{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T15:56:09Z","timestamp":1773762969888,"version":"3.50.1"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["22KJ1843"],"award-info":[{"award-number":["22KJ1843"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3402064","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:30:53Z","timestamp":1716226253000},"page":"2841-2856","source":"Crossref","is-referenced-by-count":3,"title":["EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5273-2738","authenticated-orcid":false,"given":"Zhuoyuan","family":"Mao","sequence":"first","affiliation":[{"name":"Kyoto University, Kyoto, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9848-6384","authenticated-orcid":false,"given":"Chenhui","family":"Chu","sequence":"additional","affiliation":[{"name":"Kyoto University, Kyoto, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5398-8399","authenticated-orcid":false,"given":"Sadao","family":"Kurohashi","sequence":"additional","affiliation":[{"name":"Kyoto University, Kyoto, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2619"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764273"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4330"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00288"},{"key":"ref7","article-title":"Robust cross-lingual embeddings from parallel sentences","author":"Sabet","year":"2019"},{"key":"ref8","first-page":"7057","article-title":"Cross-lingual language model pretraining","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Conneau","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/746"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.226"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.138"},{"key":"ref16","first-page":"976","article-title":"Leveraging multi-lingual positive instances in contrastive learning to improve sentence embedding","volume-title":"Proc. 18th Conf. Eur. Chapter Assoc. Comput. Linguistics","author":"Zhao","year":"2024"},{"key":"ref17","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Lan","year":"2020"},{"key":"ref18","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.115"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587669"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00474"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.417"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2512"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w17-2512"},{"key":"ref27","first-page":"3548","article-title":"A corpus for multilingual document classification in eight languages","volume-title":"Proc. 11th Int. Conf. Lang. Resour. Eval.","author":"Schwenk","year":"2018"},{"key":"ref28","first-page":"1118","article-title":"Cross-language text classification using structural correspondence learning","volume-title":"Proc. 48th Annu. Meeting Assoc. Comput. Linguistics","author":"Prettenhofer","year":"2010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.369"},{"key":"ref30","first-page":"1","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. 1st Int. Conf. Learn. Representations","author":"Mikolov","year":"2013"},{"key":"ref31","first-page":"1","article-title":"A simple but tough-to-beat baseline for sentence embeddings","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Arora","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1070"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2029"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.502"},{"key":"ref37","article-title":"Text embeddings by weakly-supervised contrastive pre-training","author":"Wang","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.124"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.72"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.197"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.393"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.707"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.402"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.58837\/chula.is.2022.31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.71"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref48","article-title":"A deep neural network approach to parallel sentence extraction","author":"Grgoire","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00097"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6317"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3022"},{"key":"ref52","first-page":"1","article-title":"An efficient framework for learning sentence representations","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Logeswaran","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1075"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.716"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.621"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.191"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1071"},{"key":"ref58","first-page":"5926","article-title":"MASS: Masked sequence to sequence pre-training for language generation","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Song","year":"2019"},{"key":"ref59","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref61","first-page":"1","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Clark","year":"2020"},{"key":"ref62","first-page":"1","article-title":"On learning universal representations across languages","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Wei","year":"2021"},{"key":"ref63","first-page":"1","article-title":"Searching for activation functions","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Ramachandran","year":"2018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref66","first-page":"2214","article-title":"Parallel data, tools and interfaces in OPUS","volume-title":"Proc. 8th Int. Conf. Lang. Resour. Eval.","author":"Tiedemann","year":"2012"},{"key":"ref67","first-page":"4411","article-title":"XTREME: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Hu","year":"2020"},{"key":"ref68","first-page":"3782","article-title":"Opustools and parallel corpus diagnostics","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Aulamo","year":"2020"},{"key":"ref69","first-page":"79","article-title":"Europarl: A parallel corpus for statistical machine translation","volume-title":"Proc. Mach. Transl. Summit X","author":"Koehn","year":"2005"},{"key":"ref70","first-page":"923","article-title":"Opensubtitles2016: Extracting large parallel corpora from movie and TV subtitles","volume-title":"Proc. 10th Int. Conf. Lang. Resour. Eval.","author":"Lison","year":"2016"},{"key":"ref71","first-page":"3530","article-title":"The united nations parallel corpus v1.0","volume-title":"Proc. 10th Int. Conf. Lang. Resour. Eval.","author":"Ziemski","year":"2016"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1310"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1276"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2010"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.170"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref77","first-page":"3683","article-title":"JASS: Japanese-specific sequence to sequence pre-training for neural machine translation","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Mao","year":"2020"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3491065"},{"key":"ref79","first-page":"201","article-title":"UnihanLM: Coarse-to-fine Chinese-Japanese language model pretraining with the unihan database","volume-title":"Proc. 1st Conf. Asia-Pacific Chapter Assoc. Comput. Linguistics 10th Int. Joint Conf. Natural Lang. Process.","author":"Xu","year":"2020"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref82","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1269"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.154"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.108"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1309"},{"key":"ref88","first-page":"361","article-title":"RCV1: A new benchmark collection for text categorization research","volume":"5","author":"Lewis","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref89","first-page":"1","article-title":"Deep encoder, shallow decoder: Reevaluating non-autoregressive machine translation","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Kasai","year":"2021"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10534791.pdf?arnumber=10534791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T04:51:50Z","timestamp":1717217510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10534791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3402064","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}