---
title: "Stronger Baselines for Trustable Results in — Denkowski 2017"
description: "NMT papers often report gains over weak \"vanilla\" systems, so it is unclear whether a new method would still help a production-grade model."
authors: ["Michael Denkowski", "Graham Neubig"]
year: 2017
venue: "Proceedings of the First Workshop on Neural Machine Translation"
source: "https://aclanthology.org/W17-3203/"
doi: "10.18653/v1/w17-3203"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/denkowski-2017-stronger-baselines-trustable-results-neural/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/denkowski-2017-stronger-baselines-trustable-results-neural/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/3/) / Stronger Baselines for Trustable Results in Neural Machine Translation

# Stronger Baselines for Trustable Results in Neural Machine Translation

**Authors:** [Michael Denkowski](https://md.research.elamur.ai/free/en/authors/michael-denkowski/), [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/) · **Year:** 2017 · **Venue:** Proceedings of the First Workshop on Neural Machine Translation · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/W17-3203/) · [PDF](https://aclanthology.org/W17-3203.pdf) · [DOI 10.18653/v1/w17-3203](https://doi.org/10.18653/v1/w17-3203) · [OpenAlex](https://openalex.org/W2725082186)

**Citations:** 108 citations (openalex-snapshot · 2026-10-14) · [56](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
NMT papers often report gains over weak "vanilla" systems, so it is unclear whether a new method would still help a production-grade model. Denkowski and Neubig propose three easy-to-adopt upgrades for experimental baselines. The first is Adam training with learning-rate halving and optimizer restarts. The second is sub-word vocabularies built with byte pair encoding (BPE). The third is decoding with ensembles of independently trained models. They use an attentional encoder-decoder built with Lamtram and DyNet and test it on five WMT16 and IWSLT16 translation scenarios, with training sets from about 114K to 4.5M sentence pairs. BLEU is averaged over several training runs. Combined, the upgrades add roughly 4–5 BLEU in every scenario. The authors then re-test four published extensions: lexicon bias, pre-translation, data bootstrapping and dropout. Gains seen on vanilla systems often shrink, disappear or reverse on the stronger baselines. The study shows that baseline strength can change experimental conclusions, and it urges researchers to evaluate new ideas on realistic systems.

## Key points
- **Data:** The scenarios are WMT German-English (4.56M sentences), English-Finnish (2.08M) and Romanian-English (612K), plus IWSLT English-French (220K) and Czech-English (114K, TED talks).
- **Baseline model:** A bi-directional single-layer LSTM (size 1024) with MLP attention, 512-dimensional embeddings and a 50K-word vocabulary. Unknown words are handled by a fast_align dictionary lookup or by copying the source word.
- **Training:** Adam (max step 0.0002) with only 2 restarts plus SGD-style annealing trained faster than fully annealed SGD (initial rate 0.5, 5 halvings). It also reached lower dev perplexity and higher BLEU. Restarting resets Adam's per-parameter rates, which helps it leave poor local optima.
- **Re-tested extensions:** Of the four extensions, only data bootstrapping (with a phrase-based re-segmentation extension) improved the fully strengthened systems in both evaluated scenarios, and only marginally. Lexicon bias and pre-translation became redundant or harmful and reduced ensemble diversity.
- **Dropout:** Dropout still helped all configurations for Czech-English, but stronger English-French systems needed it less.

*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/en/shelves/linguistics/) · [Machine translation](https://md.research.elamur.ai/free/en/shelves/machine-translation/)

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

## Cited by

Cited by

56 papers of our library cite it (of the 140673 whose bibliographies we read); 6 of them have a page here, 50 not yet.

