{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:12:41Z","timestamp":1781017961838,"version":"3.54.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,2,10]],"date-time":"2021-02-10T00:00:00Z","timestamp":1612915200000},"content-version":"vor","delay-in-days":71,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Translation"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper presents a set of effective approaches to handle extremely low-resource language pairs for self-attention based neural machine translation (NMT) focusing on English and four Asian languages. Starting from an initial set of parallel sentences used to train bilingual baseline models, we introduce additional monolingual corpora and data processing techniques to improve translation quality. We describe a series of best practices and empirically validate the methods through an evaluation conducted on eight translation directions, based on state-of-the-art NMT approaches such as hyper-parameter search, data augmentation with forward and backward translation in combination with tags and noise, as well as joint multilingual training. Experiments show that the commonly used default architecture of self-attention NMT models does not reach the best results, validating previous work on the importance of hyper-parameter tuning. Additionally, empirical results indicate the amount of synthetic data required to efficiently increase the parameters of the models leading to the best translation quality measured by automatic metrics. We show that the best NMT models trained on large amount of tagged back-translations outperform three other synthetic data generation approaches. Finally, comparison with statistical machine translation (SMT) indicates that extremely low-resource NMT requires a large amount of synthetic parallel data obtained with back-translation in order to close the performance gap with the preceding SMT approach.<\/jats:p>","DOI":"10.1007\/s10590-020-09258-6","type":"journal-article","created":{"date-parts":[[2021,2,10]],"date-time":"2021-02-10T07:41:56Z","timestamp":1612942916000},"page":"347-382","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Extremely low-resource neural machine translation for Asian languages"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4353-7804","authenticated-orcid":false,"given":"Raphael","family":"Rubino","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Marie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raj","family":"Dabre","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atushi","family":"Fujita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masao","family":"Utiyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eiichiro","family":"Sumita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,10]]},"reference":[{"key":"9258_CR1","doi-asserted-by":"publisher","unstructured":"Aharoni R, Johnson M, Firat O (2019) Massively multilingual neural machine translation. In: 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), pp 3874\u20133884. Association for Computational Linguistics, Minneapolis, USA. https:\/\/doi.org\/10.18653\/v1\/N19-1388. https:\/\/aclweb.org\/anthology\/N19-1388","DOI":"10.18653\/v1\/N19-1388"},{"key":"9258_CR2","doi-asserted-by":"publisher","unstructured":"Artetxe M, Labaka G, Agirre E (2018) Unsupervised statistical machine translation. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp 3632\u20133642. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/D18-1399. https:\/\/aclweb.org\/anthology\/D18-1399","DOI":"10.18653\/v1\/D18-1399"},{"key":"9258_CR3","doi-asserted-by":"crossref","unstructured":"Artetxe M, Labaka G, Agirre E, Cho K (2018) Unsupervised neural machine translation. In: Proceedings of the 6th international conference on learning representations. Vancouver, Canada. https:\/\/openreview.net\/forum?id=Sy2ogebAW","DOI":"10.18653\/v1\/D18-1399"},{"key":"9258_CR4","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. arXiv:1607.06450"},{"key":"9258_CR5","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: