---
title: "The SADID Evaluation Datasets for Low-Resource — Abid 2020"
description: "Arabic dialects are mostly spoken and have no standard spelling."
authors: ["Wael Abid"]
year: 2020
venue: "Proceedings of the 28th International Conference on Computational Linguistics"
source: "https://aclanthology.org/2020.coling-main.530/"
doi: "10.18653/v1/2020.coling-main.530"
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/abid-2020-sadid-evaluation-datasets-low-resource/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/abid-2020-sadid-evaluation-datasets-low-resource/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2020](https://md.research.elamur.ai/free/en/papers/2020/page/6/) / The SADID Evaluation Datasets for Low-Resource Spoken Language Machine Translation of Arabic Dialects

# The SADID Evaluation Datasets for Low-Resource Spoken Language Machine Translation of Arabic Dialects

**Authors:** Wael Abid · **Year:** 2020 · **Venue:** Proceedings of the 28th International Conference on Computational Linguistics · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2020.coling-main.530/) · [PDF](https://aclanthology.org/2020.coling-main.530.pdf) · [DOI 10.18653/v1/2020.coling-main.530](https://doi.org/10.18653/v1/2020.coling-main.530) · [OpenAlex](https://openalex.org/W3114901634)

**Citations:** 8 citations (openalex-snapshot · 2026-10-14) · [9](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Arabic dialects are mostly spoken and have no standard spelling. Public test data for translating them has been scarce, which makes results hard to compare or reproduce. The author builds SADID, a freely released 4-way evaluation benchmark covering Egyptian, Levantine, MSA and English, split into dev, devtest and blind test portions. The English source text comes from three places. Native speakers were surveyed on the topics they discuss in dialect, and the sources were picked to match those everyday subjects: Simple Wikipedia filtered against technical vocabulary, Cornell Movie Dialogs Corpus, and lightly simplified Aesop Fables. Three professional translators per variety, each from a different city, produced the translations, and two native raters screened every output. The paper also tests state-of-the-art MT baselines and unsupervised segmentation settings. It proposes "bootstrapping," a language-agnostic augmentation that reuses only the existing parallel data. The best results come from a multilingual model that combines dialects, MSA and bootstrapping. The benchmark's built-in diversity of domains and translators also shows how fragile these systems are.

## Key points
- **Topic survey:** 65 native speakers from 6 countries were asked which topics they discuss in dialect and where they switch or borrow from another language. Highly technical subjects were the main cases for switching.
- **Source selection:**
  - A Simple Wikipedia dump from April 2020 (160,935 articles) was cut to 5,263 sentences from 2,365 articles, using tf-idf filtering, length limits and character limits.
  - That subsample was then checked by hand.
  - Movie dialogs were kept only if they had at least 6 sentences and no profanity.
- **Translators by city:** Egyptian translators came from Cairo, Alexandria and Qena. Levantine translators came from Nablus, Gaza and Khan Yunis.
- **Quality control:** Raters scored meaning preservation and naturalness on a 1–20 scale. Any score below 15 sent the sentence back for re-translation.
- **Results by domain (LEV-ENG test: 886 subtitle, 833 fable and 1,275 Wikipedia sentences):**
  - Bootstrapping raised overall BLEU from 12.66 to 13.77, with gains on every subset.
  - Back-translation reached 14.94 overall, mainly from a 19.40 score on Wikipedia, but fell below the baseline on subtitles and fables.
- **Multilingual training and city effects:**
  - Adding MSA to a dialect-only multilingual model added 3.76–4.18 BLEU in the dialect→English direction.
  - The baseline ENG-EGY system scored lowest on the Qena translator's output.

## Interesting ideas
- Splitting the test set by source genre and reporting BLEU per slice showed that back-translation's overall gain came from one domain and hid losses on the others. — For Mova (learn): Evaluation reports could always break scores down by text genre (fables, school texts, encyclopedic prose), so that a repair rule or teacher tier that helps only one genre is caught before adoption.
- Hiring several annotators from different cities and scoring the system against each one separately turns annotator variation into a measurable robustness signal. — For Mova (tree): When building or converting treebanks, keeping per-annotator or per-source subsets would let us check whether the parser is overfitted to one annotation habit or dialect convention.
- Each item was gated on two separate criteria, faithfulness and naturalness, and anything below threshold on either one went back for rework. — For Mova (learn): Silver data from witness parsers or LLM teachers could be accepted only when it passes two separate checks, such as structural agreement and semantic plausibility, with rejected items queued for repair.
- Writing the source text in a pivot language rather than in one of the target varieties keeps the translations from inheriting that variety's expressions. — For Mova (back): For translation through the meta-world, reference texts should be generated from the meaning graph or a neutral source, so that evaluation is not biased toward one surface language.
- Fables were lightly simplified into a more conversational style, and encyclopedic sentences dense with technical terms were dropped using tf-idf. This keeps the test material close to everyday language. — For Mova (answer): Fable and tale QA sets could be curated the same way, filtering out rare-term-heavy sentences, so that test failures reflect reasoning gaps rather than vocabulary gaps.