- [The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/chen-2018-best-both-worlds-combining-recent/)
- [A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing](https://md.research.elamur.ai/free/en/papers/kobayashi-2022-simple-strong-baseline-end-end/)
- [An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution](https://md.research.elamur.ai/free/en/papers/konno-2020-empirical-study-contextual-data-augmentation/)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://md.research.elamur.ai/free/en/papers/kudo-2018-sentencepiece-simple-language-independent-subword/)
- [Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations](https://md.research.elamur.ai/free/en/papers/noord-2017-neural-semantic-parsing-character-based/)
- [When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation?](https://md.research.elamur.ai/free/en/papers/qi-2018-when-why-are-pre-trained/)

## Cite

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

```bibtex
@inproceedings{denkowski2017stronger,
  title = {{Stronger Baselines for Trustable Results in Neural Machine Translation}},
  author = {Denkowski, Michael and Neubig, Graham},
  booktitle = {Proceedings of the First Workshop on Neural Machine Translation},
  year = {2017},
  doi = {10.18653/v1/w17-3203},
  url = {https://doi.org/10.18653/v1/w17-3203}
}
```

- [← previous Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task](https://md.research.elamur.ai/free/en/papers/ud-2017-dozat-stanford-s-graph-based-neural/)
- [next → Style Transfer from Non-Parallel Text by Cross-Alignment](https://md.research.elamur.ai/free/en/papers/shen-2017-style-transfer-non-parallel-text/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/3/)

