We present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations. This is done in a self-supervised way without parallel data, in such a way that both tasks enhance each other during training. The method is language independent, introduces no additional hyper-parameters, and achieves BLEU scores of 29.21 (en2fr) and 27.36 (fr2en) on newstest2014 using English and French Wikipedia data for training.
Dana Ruiter, Cristina España-Bonet, and Josef van Genabith. 2019.Self-Supervised Neural Machine Translation. InProceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1828–1834, Florence, Italy. Association for Computational Linguistics.
@inproceedings{ruiter-etal-2019-self, title = "Self-Supervised Neural Machine Translation", author = "Ruiter, Dana and Espa{\~n}a-Bonet, Cristina and van Genabith, Josef", editor = "Korhonen, Anna and Traum, David and M{\`a}rquez, Llu{\'i}s", booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics", month = jul, year = "2019", address = "Florence, Italy", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/P19-1178/", doi = "10.18653/v1/P19-1178", pages = "1828--1834", abstract = "We present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations. This is done in a self-supervised way without parallel data, in such a way that both tasks enhance each other during training. The method is language independent, introduces no additional hyper-parameters, and achieves BLEU scores of 29.21 (en2fr) and 27.36 (fr2en) on newstest2014 using English and French Wikipedia data for training."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="ruiter-etal-2019-self"> <titleInfo> <title>Self-Supervised Neural Machine Translation</title> </titleInfo> <name type="personal"> <namePart type="given">Dana</namePart> <namePart type="family">Ruiter</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Cristina</namePart> <namePart type="family">España-Bonet</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Josef</namePart> <namePart type="family">van Genabith</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2019-07</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title> </titleInfo> <name type="personal"> <namePart type="given">Anna</namePart> <namePart type="family">Korhonen</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">David</namePart> <namePart type="family">Traum</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Lluís</namePart> <namePart type="family">Màrquez</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Florence, Italy</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>We present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations. This is done in a self-supervised way without parallel data, in such a way that both tasks enhance each other during training. The method is language independent, introduces no additional hyper-parameters, and achieves BLEU scores of 29.21 (en2fr) and 27.36 (fr2en) on newstest2014 using English and French Wikipedia data for training.</abstract> <identifier type="citekey">ruiter-etal-2019-self</identifier> <identifier type="doi">10.18653/v1/P19-1178</identifier> <location> <url>https://aclanthology.org/P19-1178/</url> </location> <part> <date>2019-07</date> <extent unit="page"> <start>1828</start> <end>1834</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Self-Supervised Neural Machine Translation%A Ruiter, Dana%A España-Bonet, Cristina%A van Genabith, Josef%Y Korhonen, Anna%Y Traum, David%Y Màrquez, Lluís%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics%D 2019%8 July%I Association for Computational Linguistics%C Florence, Italy%F ruiter-etal-2019-self%X We present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations. This is done in a self-supervised way without parallel data, in such a way that both tasks enhance each other during training. The method is language independent, introduces no additional hyper-parameters, and achieves BLEU scores of 29.21 (en2fr) and 27.36 (fr2en) on newstest2014 using English and French Wikipedia data for training.%R 10.18653/v1/P19-1178%U https://aclanthology.org/P19-1178/%U https://doi.org/10.18653/v1/P19-1178%P 1828-1834
Dana Ruiter, Cristina España-Bonet, and Josef van Genabith. 2019.Self-Supervised Neural Machine Translation. InProceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1828–1834, Florence, Italy. Association for Computational Linguistics.