{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:24:44Z","timestamp":1766298284076},"reference-count":34,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The quality of Neural Machine Translation (NMT), as a data-driven approach, massively depends on quantity, quality and relevance of the training dataset. Such approaches have achieved promising results for bilingually high-resource scenarios but are inadequate for low-resource conditions. Generally, the NMT systems learn from millions of words from bilingual training dataset. However, human labeling process is very costly and time consuming. In this paper, we describe a round-trip training approach to bilingual low-resource NMT that takes advantage of monolingual datasets to address training data bottleneck, thus augmenting translation quality. We conduct detailed experiments on English-Spanish as a high-resource language pair as well as Persian-Spanish as a low-resource language pair. Experimental results show that this competitive approach outperforms the baseline systems and improves translation quality.<\/jats:p>","DOI":"10.1515\/comp-2019-0019","type":"journal-article","created":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T07:40:44Z","timestamp":1571038844000},"page":"268-278","source":"Crossref","is-referenced-by-count":20,"title":["Augmenting Neural Machine Translation through Round-Trip Training Approach"],"prefix":"10.1515","volume":"9","author":[{"given":"Benyamin","family":"Ahmadnia","sequence":"first","affiliation":[{"name":"Department of Computer Science , Tulane University , New Orleans , LA 70118 , United States of America"}]},{"given":"Bonnie J.","family":"Dorr","sequence":"additional","affiliation":[{"name":"Institute for Human and Machine Cognition (IHMC) , Ocala , FL 34471 , United States of America"}]}],"member":"374","published-online":{"date-parts":[[2019,10,11]]},"reference":[{"key":"2022042707443480022_j_comp-2019-0019_ref_001_w2aab3b7c18b1b6b1ab1ab1Aa","unstructured":"[1] Bahdanau D., Cho K., Bengio Y., Neural machine translation by jointly learning to align and translate, Proceedings of the International Conference on Learning Representations, 2015"},{"key":"2022042707443480022_j_comp-2019-0019_ref_002_w2aab3b7c18b1b6b1ab1ab2Aa","doi-asserted-by":"crossref","unstructured":"[2] Ahmadnia B., Serrano J., Employing pivot language technique through statistical and neural machine translation frameworks: The case of under-resourced Persian-Spanish language pair, International Journal on Natural Language Computing, 2017, 6(5), 37\u20134710.5121\/ijnlc.2017.6503","DOI":"10.5121\/ijnlc.2017.6503"},{"key":"2022042707443480022_j_comp-2019-0019_ref_003_w2aab3b7c18b1b6b1ab1ab3Aa","unstructured":"[3] Brants T., Popat A. C., Xu P., Och F. J., Dean J., Large language models in machine translation, Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 2007, 858\u2013867"},{"key":"2022042707443480022_j_comp-2019-0019_ref_004_w2aab3b7c18b1b6b1ab1ab4Aa","unstructured":"[4] G\u00fcl\u00e7ehre \u00c7., et al., On using monolingual corpora in neural machine translation, ArXiv, Vol. abs\/1503.03535, 2015"},{"key":"2022042707443480022_j_comp-2019-0019_ref_005_w2aab3b7c18b1b6b1ab1ab5Aa","unstructured":"[5] Ueffing N., Haffari G., Sarkar A., On using monolingual corpora in statistical machine translation, Journal of Machine Translation, 2008"},{"key":"2022042707443480022_j_comp-2019-0019_ref_006_w2aab3b7c18b1b6b1ab1ab6Aa","unstructured":"[6] Sennrich R., Haddow B., Birch A., Improving neural machine translation models with monolingual data, Proceedings of the 54th Annual Meeting of Association for Computational Linguistics, 201610.18653\/v1\/P16-1009"},{"key":"2022042707443480022_j_comp-2019-0019_ref_007_w2aab3b7c18b1b6b1ab1ab7Aa","doi-asserted-by":"crossref","unstructured":"[7] Ahmadnia