@article{koehn2005europarl, title={Europarl: A parallel corpus for statistical machine translation}, author={Koehn, Philipp}, journal={Proc. 10th Machine Translation Summit (MT Summit), 2005}, pages={79--86}, year={2005} } @misc{neubig11kftt, author = {Graham Neubig}, title = {The {Kyoto} Free Translation Task}, howpublished = "http://www.phontron.com/kftt", year = {2011} } @inproceedings{tiedemann-2012-parallel, title = "Parallel Data, Tools and Interfaces in {OPUS}", author = {Tiedemann, J{\"o}rg}, booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)", month = may, year = "2012", address = "Istanbul, Turkey", publisher = "European Language Resources Association (ELRA)", url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/463_Paper.pdf", pages = "2214--2218", } @inproceedings{post-etal-2012-constructing, title = "Constructing Parallel Corpora for Six {I}ndian Languages via Crowdsourcing", author = "Post, Matt and Callison-Burch, Chris and Osborne, Miles", booktitle = "Proceedings of the Seventh Workshop on Statistical Machine Translation", month = jun, year = "2012", address = "Montr{\'e}al, Canada", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/W12-3152", pages = "401--409", } @inproceedings{ziemski-etal-2016-unpc, title = "The United Nations Parallel Corpus v1.0", author = "Ziemski, Micha{\l} and Junczys-Dowmunt, Marcin and Pouliquen, Bruno", booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)", month = may, year = "2016", address = "Portoro{\v{z}}, Slovenia", publisher = "European Language Resources Association (ELRA)", url = "https://www.aclweb.org/anthology/L16-1561", pages = "3530--3534", } @inproceedings{rozis-skadins-2017-tilde, title = "Tilde {MODEL} - Multilingual Open Data for {EU} Languages", author = "Rozis, Roberts and Skadi{\c{n}}{\v{s}}, Raivis", booktitle = "Proceedings of the 21st Nordic Conference on Computational Linguistics", month = may, year = "2017", address = "Gothenburg, Sweden", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/W17-0235", pages = "263--265", } @inproceedings{kunchukuttan-etal-2018-iit, title = "The {IIT} {B}ombay {E}nglish-{H}indi Parallel Corpus", author = "Kunchukuttan, Anoop and Mehta, Pratik and Bhattacharyya, Pushpak", booktitle = "Proceedings of the Eleventh International Conference on Language Resources and Evaluation ({LREC} 2018)", month = may, year = "2018", address = "Miyazaki, Japan", publisher = "European Language Resources Association (ELRA)", url = "https://www.aclweb.org/anthology/L18-1548", } @inproceedings{agic-vulic-2019-jw300, title = "{JW}300: A Wide-Coverage Parallel Corpus for Low-Resource Languages", author = "Agi{\'c}, {\v{Z}}eljko and Vuli{\'c}, Ivan", 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://www.aclweb.org/anthology/P19-1310", doi = "10.18653/v1/P19-1310", pages = "3204--3210", } @inproceedings{espla-etal-2019-paracrawl, title = "{P}ara{C}rawl: Web-scale parallel corpora for the languages of the {EU}", author = "Espl{\`a}, Miquel and Forcada, Mikel and Ram{\'\i}rez-S{\'a}nchez, Gema and Hoang, Hieu", booktitle = "Proceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks", month = aug, year = "2019", address = "Dublin, Ireland", publisher = "European Association for Machine Translation", url = "https://www.aclweb.org/anthology/W19-6721", pages = "118--119", } @inproceedings{qi-etal-2018-pretrainemb, title = "When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation?", author = "Qi, Ye and Sachan, Devendra and Felix, Matthieu and Padmanabhan, Sarguna and Neubig, Graham", booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)", month = jun, year = "2018", address = "New Orleans, Louisiana", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/N18-2084", doi = "10.18653/v1/N18-2084", pages = "529--535", } @misc{haddow2020pmindia, title={PMIndia -- A Collection of Parallel Corpora of Languages of India}, author={Barry Haddow and Faheem Kirefu}, year={2020}, eprint={2001.09907}, archivePrefix={arXiv}, primaryClass={cs.CL} } @article{schwenk-etal-2019-wikimatrixv1, author = {Holger Schwenk and Vishrav Chaudhary and Shuo Sun and Hongyu Gong and Francisco Guzm{\'{a}}n}, title = {WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia}, journal = {CoRR}, volume = {abs/1907.05791}, year = {2019}, url = {http://arxiv.org/abs/1907.05791}, archivePrefix = {arXiv}, eprint = {1907.05791}, timestamp = {Wed, 17 Jul 2019 10:27:36 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1907-05791.