Proceedings of the 3rd international conference on learning representations. San Diego, USA. arxiv:1409.0473"},{"key":"9258_CR6","doi-asserted-by":"publisher","unstructured":"Barrault L, Bojar O, Costa-juss\u00e0 MR, Federmann C, Fishel M, Graham Y, Haddow B, Huck M, Koehn P, Malmasi S, Monz C, M\u00fcller M, Pal S, Post M, Zampieri M (2019) Findings of the 2019 conference on machine translation (WMT19). In: Proceedings of the fourth conference on machine translation (Volume 2: Shared Task Papers, Day 1), pp 1\u201361. Association for Computational Linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/W19-5301. https:\/\/aclweb.org\/anthology\/W19-5301","DOI":"10.18653\/v1\/W19-5301"},{"key":"9258_CR7","unstructured":"Bogoychev N, Sennrich R (2019) Domain, translationese and noise in synthetic data for neural machine translation. arXiv:1911.03362"},{"key":"9258_CR8","unstructured":"Bojanowski P, Grave E, Joulin A, Mikolov T (2016) Enriching word vectors with subword information. arXiv:1607.04606"},{"key":"9258_CR9","doi-asserted-by":"publisher","unstructured":"Bojar O, Chatterjee R, Federmann C, Graham Y, Haddow B, Huck M, Jimeno\u00a0Yepes A, Koehn P, Logacheva V, Monz C, Negri M, Neveol A, Neves M, Popel M, Post M, Rubino R, Scarton C, Specia L, Turchi M, Verspoor K, Zampieri M (2016) Findings of the 2016 conference on machine translation. In: Proceedings of the first conference on machine translation, pp 131\u2013198. Association for Computational Linguistics, Berlin, Germany. https:\/\/doi.org\/10.18653\/v1\/W16-2301. https:\/\/aclweb.org\/anthology\/W16-2301","DOI":"10.18653\/v1\/W16-2301"},{"key":"9258_CR10","doi-asserted-by":"publisher","unstructured":"Brown PF, Lai JC, Mercer RL (1991) Aligning sentences in parallel corpora. In: Proceedings of the 29th annual meeting on association for computational linguistics, pp 169\u2013176. Association for Computational Linguistics, Berkeley, USA. https:\/\/doi.org\/10.3115\/981344.981366. https:\/\/aclweb.org\/anthology\/P91-1022","DOI":"10.3115\/981344.981366"},{"key":"9258_CR11","doi-asserted-by":"publisher","unstructured":"Burlot F, Yvon F (2018) Using monolingual data in neural machine translation: a systematic study. In: Proceedings of the third conference on machine translation: research papers, pp 144\u2013155. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/W18-6315. https:\/\/aclweb.org\/anthology\/W18-6315","DOI":"10.18653\/v1\/W18-6315"},{"key":"9258_CR12","doi-asserted-by":"publisher","unstructured":"Caswell I, Chelba C, Grangier D (2019) Tagged back-translation. In: Proceedings of the fourth conference on machine translation (volume 1: research papers), pp 53\u201363. association for computational linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/W19-5206. https:\/\/aclweb.org\/anthology\/W19-5206.pdf","DOI":"10.18653\/v1\/W19-5206"},{"key":"9258_CR13","unstructured":"Cettolo M, Jan N, Sebastian S, Bentivogli L, Cattoni R, Federico M (2016) The IWSLT 2016 evaluation campaign. In: Proceedings of the 13th international workshop on spoken language translation. Seatle, USA. https:\/\/workshop2016.iwslt.org\/downloads\/IWSLT_2016_evaluation_overview.pdf"},{"key":"9258_CR14","doi-asserted-by":"publisher","unstructured":"Chen PJ, Shen J, Le M, Chaudhary V, El-Kishky A, Wenzek G, Ott M, Ranzato M (2019) Facebook AI\u2019s WAT19 Myanmar-English Translation Task submission. In: Proceedings of the 6th Workshop on Asian Translation, pp 112\u2013122. Association for Computational Linguistics, Hong Kong, China. https:\/\/doi.org\/10.18653\/v1\/D19-5213. https:\/\/aclweb.org\/anthology\/D19-5213","DOI":"10.18653\/v1\/D19-5213"},{"key":"9258_CR15","unstructured":"Cherry C, Foster G (2012) Batch tuning strategies for statistical machine translation. