{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T02:56:19Z","timestamp":1785898579611,"version":"3.56.0"},"reference-count":52,"publisher":"MIT Press - Journals","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Transactions of the Association for Computational Linguistics"],"published-print":{"date-parts":[[2019,11]]},"abstract":"<jats:p> We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts. Our system uses a single BiLSTM encoder with a shared byte-pair encoding vocabulary for all languages, which is coupled with an auxiliary decoder and trained on publicly available parallel corpora. This enables us to learn a classifier on top of the resulting embeddings using English annotated data only, and transfer it to any of the 93 languages without any modification. Our experiments in cross-lingual natural language inference (XNLI data set), cross-lingual document classification (MLDoc data set), and parallel corpus mining (BUCC data set) show the effectiveness of our approach. We also introduce a new test set of aligned sentences in 112 languages, and show that our sentence embeddings obtain strong results in multilingual similarity search even for low- resource languages. Our implementation, the pre-trained encoder, and the multilingual test set are available at https:\/\/github.com\/facebookresearch\/LASER . <\/jats:p>","DOI":"10.1162\/tacl_a_00288","type":"journal-article","created":{"date-parts":[[2019,9,11]],"date-time":"2019-09-11T19:59:46Z","timestamp":1568231986000},"page":"597-610","source":"Crossref","is-referenced-by-count":386,"title":["Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond"],"prefix":"10.1162","volume":"7","author":[{"given":"Mikel","family":"Artetxe","sequence":"first","affiliation":[{"name":"University of the Basque Country (UPV\/EHU)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holger","family":"Schwenk","sequence":"additional","affiliation":[{"name":"Facebook AI Research."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"key":"bib1","author":"Ammar Waleed","year":"2016","journal-title":"CoRR"},{"key":"bib2","first-page":"5012","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence","author":"Artetxe Mikel","year":"2018"},{"key":"bib3","doi-asserted-by":"crossref","first-page":"789","DOI":"10.18653\/v1\/P18-1073","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Artetxe Mikel","year":"2018"},{"key":"bib4","doi-asserted-by":"crossref","first-page":"3632","DOI":"10.18653\/v1\/D18-1399","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Artetxe Mikel","year":"2018"},{"key":"bib5","author":"Artetxe Mikel","year":"2018","journal-title":"CoRR"},{"key":"bib6","doi-asserted-by":"crossref","first-page":"41","DOI":"10.18653\/v1\/W17-2508","volume-title":"Proceedings of the 10th Workshop on Building and Using Comparable Corpora","author":"Azpeitia Andoni","year":"2017"},{"key":"bib7","volume-title":"Proceedings of the 11th Workshop on Building and Using Comparable Corpora","author":"Azpeitia Andoni","year":"2018"},{"key":"bib8","volume-title":"Proceedings of the 11th Workshop on Building and Using Comparable Corpora","author":"Bouamor Houda","year":"2018"},{"key":"bib9","doi-asserted-by":"crossref","first-page":"632","DOI":"10.18653\/v1\/D15-1075","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Bowman Samuel R.","year":"2015"},{"key":"bib10","first-page":"169","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Cer Daniel","year":"2018"},{"key":"bib11","volume-title":"Proceedings of the 11th Workshop on Building and Using Comparable Corpora","author":"Wong Derek F.","year":"2018"},{"key":"bib12","first-page":"670","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Conneau Alexis","year":"2017"},{"key":"bib13","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR 2018)","author":"Conneau Alexis","year":"2018"},{"key":"bib14","doi-asserted-by":"crossref","first-page":"2475","DOI":"10.18653\/v1\/D18-1269","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Conneau Alexis","year":"2018"},{"key":"bib15","first-page":"3079","volume-title":"Advances in Neural Information Processing Systems 28","author":"Dai Andrew M.","year":"2015"},{"key":"bib16","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin Jacob","year":"2019"},{"key":"bib17","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.18653\/v1\/P18-1141","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Dufter Philipp","year":"2018"},{"key":"bib18","doi-asserted-by":"crossref","first-page":"489","DOI":"10.18653\/v1\/D18-1045","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Edunov Sergey","year":"2018"},{"key":"bib19","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1109\/JSTSP.2017.2764273","author":"Espa\u00f1a-Bonet Cristina","year":"2017","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"bib20","first-page":"748","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","volume":"37","author":"Gouws Stephan","year":"2015"},{"key":"bib21","doi-asserted-by":"crossref","first-page":"46","DOI":"10.18653\/v1\/W17-2509","volume-title":"Proceedings