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } @inproceedings{zhang-etal-2020-multiling-nmt, title = "Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation", author = "Zhang, Biao and Williams, Philip and Titov, Ivan and Sennrich, Rico", booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", month = jul, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.acl-main.148", pages = "1628--1639", } @inproceedings{bojar-etal-2013-findings, title = "Findings of the 2013 {W}orkshop on {S}tatistical {M}achine {T}ranslation", author = "Bojar, Ond{\v{r}}ej and Buck, Christian and Callison-Burch, Chris and Federmann, Christian and Haddow, Barry and Koehn, Philipp and Monz, Christof and Post, Matt and Soricut, Radu and Specia, Lucia", booktitle = "Proceedings of the Eighth Workshop on Statistical Machine Translation", month = aug, year = "2013", address = "Sofia, Bulgaria", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/W13-2201", pages = "1--44", } @inproceedings{bojar-etal-2014-findings, title = "Findings of the 2014 Workshop on Statistical Machine Translation", author = "Bojar, Ond{\v{r}}ej and Buck, Christian and Federmann, Christian and Haddow, Barry and Koehn, Philipp and Leveling, Johannes and Monz, Christof and Pecina, Pavel and Post, Matt and Saint-Amand, Herve and Soricut, Radu and Specia, Lucia and Tamchyna, Ale{\v{s}}", booktitle = "Proceedings of the Ninth Workshop on Statistical Machine Translation", month = jun, year = "2014", address = "Baltimore, Maryland, USA", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/W14-3302", doi = "10.3115/v1/W14-3302", pages = "12--58", } @inproceedings{bojar-etal-2015-findings, title = "Findings of the 2015 Workshop on Statistical Machine Translation", author = "Bojar, Ond{\v{r}}ej and Chatterjee, Rajen and Federmann, Christian and Haddow, Barry and Huck, Matthias and Hokamp, Chris and Koehn, Philipp and Logacheva, Varvara and Monz, Christof and Negri, Matteo and Post, Matt and Scarton, Carolina and Specia, Lucia and Turchi, Marco", booktitle = "Proceedings of the Tenth Workshop on Statistical Machine Translation", month = sep, year = "2015", address = "Lisbon, Portugal", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/W15-3001", doi = "10.18653/v1/W15-3001", pages = "1--46", } @inproceedings{bojar-etal-2016-findings, title = "Findings of the 2016 Conference on Machine Translation", author = "Bojar, Ond{\v{r}}ej and Chatterjee, Rajen and Federmann, Christian and Graham, Yvette and Haddow, Barry and Huck, Matthias and Jimeno Yepes, Antonio and Koehn, Philipp and Logacheva, Varvara and Monz, Christof and Negri, Matteo and N{\'e}v{\'e}ol, Aur{\'e}lie and Neves, Mariana and Popel, Martin and Post, Matt and Rubino, Raphael and Scarton, Carolina and Specia, Lucia and Turchi, Marco and Verspoor, Karin and Zampieri, Marcos", booktitle = "Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers", month = aug, year = "2016", address = "Berlin, Germany", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/W16-2301", doi = "10.18653/v1/W16-2301", pages = "131--198", } @inproceedings{bojar-etal-2017-findings, title = "Findings of the 2017 Conference on Machine Translation ({WMT}17)", author = "Bojar, Ond{\v{r}}ej and Chatterjee, Rajen and Federmann, Christian and Graham, Yvette and Haddow, Barry and Huang, Shujian and Huck, Matthias and Koehn, Philipp and Liu, Qun and Logacheva, Varvara and Monz, Christof and Negri, Matteo and Post, Matt and Rubino, Raphael and Specia, Lucia and Turchi, Marco", booktitle = "Proceedings of the Second Conference on Machine Translation", month = sep, year = "2017", address = "Copenhagen, Denmark", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/W17-4717", doi = "10.18653/v1/W17-4717", pages = "169--214", } @inproceedings{bojar-etal-2018-findings, title = "Findings of the 2018 Conference on Machine Translation ({WMT}18)", author = "Bojar, Ond{\v{r}}ej and Federmann, Christian and Fishel, Mark and Graham, Yvette and Haddow, Barry and Koehn, Philipp and Monz, Christof", booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers", month = oct, year = "2018", address = "Belgium, Brussels", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/W18-6401", doi = "10.18653/v1/W18-6401", pages = "272--303", } @inproceedings{barrault-etal-2019-findings, title = "Findings of the 2019 Conference on Machine Translation ({WMT}19)", author = {Barrault, Lo{\"\i}c and Bojar, Ond{\v{r}}ej and Costa-juss{\`a}, Marta R. and Federmann, Christian and Fishel, Mark and Graham, Yvette and Haddow, Barry and Huck, Matthias and Koehn, Philipp and Malmasi, Shervin and Monz, Christof and M{\"u}ller, Mathias and Pal, Santanu and Post, Matt and Zampieri, Marcos}, booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)", month = aug, year = "2019", address = "Florence, Italy", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/W19-5301", doi = "10.18653/v1/W19-5301", pages = "1--61", } @inproceedings{barrault-etal-2020-findings, title = "Findings of the 2020 Conference on Machine Translation ({WMT}20)", author = {Barrault, Lo{\"\i}c and Biesialska, Magdalena and Bojar, Ond{\v{r}}ej and Costa-juss{\`a}, Marta R. and Federmann, Christian and Graham, Yvette and Grundkiewicz, Roman and Haddow, Barry and Huck, Matthias and Joanis, Eric and Kocmi, Tom and Koehn, Philipp and Lo, Chi-kiu and Ljube{\v{s}}i{\'c}, Nikola and Monz, Christof and Morishita, Makoto and Nagata, Masaaki and Nakazawa, Toshiaki and Pal, Santanu and Post, Matt and Zampieri, Marcos}, booktitle = "Proceedings of the Fifth Conference on Machine Translation", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.wmt-1.1", pages = "1--55", }