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 427\u2013436. Association for Computational Linguistics, Montr\u00e9al, Canada. https:\/\/aclweb.org\/anthology\/N12-1047"},{"key":"9258_CR16","doi-asserted-by":"publisher","unstructured":"Cho K, van Merri\u00ebnboer B, Bahdanau D, Bengio Y (2014) On the properties of neural machine translation: Encoder\u2013decoder approaches. In: Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pp. 103\u2013111. Association for Computational Linguistics, Doha, Qatar. https:\/\/doi.org\/10.3115\/v1\/W14-4012. https:\/\/aclweb.org\/anthology\/W14-4012\/","DOI":"10.3115\/v1\/W14-4012"},{"key":"9258_CR17","doi-asserted-by":"publisher","unstructured":"Dabre R, Fujita A, Chu C (2019) Exploiting multilingualism through multistage fine-tuning for low-resource neural machine translation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 1410\u20131416. Association for Computational Linguistics, Hong Kong, China. https:\/\/doi.org\/10.18653\/v1\/D19-1146. https:\/\/aclweb.org\/anthology\/D19-1146","DOI":"10.18653\/v1\/D19-1146"},{"key":"9258_CR18","doi-asserted-by":"publisher","unstructured":"Edunov S, Ott M, Auli M, Grangier D (2018) Understanding back-translation at scale. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 489\u2013500. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/D18-1045. https:\/\/aclweb.org\/anthology\/D18-1045","DOI":"10.18653\/v1\/D18-1045"},{"key":"9258_CR19","unstructured":"Elsken T, Metzen JH, Hutter F (2018) Neural architecture search: a survey. arXiv:1808.05377"},{"key":"9258_CR20","doi-asserted-by":"publisher","unstructured":"Firat O, Cho K, Bengio Y (2016) Multi-way, multilingual neural machine translation with a shared attention mechanism. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 866\u2013875. Association for Computational Linguistics, San Diego, USA. https:\/\/doi.org\/10.18653\/v1\/N16-1101. https:\/\/aclweb.org\/anthology\/N16-1101","DOI":"10.18653\/v1\/N16-1101"},{"key":"9258_CR21","doi-asserted-by":"publisher","unstructured":"Firat O, Sankaran B, Al-Onaizan Y, Yarman\u00a0Vural FT, Cho K (2016) Zero-resource translation with multi-lingual neural machine translation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 268\u2013277. Association for Computational Linguistics, Austin, USA. https:\/\/doi.org\/10.18653\/v1\/D16-1026. https:\/\/aclweb.org\/anthology\/D16-1026","DOI":"10.18653\/v1\/D16-1026"},{"key":"9258_CR22","doi-asserted-by":"publisher","unstructured":"Forcada ML, $$\\tilde{{\\rm N}}$$eco RP (1997) Recursive hetero-associative memories for translation. In: Mira J, Moreno-D\u00edaz R, Cabestany J (eds) Biological and artificial computation: from neuroscience to technology. Springer, Berlin. https:\/\/doi.org\/10.1007\/BFb0032504","DOI":"10.1007\/BFb0032504"},{"key":"9258_CR23","first-page":"88","volume":"1","author":"M Gellerstam","year":"1986","unstructured":"Gellerstam M (1986) Translationese in Swedish novels translated from English. Transl Stud Scand 1:88\u201395","journal-title":"Transl Stud Scand"},{"key":"9258_CR24","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.csl.2017.01.014","volume":"45","author":"C Gulcehre","year":"2017","unstructured":"Gulcehre C, Firat O, Xu K, Cho K, Bengio Y (2017) On integrating a language model into neural machine translation. Comput Speech Lang 45:137\u2013148. https:\/\/doi.org\/10.1016\/j.csl.2017.01.014","journal-title":"Comput Speech Lang"},{"key":"9258_CR25","unstructured":"Heafield K, Pouzyrevsky I, Clark JH, Koehn P (2013) Scalable modified Kneser-Ney language model estimation. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pp. 690\u2013696. Association for Computational Linguistics, Sofia, Bulgaria. https:\/\/aclweb.org\/anthology\/P13-2121\/"},{"key":"9258_CR26","doi-asserted-by":"publisher","unstructured":"Imamura K, Sumita E (2018) NICT self-training approach to neural machine translation at NMT-2018. In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 110\u2013115. Association for Computational Linguistics, Melbourne, Australia. https:\/\/doi.org\/10.18653\/v1\/W18-2713. https:\/\/aclweb.org\/anthology\/W18-2713","DOI":"10.18653\/v1\/W18-2713"},{"key":"9258_CR27","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1162\/tacl_a_00065","volume":"5","author":"M