## References

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

1. pure neural machine translation systems. abs/1610.05540. — [arXiv:1610.05540](https://arxiv.org/abs/1610.05540) [find](https://scholar.google.com/scholar?q=pure+neural+machine+translation+systems%2E+abs%2F1610%2E05540%2E+%E2%80%94+%5BarXiv%3A1610%2E05540%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1610%2E05540%29)
2. Philip Arthur, Graham Neubig, and Satoshi Nakamura. 2016. Incorporating discrete translation lexicons into neural machine translation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Austin, Texas, pages 1557–1567. [find](https://scholar.google.com/scholar?q=Philip+Arthur%2C+Graham+Neubig%2C+and+Satoshi+Nakamura%2E+2016%2E+Incorporating+discrete+translation+lexicons+into+neural+machine+translation%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+in+Nat)
3. CoRR Chris Dyer, Victor Chahuneau, and Noah A. Smith. 2013. A simple, fast, and effective reparameterization of ibm model 2. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pages 644–648. [find](https://scholar.google.com/scholar?q=CoRR+Chris+Dyer%2C+Victor+Chahuneau%2C+and+Noah+A%2E+Smith%2E+2013%2E+A+simple%2C+fast%2C+and+effective+reparameterization+of+ibm+model+2%2E+In+Proceedings+of+the+2013+Conference+of+the+North+American+Chapter+of+the+)
4. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Dzmitry+Bahdanau%2C+Kyunghyun+Cho%2C+and+Yoshua+Bengio%2E+2015%2E+Neural+machine+translation+by+jointly+learning+to+align+and+translate%2E+In+International+Conference+on+Learning+Representations%2E) [our card](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/)
5. M Amin Farajian, Rajen Chatterjee, Costanza Conforti, Shahab Jalalvand, Vevake Balaraman, Mattia A Di Gangi, Duygu Ataman, Marco Turchi, Matteo Negri, and Marcello Federico. 2016. Fbks neural machine translation systems for iwslt 2016. In Proceedings of the ninth International Workshop on Spoken Lan… [find](https://scholar.google.com/scholar?q=M+Amin+Farajian%2C+Rajen+Chatterjee%2C+Costanza+Conforti%2C+Shahab+Jalalvand%2C+Vevake+Balaraman%2C+Mattia+A+Di+Gangi%2C+Duygu+Ataman%2C+Marco+Turchi%2C+Matteo+Negri%2C+and+Marcello+Federico%2E+2016%2E+Fbks+neural+machine+)
6. Ondřej 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=Ondr%CC%8Cej+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+M) [our card](https://md.research.elamur.ai/free/en/papers/bojar-2016-findings-2016-conference-machine-translation/)
7. Yarin Gal and Zoubin Ghahramani. 2016. A theoretically grounded application of dropout in recurrent neural networks. In D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett, editors, Advances in Neural Information Processing Systems 29, Curran Associates, Inc., pages 1019–1027. [find](https://scholar.google.com/scholar?q=Yarin+Gal+and+Zoubin+Ghahramani%2E+2016%2E+A+theoretically+grounded+application+of+dropout+in+recurrent+neural+networks%2E+In+D%2E+D%2E+Lee%2C+M%2E+Sugiyama%2C+U%2E+V%2E+Luxburg%2C+I%2E+Guyon%2C+and+R%2E+Garnett%2C+editors%2C+Advanc) [our card](https://md.research.elamur.ai/free/en/papers/gal-2015-theoretically-grounded-application-dropout-recurrent/)
8. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 . [find](https://scholar.google.com/scholar?q=Geoffrey+Hinton%2C+Oriol+Vinyals%2C+and+Jeff+Dean%2E+2015%2E+Distilling+the+knowledge+in+a+neural+network%2E+arXiv+preprint+arXiv%3A1503%2E02531+%2E) [our card](https://md.research.elamur.ai/free/en/papers/hinton-2015-distilling-knowledge-neural-network/)
9. Denny Britz, Anna Goldie, Thang Luong, and Quoc Le. 2017. Massive exploration of neural machine translation architectures. arXiv preprint arXiv:1703.03906 . [find](https://scholar.google.com/scholar?q=Denny+Britz%2C+Anna+Goldie%2C+Thang+Luong%2C+and+Quoc+Le%2E+2017%2E+Massive+exploration+of+neural+machine+translation+architectures%2E+arXiv+preprint+arXiv%3A1703%2E03906+%2E)
10. Sébastien Jean, Kyunghyun Cho, Roland Memisevic, and Yoshua Bengio. 2015. On using very large target vocabulary for neural machine translation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language P… [find](https://scholar.google.com/scholar?q=Se%CC%81bastien+Jean%2C+Kyunghyun+Cho%2C+Roland+Memisevic%2C+and+Yoshua+Bengio%2E+2015%2E+On+using+very+large+target+vocabulary+for+neural+machine+translation%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+Associ) [our card](https://md.research.elamur.ai/free/en/papers/jean-2015-very-large-target-vocabulary-neural/)