B., Haffari G., Serrano J., Statistical machine translation for bilingually low-resource scenarios: A round-tripping approach, Proceedings of the 3rd IEEE International Conference on Machine Learning and Natural Language Processing, 2018, 261\u201326510.1109\/CIST.2018.8596614","DOI":"10.1109\/CIST.2018.8596614"},{"key":"2022042707443480022_j_comp-2019-0019_ref_008_w2aab3b7c18b1b6b1ab1ab8Aa","unstructured":"[8] He D., et al., Dual learning for machine translation, Proceedings of the 30th Conference on Neural Information Processing Systems, 2016"},{"key":"2022042707443480022_j_comp-2019-0019_ref_009_w2aab3b7c18b1b6b1ab1ab9Aa","unstructured":"[9] Jean S., Cho K., Memisevic R., Bengio Y., On using very large target vocabulary for neural machine translation, ArXiv, Vol. 412.2007, 201510.3115\/v1\/P15-1001"},{"key":"2022042707443480022_j_comp-2019-0019_ref_010_w2aab3b7c18b1b6b1ab1ac10Aa","doi-asserted-by":"crossref","unstructured":"[10] Rowley H. A., Baluja S., Kanade T., Neural network-based face detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(1), 23\u20133810.1109\/34.655647","DOI":"10.1109\/34.655647"},{"key":"2022042707443480022_j_comp-2019-0019_ref_011_w2aab3b7c18b1b6b1ab1ac11Aa","doi-asserted-by":"crossref","unstructured":"[11] McClosky D., Charniak E., Johnson M., Effective self-training for parsing, Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, 2006, 152\u201315910.3115\/1220835.1220855","DOI":"10.3115\/1220835.1220855"},{"key":"2022042707443480022_j_comp-2019-0019_ref_012_w2aab3b7c18b1b6b1ab1ac12Aa","doi-asserted-by":"crossref","unstructured":"[12] Blum A., Mitchell T., Combining labeled and unlabeled data with co-training, Proceedings of the 11th Annual Conference on Computational Learning Theory, 1998, 92\u201310010.1145\/279943.279962","DOI":"10.1145\/279943.279962"},{"key":"2022042707443480022_j_comp-2019-0019_ref_013_w2aab3b7c18b1b6b1ab1ac13Aa","unstructured":"[13] Schwenk H., Investigations on large-scale lightly-supervised training for statistical machine translation, Proceedings of IWSLT, 2008, 182\u2013189"},{"key":"2022042707443480022_j_comp-2019-0019_ref_014_w2aab3b7c18b1b6b1ab1ac14Aa","doi-asserted-by":"crossref","unstructured":"[14] Ter-Sarkisov A., Schwenk H., Barrault L., Bougares F., Incremental adaptation strategies for neural network language models, Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, 2015, 48\u20135610.18653\/v1\/W15-4006","DOI":"10.18653\/v1\/W15-4006"},{"key":"2022042707443480022_j_comp-2019-0019_ref_015_w2aab3b7c18b1b6b1ab1ac15Aa","doi-asserted-by":"crossref","unstructured":"[15] Sennrich R., Haddow B., Birch A., Neural machine translation of rare words with subword units, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016, 1715\u2013172510.18653\/v1\/P16-1162","DOI":"10.18653\/v1\/P16-1162"},{"key":"2022042707443480022_j_comp-2019-0019_ref_016_w2aab3b7c18b1b6b1ab1ac16Aa","unstructured":"[16] Artetxe M., Labaka G., Agirre E., Cho K., Unsupervised neural machine translation, ArXiv, Vol. abs\/1710.11041, 201710.18653\/v1\/D18-1399"},{"key":"2022042707443480022_j_comp-2019-0019_ref_017_w2aab3b7c18b1b6b1ab1ac17Aa","unstructured":"[17] Lample G., Conneau A., Denoyer L., Ranzato M., Unsupervised machine translation using monolingual corpora only, Proceedings of the International Conference on Learning Representations, 2018"},{"key":"2022042707443480022_j_comp-2019-0019_ref_018_w2aab3b7c18b1b6b1ab1ac18Aa","doi-asserted-by":"crossref","unstructured":"[18] Yang Z., Chen W., Wang F., Xu B., Unsupervised neural machine translation with weight sharing, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018, 46\u20135510.18653\/v1\/P18-1005","DOI":"10.18653\/v1\/P18-1005"},{"key":"2022042707443480022_j_comp-2019-0019_ref_019_w2aab3b7c18b1b6b1ab1ac19Aa","unstructured":"[19] Wu