Johnson","year":"2017","unstructured":"Johnson M, Schuster M, Le QV, Krikun M, Wu Y, Chen Z, Thorat N, Vi\u00e9gas F, Wattenberg M, Corrado G, Hughes M, Dean J (2017) Google\u2019s multilingual neural machine translation system: enabling zero-shot translation. Trans Assoc Comput Linguist 5:339\u2013351. https:\/\/doi.org\/10.1162\/tacl_a_00065","journal-title":"Trans Assoc Comput Linguist"},{"key":"9258_CR28","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980"},{"key":"9258_CR29","unstructured":"Koehn P (2004) Statistical significance tests for machine translation evaluation. In: Proceedings of the 2004 conference on empirical methods in natural language processing, pp. 388\u2013395"},{"key":"9258_CR30","doi-asserted-by":"crossref","unstructured":"Koehn P, Hoang H, Birch A, Callison-Burch C, Federico M, Bertoldi N, Cowan B, Shen W, Moran C, Zens R, Dyer C, Bojar O, Constantin A, Herbst E (2007) Moses: Open source toolkit for statistical machine translation. In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions, pp. 177\u2013180. Association for Computational Linguistics, Prague, Czech Republic. https:\/\/aclweb.org\/anthology\/P07-2045","DOI":"10.3115\/1557769.1557821"},{"key":"9258_CR31","doi-asserted-by":"publisher","unstructured":"Koehn P, Knowles R (2017) Six challenges for neural machine translation. In: Proceedings of the First Workshop on Neural Machine Translation, pp. 28\u201339. Association for Computational Linguistics, Vancouver, Canada. https:\/\/doi.org\/10.18653\/v1\/W17-3204. https:\/\/aclweb.org\/anthology\/W17-3204","DOI":"10.18653\/v1\/W17-3204"},{"key":"9258_CR32","doi-asserted-by":"publisher","unstructured":"Kudo T, Richardson J (2018) Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 66\u201371. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/D18-2012. https:\/\/aclweb.org\/anthology\/D18-2012","DOI":"10.18653\/v1\/D18-2012"},{"key":"9258_CR33","unstructured":"Lambert P, Schwenk H, Servan C, Abdul-Rauf S (2011) Investigations on translation model adaptation using monolingual data. In: Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 284\u2013293. Association for Computational Linguistics, Edinburgh, Scotland. https:\/\/aclweb.org\/anthology\/W11-2132"},{"key":"9258_CR34","unstructured":"Lample G, Conneau A (2019) Cross-lingual language model pretraining. In: Proceedings of Advances in Neural Information Processing Systems 32, pp. 7057\u20137067. Curran Associates, Inc., Vancouver, Canada. https:\/\/papers.nips.cc\/paper\/8928-cross-lingual-language-model-pretraining"},{"key":"9258_CR35","unstructured":"Lample G, Conneau A, Denoyer L, Ranzato M (2018) Unsupervised machine translation using monolingual corpora only. In: Proceedings of the 6th International Conference on Learning Representations. Vancouver, Canada. https:\/\/openreview.net\/forum?id=rkYTTf-AZ"},{"key":"9258_CR36","doi-asserted-by":"publisher","unstructured":"Lample G, Ott M, Conneau A, Denoyer L, Ranzato M (2018) Phrase-based & neural unsupervised machine translation. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 5039\u20135049. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/D18-1549. https:\/\/aclweb.org\/anthology\/D18-1549","DOI":"10.18653\/v1\/D18-1549"},{"key":"9258_CR37","doi-asserted-by":"publisher","unstructured":"Marie B, Dabre R, Fujita A (2019) NICT\u2019s machine translation systems for the WMT19 similar language translation task. In: Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), pp. 208\u2013212. Association for Computational Linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/W19-5428. https:\/\/aclweb.org\/anthology\/W19-5428","DOI":"10.18653\/v1\/W19-5428"},{"key":"9258_CR38","doi-asserted-by":"publisher","unstructured":"Marie B, Sun H, Wang R, Chen K, Fujita A, Utiyama M, Sumita E (2019) NICT\u2019s unsupervised neural and statistical machine translation systems for the WMT19 news translation task. In: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pp. 294\u2013301. Association for Computational Linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/W19-5330. https:\/\/aclweb.org\/anthology\/W19-5330","DOI":"10.18653\/v1\/W19-5330"},{"key":"9258_CR39","unstructured":"Michel P, Levy O, Neubig G (2019) Are sixteen heads really better than one? In: Proceedings of Advances in Neural Information Processing Systems 32, pp. 14014\u201314024. Curran Associates, Inc., Vancouver, Canada. https:\/\/papers.nips.cc\/paper\/9551-are-sixteen-heads-really-better-than-one"},{"key":"9258_CR40","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on International Conference on Machine Learning, pp. 807\u2013814. Madison, USA. https:\/\/dl.acm.org\/doi\/10.5555\/3104322.3104425"},{"key":"9258_CR41","unstructured":"Nguyen TQ, Salazar J (2019) Transformers without tears: improving the normalization of self-attention. arXiv:1910.05895"},{"key":"9258_CR42","doi-asserted-by":"publisher","unstructured":"Och FJ, Ney H (2000) Improved statistical alignment models. In: Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, pp. 440\u2013447. Association for Computational Linguistics, Hong Kong, China. https:\/\/doi.org\/10.3115\/1075218.1075274. https:\/\/aclweb.org\/anthology\/P00-1056\/","DOI":"10.3115\/1075218.1075274"},{"key":"9258_CR43","doi-asserted-by":"publisher","unstructured":"Ott M, Edunov S, Baevski A, Fan A, Gross S, Ng N, Grangier D, Auli M (2019) fairseq: A fast, extensible toolkit for sequence modeling. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pp. 48\u201353. Association for Computational Linguistics, Minneapolis, USA. https:\/\/doi.org\/10.18653\/v1\/N19-4009. https:\/\/aclweb.org\/anthology\/N19-4009\/","DOI":"10.18653\/v1\/N19-4009"},{"key":"9258_CR44","doi-asserted-by":"publisher","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics, Philadelphia, USA. https:\/\/doi.org\/10.3115\/1073083.1073135. https:\/\/aclweb.org\/anthology\/P02-1040\/","DOI":"10.3115\/1073083.1073135"},{"key":"9258_CR45","doi-asserted-by":"publisher","unstructured":"Popovi\u0107 M (2015) chrF: character n-gram F-score for automatic MT evaluation. In: Proceedings of the Tenth Workshop on Statistical Machine Translation, pp. 392\u2013395. Association for Computational Linguistics, Lisbon, Portugal. https:\/\/doi.org\/10.18653\/v1\/W15-3049. https:\/\/aclweb.org\/anthology\/W15-3049\/","DOI":"10.18653\/v1\/W15-3049"},{"key":"9258_CR46","doi-asserted-by":"publisher","unstructured":"Post M (2018) A call for clarity in reporting BLEU scores. In: Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 186\u2013191. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/W18-6319. https:\/\/aclweb.org\/anthology\/W18-6319\/","DOI":"10.18653\/v1\/W18-6319"},{"key":"9258_CR47","doi-asserted-by":"publisher","unstructured":"Riza H, Purwoadi M, Uliniansyah T, Ti AA, Aljunied SM, Mai LC, Thang VT, Thai NP, Chea V, Sam S, et\u00a0al (2016) Introduction of the Asian Language Treebank. In: 2016 Conference of The Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA), pp. 1\u20136. Institute of Electrical and Electronics Engineers, Bali, Indonesia. https:\/\/doi.org\/10.1109\/ICSDA.2016.7918974. https:\/\/ieeexplore.ieee.org\/document\/7918974","DOI":"10.1109\/ICSDA.2016.7918974"},{"key":"9258_CR48","unstructured":"Schwenk H (2008) Investigations on large-scale lightly-supervised training for statistical machine translation. In: Proceedings of the International Workshop on Spoken Language Translation, pp. 182\u2013189. Honolulu, USA. https:\/\/www.isca-speech.org\/archive\/iwslt_08\/papers\/slt8_182.pdf"},{"key":"9258_CR49","unstructured":"Schwenk H, Chaudhary V, Sun S, Gong H, Guzm\u00e1n F (2019) WikiMatrix: Mining 135M parallel sentences in 1620 language pairs from Wikipedia"},{"key":"9258_CR50","doi-asserted-by":"publisher","unstructured":"Sennrich R, Haddow B, Birch A (2016a) Improving neural machine translation models with monolingual data. