{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T15:55:26Z","timestamp":1790697326253,"version":"4.1.0"},"reference-count":37,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2021,1,31]],"date-time":"2021-01-31T00:00:00Z","timestamp":1612051200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"JSPS grant-in-aid for early-career scientists"},{"name":"Unsupervised Neural Machine Translation in Universal Scenarios"},{"name":"National Key Research and Development Program of China","award":["2018YFC0830700"],"award-info":[{"award-number":["2018YFC0830700"]}]},{"name":"NICT tenure-track researcher startup fund \u201cToward Intelligent Machine Translation.\u201d"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2021,1,31]]},"abstract":"<jats:p>Unsupervised neural machine translation (UNMT) has achieved remarkable results for several language pairs, such as French\u2013English and German\u2013English. Most previous studies have focused on modeling UNMT systems; few studies have investigated the effect of UNMT on specific languages. In this article, we first empirically investigate UNMT for four diverse language pairs (French\/German\/Chinese\/Japanese\u2013English). We confirm that the performance of UNMT in translation tasks for similar language pairs (French\/German\u2013English) is dramatically better than for distant language pairs (Chinese\/Japanese\u2013English). We empirically show that the lack of shared words and different word orderings are the main reasons that lead UNMT to underperform in Chinese\/Japanese\u2013English. Based on these findings, we propose several methods, including artificial shared words and pre-ordering, to improve the performance of UNMT for distant language pairs. Moreover, we propose a simple general method to improve translation performance for all these four language pairs. The existing UNMT model can generate a translation of a reasonable quality after a few training epochs owing to a denoising mechanism and shared latent representations. However, learning shared latent representations restricts the performance of translation in both directions, particularly for distant language pairs, while denoising dramatically delays convergence by continuously modifying the training data. To avoid these problems, we propose a simple, yet effective and efficient, approach that (like UNMT) relies solely on monolingual corpora: pseudo-data-based unsupervised neural machine translation. Experimental results for these four language pairs show that our proposed methods significantly outperform UNMT baselines.<\/jats:p>","DOI":"10.1145\/3418059","type":"journal-article","created":{"date-parts":[[2021,3,31]],"date-time":"2021-03-31T16:11:04Z","timestamp":1617207064000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Unsupervised Neural Machine Translation for Similar and Distant Language Pairs"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5899-0401","authenticated-orcid":false,"given":"Haipeng","family":"Sun","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, Heilongjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8007-2503","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masao","family":"Utiyama","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Marie","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4346-7618","authenticated-orcid":false,"given":"Kehai","family":"Chen","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eiichiro","family":"Sumita","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Seika-cho, Souraku-gun, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiejun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, Heilongjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,3,31]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Proceedings of the 32nd AAAI Conference on Artificial Intelligence. AAAI Press, 5012--5019","author":"Artetxe Mikel","year":"2018"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1073"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1399"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1019"},{"key":"e_1_2_1_5_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations.","author":"Artetxe Mikel","year":"2018"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_2_1_7_1","volume-title":"Findings of the 2019 conference on machine translation (WMT19). In Proceedings of the 4th Conference on Machine Translation","volume":"61","author":"Bojar Ond\u0159ej","year":"2019"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219906"},{"key":"e_1_2_1_9_1","volume-title":"Advances in Neural Information Processing Systems 32. Curran Associates","author":"Conneau Alexis"},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations.","author":"Conneau Alexis","year":"2018"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1515\/pralin-2017-0018"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1078"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2518100"},{"key":"e_1_2_1_14_1","volume-title":"Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems. Curran Associates","author":"He Di","year":"2016"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1162"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2703"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-3004"},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the 3rd International Conference on Learning Representations.","author":"Kingma Diederik P","year":"2015"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1557769.1557821"},{"key":"e_1_2_1_20_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations.","author":"Lample Guillaume","year":"2018"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1549"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1017"},{"key":"e_1_2_1_23_1","volume-title":"Ethnologue: Languages of the World. SIL international","author":"Lewis M. Paul","year":"2009"},{"key":"e_1_2_1_24_1","volume-title":"Unsupervised neural machine translation initialized by unsupervised statistical machine translation. CoRR abs\/1810.12703","author":"Marie Benjamin","year":"2018"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5330"},{"key":"e_1_2_1_26_1","unstructured":"Shuo Ren Zhirui Zhang Shujie Liu Ming Zhou and Shuai Ma. 2019. Unsupervised neural machine translation with SMT as posterior regularization. In Proceedings of the 32rd AAAI Conference on Artificial Intelligence (AAAI\u201919) Proceedings of the 31st Innovative Applications of Artificial Intelligence Conference (IAAI\u201919) Proceedings of the 9th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI\u201919). AAAI Press 241--248.  Shuo Ren Zhirui Zhang Shujie Liu Ming Zhou and Shuai Ma. 2019. Unsupervised neural machine translation with SMT as posterior regularization. In Proceedings of the 32rd AAAI Conference on Artificial Intelligence (AAAI\u201919) Proceedings of the 31st Innovative Applications of Artificial Intelligence Conference (IAAI\u201919) Proceedings of the 9th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI\u201919). AAAI Press 241--248."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1072"},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML\u201919)","author":"Song Kaitao","year":"2019"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1119"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1008"},{"key":"e_1_2_1_32_1","volume-title":"Advances in Neural Information Processing Systems 30. Curran Associates","author":"Vaswani Ashish"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953039"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1120"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/739"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1005"},{"key":"e_1_2_1_37_1","unstructured":"Zhirui Zhang Shujie Liu Mu Li Ming Zhou and Enhong Chen. 2018. Joint training for neural machine translation models with monolingual data. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI\u201918) Proceedings of the 30th innovative Applications of Artificial Intelligence (IAAI\u201918) and Proceedings of the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI\u201918). AAAI Press 555--562.  Zhirui Zhang Shujie Liu Mu Li Ming Zhou and Enhong Chen. 2018. Joint training for neural machine translation models with monolingual data. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI\u201918) Proceedings of the 30th innovative Applications of Artificial Intelligence (IAAI\u201918) and Proceedings of the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI\u201918). AAAI Press 555--562."}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3418059","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3418059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:31:35Z","timestamp":1750195895000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3418059"}},"subtitle":["An Empirical Study"],"short-title":[],"issued":{"date-parts":[[2021,1,31]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1,31]]}},"alternative-id":["10.1145\/3418059"],"URL":"https:\/\/doi.org\/10.1145\/3418059","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,31]]},"assertion":[{"value":"2019-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-08-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}