11. M Cettolo, J Niehues, S Stüker, L Bentivogli, R Cattoni, and M Federico. 2016. The iwslt 2016 evaluation campaign . [find](https://scholar.google.com/scholar?q=M+Cettolo%2C+J+Niehues%2C+S+Stu%CC%88ker%2C+L+Bentivogli%2C+R+Cattoni%2C+and+M+Federico%2E+2016%2E+The+iwslt+2016+evaluation+campaign+%2E)
12. Mauro Cettolo, Christian Girardi, and Marcello Federico. 2012. Wit 3 : Web inventory of transcribed and translated talks. In Proceedings of the 16 th Conference of the European Association for Machine Translation (EAMT). Trento, Italy, pages 261–268. [find](https://scholar.google.com/scholar?q=Mauro+Cettolo%2C+Christian+Girardi%2C+and+Marcello+Federico%2E+2012%2E+Wit+3+%3A+Web+inventory+of+transcribed+and+translated+talks%2E+In+Proceedings+of+the+16+th+Conference+of+the+European+Association+for+Machine)
13. Yoon Kim and Alexander M. Rush. 2016. Sequence-level knowledge distillation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Austin, Texas, pages 1317–1327. [find](https://scholar.google.com/scholar?q=Yoon+Kim+and+Alexander+M%2E+Rush%2E+2016%2E+Sequence%2Dlevel+knowledge+distillation%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2E+Association+for+Computational+Li) [our card](https://md.research.elamur.ai/free/en/papers/kim-2016-sequence-level-knowledge-distillation/)
14. Wenhu Chen, Evgeny Matusov, Shahram Khadivi, and Jan-Thorsten Peter. 2016. Guided alignment training for topic-aware neural machine translation. [find](https://scholar.google.com/scholar?q=Wenhu+Chen%2C+Evgeny+Matusov%2C+Shahram+Khadivi%2C+and+Jan%2DThorsten+Peter%2E+2016%2E+Guided+alignment+training+for+topic%2Daware+neural+machine+translation%2E)
15. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Diederik+P%2E+Kingma+and+Jimmy+Ba%2E+2015%2E+Adam%3A+A+method+for+stochastic+optimization%2E+In+Proceedings+of+the+3rd+International+Conference+on+Learning+Representations+%28ICLR%29%2E)
16. Jonathan H. Clark, Chris Dyer, Alon Lavie, and Noah A. Smith. 2011. 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. pages 176… [find](https://scholar.google.com/scholar?q=Jonathan+H%2E+Clark%2C+Chris+Dyer%2C+Alon+Lavie%2C+and+Noah+A%2E+Smith%2E+2011%2E+Better+hypothesis+testing+for+statistical+machine+translation%3A+Controlling+for+optimizer+instability%2E+In+Proceedings+of+the+49th+Ann)
17. Adhiguna Kuncoro, Miguel Ballesteros, Lingpeng Kong, Chris Dyer, and Noah A. Smith. 2016. Distilling an ensemble of greedy dependency parsers into one mst parser. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Aus… [find](https://scholar.google.com/scholar?q=Adhiguna+Kuncoro%2C+Miguel+Ballesteros%2C+Lingpeng+Kong%2C+Chris+Dyer%2C+and+Noah+A%2E+Smith%2E+2016%2E+Distilling+an+ensemble+of+greedy+dependency+parsers+into+one+mst+parser%2E+In+Proceedings+of+the+2016+Conference)
18. Josep Crego, Jungi Kim, Guillaume Klein, Anabel Rebollo, Kathy Yang, Jean Senellart, Egor Akhanov, Patrice Brunelle, Aurelien Coquard, Yongchao Deng, Satoshi Enoue, Chiyo Geiss, Joshua Johanson, Ardas Khalsa, Raoum Khiari, Byeongil Ko, Catherine Kobus, Jean Lorieux, Leidiana Martins, Dang-Chuan Nguy… [find](https://scholar.google.com/scholar?q=Josep+Crego%2C+Jungi+Kim%2C+Guillaume+Klein%2C+Anabel+Rebollo%2C+Kathy+Yang%2C+Jean+Senellart%2C+Egor+Akhanov%2C+Patrice+Brunelle%2C+Aurelien+Coquard%2C+Yongchao+Deng%2C+Satoshi+Enoue%2C+Chiyo+Geiss%2C+Joshua+Johanson%2C+Ardas)
19. SYSTRAN’s Jason Lee, Kyunghyun Cho, and Thomas Hofmann. 2016. Fully character-level neural machine translation without explicit segmentation. CoRR abs/1610.03017. [find](https://scholar.google.com/scholar?q=SYSTRAN%E2%80%99s+Jason+Lee%2C+Kyunghyun+Cho%2C+and+Thomas+Hofmann%2E+2016%2E+Fully+character%2Dlevel+neural+machine+translation+without+explicit+segmentation%2E+CoRR+abs%2F1610%2E03017%2E) [our card](https://md.research.elamur.ai/free/en/papers/lee-2017-fully-character-level-neural-machine/)