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 86\u201396. Association for Computational Linguistics, Berlin, Germany. https:\/\/doi.org\/10.18653\/v1\/P16-1009. https:\/\/aclweb.org\/anthology\/P16-1009","DOI":"10.18653\/v1\/P16-1009"},{"key":"9258_CR51","doi-asserted-by":"publisher","unstructured":"Sennrich R, Haddow B, Birch A (2016b) Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1715\u20131725. Association for Computational Linguistics, Berlin, Germany. https:\/\/doi.org\/10.18653\/v1\/P16-1162. https:\/\/aclweb.org\/anthology\/P16-1162","DOI":"10.18653\/v1\/P16-1162"},{"key":"9258_CR52","doi-asserted-by":"publisher","unstructured":"Sennrich R, Zhang B (2019) Revisiting low-resource neural machine translation: A case study. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 211\u2013221. Association for Computational Linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/P19-1021. https:\/\/aclweb.org\/anthology\/P19-1021","DOI":"10.18653\/v1\/P19-1021"},{"key":"9258_CR53","doi-asserted-by":"publisher","unstructured":"S\u00f8gaard A, Ruder S, Vuli\u0107 I (2018) On the limitations of unsupervised bilingual dictionary induction. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 778\u2013788. Association for Computational Linguistics, Melbourne, Australia. https:\/\/doi.org\/10.18653\/v1\/P18-1072. https:\/\/aclweb.org\/anthology\/P18-1072","DOI":"10.18653\/v1\/P18-1072"},{"key":"9258_CR54","doi-asserted-by":"publisher","unstructured":"Stahlberg F, Cross J, Stoyanov V (2018) Simple fusion: Return of the language model. In: Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 204\u2013211. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/W18-6321. https:\/\/aclweb.org\/anthology\/W18-6321","DOI":"10.18653\/v1\/W18-6321"},{"key":"9258_CR55","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Proceedings of the 27th Neural Information Processing Systems Conference (NIPS), pp. 3104\u20133112. Curran Associates, Inc., Montr\u00e9al, Canada. http:\/\/papers.nips.cc\/paper\/5346-sequence-to-sequence-learning-with-neural-networks.pdf"},{"key":"9258_CR56","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Proceedings of the 30th Neural Information Processing Systems Conference (NIPS), pp. 5998\u20136008. Curran Associates, Inc., Long Beach, USA. http:\/\/papers.nips.cc\/paper\/7181-attention-is-all-you-need.pdf"},{"key":"9258_CR57","doi-asserted-by":"publisher","unstructured":"Voita E, Talbot D, Moiseev F, Sennrich R, Titov I (2019) Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5797\u20135808. Association for Computational Linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/P19-1580. https:\/\/aclweb.org\/anthology\/P19-1580\/","DOI":"10.18653\/v1\/P19-1580"},{"key":"9258_CR58","doi-asserted-by":"publisher","unstructured":"Wang Q, Li B, Xiao T, Zhu J, Li C, Wong DF, Chao LS (2019) Learning deep transformer models for machine translation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1810\u20131822. Association for Computational Linguistics, Florence, Italy. https:\/\/doi.org\/10.18653\/v1\/P19-1176. https:\/\/aclweb.org\/anthology\/P19-1176","DOI":"10.18653\/v1\/P19-1176"},{"key":"9258_CR59","doi-asserted-by":"crossref","unstructured":"Zens R, Och FJ, Ney H (2002) Phrase-based statistical machine translation. In: Annual Conference on Artificial Intelligence, pp. 18\u201332. Springer","DOI":"10.1007\/3-540-45751-8_2"}],"container-title":["Machine Translation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-020-09258-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10590-020-09258-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-020-09258-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,25]],"date-time":"2021-02-25T11:11:13Z","timestamp":1614251473000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10590-020-09258-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":59,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["9258"],"URL":"https:\/\/doi.org\/10.1007\/s10590-020-09258-6","relation":{},"ISSN":["0922-6567","1573-0573"],"issn-type":[{"value":"0922-6567","type":"print"},{"value":"1573-0573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]},"assertion":[{"value":"4 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}