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

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

## Cited by

Cited by

9 papers of our library cite it (of the 140884 whose bibliographies we read); 2 of them have a page here, 7 not yet.

- [Jais 2: A Family of Arabic-Centric Open Large Language Models](https://md.research.elamur.ai/free/en/papers/anwar-2026-jais-2-family-arabic-centric/)
- [Ramsa: A Large Sociolinguistically Rich Emirati Arabic Speech Corpus for ASR and TTS](https://md.research.elamur.ai/free/en/papers/sabbagh-2026-ramsa-large-sociolinguistically-rich-emirati/)

## Cite

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

```bibtex
@inproceedings{abid2020sadid,
  title = {{The SADID Evaluation Datasets for Low-Resource Spoken Language Machine Translation of Arabic Dialects}},
  author = {Abid, Wael},
  booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.coling-main.530},
  url = {https://doi.org/10.18653/v1/2020.coling-main.530}
}
```

- [← previous The Pragmatics behind Politics: Modelling Metaphor, Framing and Emotion in Political Discourse](https://md.research.elamur.ai/free/en/papers/cabot-2020-pragmatics-behind-politics-modelling-metaphor/)
- [next → The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://md.research.elamur.ai/free/en/papers/joshi-2020-state-fate-linguistic-diversity-inclusion/)
- [↑ back to papers of 2020](https://md.research.elamur.ai/free/en/papers/2020/page/6/)