20. Thang Luong, Ilya Sutskever, Quoc Le, Oriol Vinyals, and Wojciech Zaremba. 2015. Addressing the rare 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, Lu… [find](https://scholar.google.com/scholar?q=Thang+Luong%2C+Ilya+Sutskever%2C+Quoc+Le%2C+Oriol+Vinyals%2C+and+Wojciech+Zaremba%2E+2015%2E+Addressing+the+rare+Yonghui+Wu%2C+Mike+Schuster%2C+Zhifeng+Chen%2C+Quoc+V%2E+Le%2C+Mohammad+Norouzi%2C+Wolfgang+Macherey%2C+Maxim+Kri)
21. Graham Neubig. 2015. lamtram: A toolkit for language and translation modeling using neural networks. [http://www.github.com/neubig/lamtram](http://www.github.com/neubig/lamtram). [↗](http://www.github.com/neubig/lamtram)
22. Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Pau… [find](https://scholar.google.com/scholar?q=Graham+Neubig%2C+Chris+Dyer%2C+Yoav+Goldberg%2C+Austin+Matthews%2C+Waleed+Ammar%2C+Antonios+Anastasopoulos%2C+Miguel+Ballesteros%2C+David+Chiang%2C+Daniel+Clothiaux%2C+Trevor+Cohn%2C+Kevin+Duh%2C+Manaal+Faruqui%2C+Cynthia+Ga) [our card](https://md.research.elamur.ai/free/en/papers/neubig-2017-dynet-dynamic-neural-network-toolkit/)
23. Matthew D. Zeiler. 2012. ADADELTA: an adaptive learning rate method. CoRR abs/1212.5701. [find](https://scholar.google.com/scholar?q=Matthew+D%2E+Zeiler%2E+2012%2E+ADADELTA%3A+an+adaptive+learning+rate+method%2E+CoRR+abs%2F1212%2E5701%2E) [our card](https://md.research.elamur.ai/free/en/papers/zeiler-2012-adadelta-adaptive-learning-rate-method/)
24. Jan Niehues, Eunah Cho, Thanh-Le Ha, and Alex Waibel. 2016. Pre-translation for neural machine translation. CoRR abs/1610.05243. [find](https://scholar.google.com/scholar?q=Jan+Niehues%2C+Eunah+Cho%2C+Thanh%2DLe+Ha%2C+and+Alex+Waibel%2E+2016%2E+Pre%2Dtranslation+for+neural+machine+translation%2E+CoRR+abs%2F1610%2E05243%2E)
25. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, pages… [find](https://scholar.google.com/scholar?q=Kishore+Papineni%2C+Salim+Roukos%2C+Todd+Ward%2C+and+Wei%2DJing+Zhu%2E+2002%2E+Bleu%3A+a+method+for+automatic+evaluation+of+machine+translation%2E+In+Proceedings+of+40th+Annual+Meeting+of+the+Association+for+Computat) [our card](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
26. Rico Sennrich, Orhan Firat, Kyunghyun Cho, Alexandra Birch, Barry Haddow, Julian Hitschler, Marcin Junczys-Dowmunt, Samuel Läubli, Antonio Valerio Miceli Barone, Jozef Mokry, and Maria Nadejde. 2017. Nematus: a Toolkit for Neural Machine Translation. In Proceedings of the Demonstrations at the 15th… [find](https://scholar.google.com/scholar?q=Rico+Sennrich%2C+Orhan+Firat%2C+Kyunghyun+Cho%2C+Alexandra+Birch%2C+Barry+Haddow%2C+Julian+Hitschler%2C+Marcin+Junczys%2DDowmunt%2C+Samuel+La%CC%88ubli%2C+Antonio+Valerio+Miceli+Barone%2C+Jozef+Mokry%2C+and+Maria+Nadejde%2E+2017%2E) [our card](https://md.research.elamur.ai/free/en/papers/sennrich-2017-nematus-toolkit-neural-machine-translation/)
27. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016a. Edinburgh neural machine translation systems for wmt 16. In Proceedings of the First Conference on Machine Translation. Association for Computational Linguistics, Berlin, Germany, pages 371– 376. [find](https://scholar.google.com/scholar?q=Rico+Sennrich%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+2016a%2E+Edinburgh+neural+machine+translation+systems+for+wmt+16%2E+In+Proceedings+of+the+First+Conference+on+Machine+Translation%2E+Association+for+Computa) [our card](https://md.research.elamur.ai/free/en/papers/sennrich-2016-edinburgh-neural-machine-translation-systems/)
28. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016b. 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). Association for Computational Linguistics, Berlin, Germany, pages… [find](https://scholar.google.com/scholar?q=Rico+Sennrich%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+2016b%2E+Neural+machine+translation+of+rare+words+with+subword+units%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Computational+Lin)
29. Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. pages 3104–3112. [find](https://scholar.google.com/scholar?q=Ilya+Sutskever%2C+Oriol+Vinyals%2C+and+Quoc+V+Le%2E+2014%2E+Sequence+to+sequence+learning+with+neural+networks%2E+In+Advances+in+neural+information+processing+systems%2E+pages+3104%E2%80%933112%2E)