2E+In+Proceedings+of+Translating+and+the+Computer+35%2C+London%2C+2013%2E+12pp%2E)
36. Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Lukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, N… [find](https://scholar.google.com/scholar?q=Yonghui+Wu%2C+Mike+Schuster%2C+Zhifeng+Chen%2C+Quoc+V%2E+Le%2C+Mohammad+Norouzi%2C+Wolfgang+Macherey%2C+Maxim+Krikun%2C+Yuan+Cao%2C+Qin+Gao%2C+Klaus+Macherey%2C+Jeff+Klingner%2C+Apurva+Shah%2C+Melvin+Johnson%2C+Xiaobing+Liu%2C+Luk)