## References

26 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Houda Bouamor, Nizar Habash, and Kemal Oflazer. 2014. A multidialectal parallel corpus of Arabic. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 1240– 1245, Reykjavik, Iceland, May. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Houda+Bouamor%2C+Nizar+Habash%2C+and+Kemal+Oflazer%2E+2014%2E+A+multidialectal+parallel+corpus+of+Arabic%2E+In+Proceedings+of+the+Ninth+International+Conference+on+Language+Resources+and+Evaluation+%28LREC%E2%80%9914%29%2C+p) [our card](https://md.research.elamur.ai/free/en/papers/bouamor-2014-multidialectal-parallel-corpus-arabic/)
2. Houda Bouamor, Sabit Hassan, and Nizar Habash. 2019. The MADAR shared task on Arabic fine-grained dialect identification. In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 199–207, Florence, Italy, August. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Houda+Bouamor%2C+Sabit+Hassan%2C+and+Nizar+Habash%2E+2019%2E+The+MADAR+shared+task+on+Arabic+fine%2Dgrained+dialect+identification%2E+In+Proceedings+of+the+Fourth+Arabic+Natural+Language+Processing+Workshop%2C+page) [our card](https://md.research.elamur.ai/free/en/papers/bouamor-2019-madar-shared-task-arabic-fine/)
3. J. Cohen. 2007. The gale project: A description and an update. In 2007 IEEE Workshop on Automatic Speech Recognition Understanding (ASRU), pages 237–237. [find](https://scholar.google.com/scholar?q=J%2E+Cohen%2E+2007%2E+The+gale+project%3A+A+description+and+an+update%2E+In+2007+IEEE+Workshop+on+Automatic+Speech+Recognition+Understanding+%28ASRU%29%2C+pages+237%E2%80%93237%2E)
4. Cristian Danescu-Niculescu-Mizil and Lillian Lee. 2011. Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, ACL 2011. [find](https://scholar.google.com/scholar?q=Cristian+Danescu%2DNiculescu%2DMizil+and+Lillian+Lee%2E+2011%2E+Chameleons+in+imagined+conversations%3A+A+new+approach+to+understanding+coordination+of+linguistic+style+in+dialogs%2E+In+Proceedings+of+the+Worksho) [our card](https://md.research.elamur.ai/free/en/papers/mizil-2011-chameleons-imagined-conversations-new-approach/)
5. Shuoyang Ding, Adithya Renduchintala, and Kevin Duh. 2019. A call for prudent choice of subword merge operations in neural machine translation. In Proceedings of Machine Translation Summit XVII Volume 1: Research Track, pages 204–213, Dublin, Ireland, August. European Association for Machine Translation. [find](https://scholar.google.com/scholar?q=Shuoyang+Ding%2C+Adithya+Renduchintala%2C+and+Kevin+Duh%2E+2019%2E+A+call+for+prudent+choice+of+subword+merge+operations+in+neural+machine+translation%2E+In+Proceedings+of+Machine+Translation+Summit+XVII+Volume)
6. Marzieh Fadaee, Arianna Bisazza, and Christof Monz. 2017. Data augmentation for low-resource neural machine translation. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). [find](https://scholar.google.com/scholar?q=Marzieh+Fadaee%2C+Arianna+Bisazza%2C+and+Christof+Monz%2E+2017%2E+Data+augmentation+for+low%2Dresource+neural+machine+translation%2E+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computational+Lin) [our card](https://md.research.elamur.ai/free/en/papers/fadaee-2017-data-augmentation-low-resource-neural/)
7. Charles A Ferguson. 1959. Diglossia, volume 15. Taylor & Francis. [find](https://scholar.google.com/scholar?q=Charles+A+Ferguson%2E+1959%2E+Diglossia%2C+volume+15%2E+Taylor+%26+Francis%2E)
8. Orhan Firat, Kyunghyun Cho, and Yoshua Bengio. 2016. Multi-way, multilingual neural machine translation with a shared attention mechanism. arXiv preprint arXiv:1601.01073. [↗](https://arxiv.org/abs/1601.01073) [our card](https://md.research.elamur.ai/free/en/papers/firat-2016-multi-way-multilingual-neural-machine/)
9. Philip Gage. 1994. A new algorithm for data compression. C Users Journal, 12(2):23–38. [find](https://scholar.google.com/scholar?q=Philip+Gage%2E+1994%2E+A+new+algorithm+for+data+compression%2E+C+Users+Journal%2C+12%282%29%3A23%E2%80%9338%2E)
10. Francisco Guzmán, Peng-Jen Chen, Myle Ott, Juan Pino, Guillaume Lample, Philipp Koehn, Vishrav Chaudhary, and Marc’Aurelio Ranzato. 2019. The FLORES evaluation datasets for low-resource machine translation: Nepali–English and Sinhala–English. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6098–6111, Hong Kong, China, November. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Francisco+Guzma%CC%81n%2C+Peng%2DJen+Chen%2C+Myle+Ott%2C+Juan+Pino%2C+Guillaume+Lample%2C+Philipp+Koehn%2C+Vishrav+Chaudhary%2C+and+Marc%E2%80%99Aurelio+Ranzato%2E+2019%2E+The+FLORES+evaluation+datasets+for+low%2Dresource+machine+trans) [our card](https://md.research.elamur.ai/free/en/papers/guzman-2019-flores-evaluation-datasets-low-resource/)
11. Nizar Habash, Owen Rambow, Mona Diab, and Reem Faraj. 2008. Guidelines for annotation of arabic dialectness. Proceedings of the LREC Workshop on HLT NLP within the Arabic world. [find](https://scholar.google.com/scholar?q=Nizar+Habash%2C+Owen+Rambow%2C+Mona+Diab%2C+and+Reem+Faraj%2E+2008%2E+Guidelines+for+annotation+of+arabic+dialectness%2E+Proceedings+of+the+LREC+Workshop+on+HLT+NLP+within+the+Arabic+world%2E)
12. N.Y. Habash. 2010. Introduction to Arabic Natural Language Processing. Synthesis digital library of engineering and computer science. Morgan & Claypool Publishers. [find](https://scholar.google.com/scholar?q=N%2EY%2E+Habash%2E+2010%2E+Introduction+to+Arabic+Natural+Language+Processing%2E+Synthesis+digital+library+of+engineering+and+computer+science%2E+Morgan+%26+Claypool+Publishers%2E)
13. Melvin Johnson, Mike Schuster, Quoc V Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, et al. 2017. Google’s multilingual neural machine translation system: Enabling zero-shot translation. Transactions of the Association for Computational Linguistics, 5:339–351. [find](https://scholar.google.com/scholar?q=Melvin+Johnson%2C+Mike+Schuster%2C+Quoc+V+Le%2C+Maxim+Krikun%2C+Yonghui+Wu%2C+Zhifeng+Chen%2C+Nikhil+Thorat%2C+Fernanda+Vie%CC%81gas%2C+Martin+Wattenberg%2C+Greg+Corrado%2C+et+al%2E+2017%2E+Google%E2%80%99s+multilingual+neural+machine+tr)
14. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Yoshua Bengio and Yann LeCun, editors, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. [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+Yoshua+Bengio+and+Yann+LeCun%2C+editors%2C+3rd+International+Conference+on+Learning+Representations%2C+ICLR+2015%2C+San+Di)
15. Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, and Marc’Aurelio Ranzato. 2018. Phrase-based & neural unsupervised machine translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 5039–5049, Brussels, Belgium, October-November. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Guillaume+Lample%2C+Myle+Ott%2C+Alexis+Conneau%2C+Ludovic+Denoyer%2C+and+Marc%E2%80%99Aurelio+Ranzato%2E+2018%2E+Phrase%2Dbased+%26+neural+unsupervised+machine+translation%2E+In+Proceedings+of+the+2018+Conference+on+Empirical+)
16. Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, and Luke Zettlemoyer. 2020. Multilingual denoising pre-training for neural machine translation. arXiv preprint arXiv:2001.08210. [↗](https://arxiv.org/abs/2001.08210)
17. Karima Meftouh, Salima Harrat, Salma Jamoussi, Mourad Abbas, and Kamel Smaili. 2015. Machine translation experiments on PADIC: A parallel Arabic DIalect corpus. In Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation, pages 26–34, Shanghai, China, October. [find](https://scholar.google.com/scholar?q=Karima+Meftouh%2C+Salima+Harrat%2C+Salma+Jamoussi%2C+Mourad+Abbas%2C+and+Kamel+Smaili%2E+2015%2E+Machine+translation+experiments+on+PADIC%3A+A+parallel+Arabic+DIalect+corpus%2E+In+Proceedings+of+the+29th+Pacific+Asia)
18. Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, and Michael Auli. 2019. fairseq: A fast, extensible toolkit for sequence modeling. In Proceedings of NAACL-HLT 2019: Demonstrations. [find](https://scholar.google.com/scholar?q=Myle+Ott%2C+Sergey+Edunov%2C+Alexei+Baevski%2C+Angela+Fan%2C+Sam+Gross%2C+Nathan+Ng%2C+David+Grangier%2C+and+Michael+Auli%2E+2019%2E+fairseq%3A+A+fast%2C+extensible+toolkit+for+sequence+modeling%2E+In+Proceedings+of+NAACL%2DHL) [our card](https://md.research.elamur.ai/free/en/papers/ott-2019-fairseq-fast-extensible-toolkit-sequence/)
19. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA, July. Association for Computational Linguistics. [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+the+40th+Annual+Meeting+of+the+Association+for+Comp) [our card](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
20. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016a. 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, August. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Rico+Sennrich%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+2016a%2E+Improving+neural+machine+translation+models+with+monolingual+data%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Computation)
21. 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), pages 1715–1725, Berlin, Germany, August. Association for Computational Linguistics. [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)
22. Toshiyuki Takezawa, Genichiro Kikui, Masahide Mizushima, and Eiichiro Sumita. 2007. Multilingual spoken language corpus development for communication research. In International Journal of Computational Linguistics & Chinese Language Processing, Volume 12, Number 3, September 2007: Special Issue on Invited Papers from ISCSLP 2006, pages 303–324, September. [find](https://scholar.google.com/scholar?q=Toshiyuki+Takezawa%2C+Genichiro+Kikui%2C+Masahide+Mizushima%2C+and+Eiichiro+Sumita%2E+2007%2E+Multilingual+spoken+language+corpus+development+for+communication+research%2E+In+International+Journal+of+Computationa)
23. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems 30, pages 5998–6008. Curran Associates, Inc. [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+ukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+In+I%2E+Guyon%2C+U%2E+V%2E+Luxburg%2C+S%2E+Bengio%2C+H%2E+W)
24. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 353–355, Brussels, Belgium, November. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alex+Wang%2C+Amanpreet+Singh%2C+Julian+Michael%2C+Felix+Hill%2C+Omer+Levy%2C+and+Samuel+Bowman%2E+2018%2E+GLUE%3A+A+multi%2Dtask+benchmark+and+analysis+platform+for+natural+language+understanding%2E+In+Proceedings+of+the) [our card](https://md.research.elamur.ai/free/en/papers/wang-2018-glue-multi-task-benchmark-analysis/)
25. Rabih Zbib, Erika Malchiodi, Jacob Devlin, David Stallard, Spyros Matsoukas, Richard Schwartz, John Makhoul, Omar F. Zaidan, and Chris Callison-Burch. 2012. Machine translation of Arabic dialects. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 49–59, Montréal, Canada, June. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Rabih+Zbib%2C+Erika+Malchiodi%2C+Jacob+Devlin%2C+David+Stallard%2C+Spyros+Matsoukas%2C+Richard+Schwartz%2C+John+Makhoul%2C+Omar+F%2E+Zaidan%2C+and+Chris+Callison%2DBurch%2E+2012%2E+Machine+translation+of+Arabic+dialects%2E+In+) [our card](https://md.research.elamur.ai/free/en/papers/zbib-2012-machine-translation-arabic-dialects/)
26. Barret Zoph, Deniz Yuret, Jonathan May, and Kevin Knight. 2016. Transfer learning for low-resource neural machine translation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1568–1575, Austin, Texas, November. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Barret+Zoph%2C+Deniz+Yuret%2C+Jonathan+May%2C+and+Kevin+Knight%2E+2016%2E+Transfer+learning+for+low%2Dresource+neural+machine+translation%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+in+Natural+Lan)