of the 10th Workshop on Building and Using Comparable Corpora","author":"Gr\u00e9goire Francis","year":"2017"},{"key":"bib22","first-page":"165","volume-title":"Proceedings of the Third Conference on Machine Translation: Research Papers","author":"Guo Mandy","year":"2018"},{"key":"bib23","author":"Hassan Hany","year":"2018","journal-title":"CoRR"},{"key":"bib24","doi-asserted-by":"crossref","first-page":"328","DOI":"10.18653\/v1\/P18-1031","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Howard Jeremy","year":"2018"},{"key":"bib25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"bib26","first-page":"3294","volume-title":"Advances in Neural Information Processing Systems 28","author":"Kiros Ryan","year":"2015"},{"key":"bib27","first-page":"1459","volume-title":"Proceedings of COLING 2012","author":"Klementiev Alexandre","year":"2012"},{"key":"bib28","author":"Lample Guillaume","year":"2019","journal-title":"CoRR"},{"key":"bib29","doi-asserted-by":"crossref","first-page":"5039","DOI":"10.18653\/v1\/D18-1549","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Lample Guillaume","year":"2018"},{"key":"bib30","first-page":"1188","volume-title":"Proceedings of the 31st International Conference on Machine Learning","volume":"32","author":"Le Quoc","year":"2014"},{"key":"bib31","first-page":"361","volume":"5","author":"Lewis David D.","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"bib32","doi-asserted-by":"crossref","first-page":"151","DOI":"10.3115\/v1\/W15-1521","volume-title":"Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing","author":"Luong Thang","year":"2015"},{"key":"bib33","first-page":"2529","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Malaviya Chaitanya","year":"2017"},{"key":"bib34","author":"Mikolov Tomas","year":"2013","journal-title":"CoRR"},{"key":"bib35","first-page":"3111","volume-title":"Advances in Neural Information Processing Systems 26","author":"Mikolov Tomas","year":"2013"},{"key":"bib36","doi-asserted-by":"crossref","first-page":"875","DOI":"10.18653\/v1\/D18-1103","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Neubig Graham","year":"2018"},{"key":"bib37","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Pennington Jeffrey","year":"2014"},{"key":"bib38","first-page":"2227","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Peters Matthew","year":"2018"},{"key":"bib39","author":"Ruder Sebastian","year":"2017","journal-title":"CoRR"},{"key":"bib40","doi-asserted-by":"crossref","first-page":"228","DOI":"10.18653\/v1\/P18-2037","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Schwenk Holger","year":"2018"},{"key":"bib41","doi-asserted-by":"crossref","first-page":"157","DOI":"10.18653\/v1\/W17-2619","volume-title":"Proceedings of the 2nd Workshop on Representation Learning for NLP","author":"Schwenk Holger","year":"2017"},{"key":"bib42","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018)","author":"Schwenk Holger","year":"2018"},{"key":"bib43","doi-asserted-by":"crossref","first-page":"86","DOI":"10.18653\/v1\/P16-1009","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sennrich Rico","year":"2016"},{"key":"bib44","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR 2018)","author":"Subramanian Sandeep","year":"2018"},{"key":"bib45","first-page":"2214","volume-title":"Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC-2012)","author":"Tiedemann J\u00f6rg","year":"2012"},{"key":"bib46","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems 30","author":"Vaswani Ashish","year":"2017"},{"key":"bib47","doi-asserted-by":"crossref","first-page":"353","DOI":"10.18653\/v1\/W18-5446","volume-title":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","author":"Wang Alex","year":"2018"},{"key":"bib48","first-page":"1112","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Williams Adina","year":"2018"},{"key":"bib49","first-page":"175","volume-title":"Proceedings of The Third Workshop on Representation Learning for NLP","author":"Katherine Yu","year":"2018"},{"key":"bib50","doi-asserted-by":"crossref","first-page":"51","DOI":"10.18653\/v1\/W17-2510","volume-title":"Proceedings of the 10th Workshop on Building and Using Comparable Corpora","author":"Zhang Zheng","year":"2017"},{"key":"bib51","doi-asserted-by":"crossref","first-page":"60","DOI":"10.18653\/v1\/W17-2512","volume-title":"Proceedings of the 10th Workshop on Building and Using Comparable Corpora","author":"Zweigenbaum Pierre","year":"2017"},{"key":"bib52","volume-title":"Proceedings of the 11th Workshop on Building and Using Comparable Corpora","author":"Zweigenbaum Pierre","year":"2018"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/tacl_a_00288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:39:29Z","timestamp":1615585169000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":52,"alternative-id":["10.1162\/tacl_a_00288"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00288","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}