H., Wang H., Pivot language approach for phrase-based statistical machine translation, Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, 2007, 856\u2013863"},{"key":"2022042707443480022_j_comp-2019-0019_ref_020_w2aab3b7c18b1b6b1ab1ac20Aa","unstructured":"[20] Ahmadnia B., Serrano J., Haffari G., Balouchzahi N., Direct-bridge combination scenario for Persian-Spanish low-resource statistical machine translation, Proceedings of the 7th International Conference of Artificial Intelligence and Natural Language, 2018, 67\u20137810.1007\/978-3-030-01204-5_7"},{"key":"2022042707443480022_j_comp-2019-0019_ref_021_w2aab3b7c18b1b6b1ab1ac21Aa","unstructured":"[21] Ahmadnia B., Haffari G., Serrano J., Round-trip training approach for bilingually low-resource statistical machine translation systems, International Journal of Artificial Intelligence, 2019, 17(1), 167\u2013185"},{"key":"2022042707443480022_j_comp-2019-0019_ref_022_w2aab3b7c18b1b6b1ab1ac22Aa","unstructured":"[22] Dorr B. J., Machine translation divergences: A formal description and proposed solution, Computational Linguistics, 1994, 20(4), 597\u2013633"},{"key":"2022042707443480022_j_comp-2019-0019_ref_023_w2aab3b7c18b1b6b1ab1ac23Aa","unstructured":"[23] Dorr B. J., Pearl L., Hwa R., Habash N., DUSTer: A method for unraveling cross-language divergences for statistical word-level alignment, Proceedings of the 5th conference of the Association for Machine Translation in the Americas, 200210.1007\/3-540-45820-4_4"},{"key":"2022042707443480022_j_comp-2019-0019_ref_024_w2aab3b7c18b1b6b1ab1ac24Aa","unstructured":"[24] Ahmadnia B., Serrano J., Haffari G., Persian-Spanish low-resource statistical machine translation through English as pivot language, Proceedings of the 9th International Conference of Recent Advances in Natural Language Processing, 2017, 24\u20133010.26615\/978-954-452-049-6_004"},{"key":"2022042707443480022_j_comp-2019-0019_ref_025_w2aab3b7c18b1b6b1ab1ac25Aa","doi-asserted-by":"crossref","unstructured":"[25] Hochreiter S., Schmidhuber J., Long short-term memory, Neural Computation, 1997, 9(8), 1735\u2013178010.1162\/neco.1997.9.8.17359377276","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"2022042707443480022_j_comp-2019-0019_ref_026_w2aab3b7c18b1b6b1ab1ac26Aa","doi-asserted-by":"crossref","unstructured":"[26] Luong T., Sutskever I., Le Q. V., Vinyals O., Zaremba W., Addressing the rare word problem in neural machine translation, Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 2015, 11\u20131910.3115\/v1\/P15-1002","DOI":"10.3115\/v1\/P15-1002"},{"key":"2022042707443480022_j_comp-2019-0019_ref_027_w2aab3b7c18b1b6b1ab1ac27Aa","unstructured":"[27] Sutton R., Mcallester D., Singh S., Mansour Y., Policy gradient methods for reinforcement learning with function approximation, Proceedings of Advances in Neural Information Processing Systems, 2000, 1057\u20131063"},{"key":"2022042707443480022_j_comp-2019-0019_ref_028_w2aab3b7c18b1b6b1ab1ac28Aa","unstructured":"[28] Sutskever I., Vinyals O., le Q. V., Sequence to sequence learning with neural networks, Proceedings of Advances in Neural Information Processing Systems, 2014, 3104\u20133112"},{"key":"2022042707443480022_j_comp-2019-0019_ref_029_w2aab3b7c18b1b6b1ab1ac29Aa","unstructured":"[29] Tiedemann J., Parallel data, tools and interfaces in OPUS, Proceedings of the 8th International Conference on Language Resources and Evaluation, 2012"},{"key":"2022042707443480022_j_comp-2019-0019_ref_030_w2aab3b7c18b1b6b1ab1ac30Aa","unstructured":"[30] Mi H., Wang Z., Ittycheriah A., Supervised attentions for neural machine translation, Proceedings of the International Conference on Empirical Methods in Natural Language Processing, 2016, 2283\u2013228810.18653\/v1\/D16-1249"},{"key":"2022042707443480022_j_comp-2019-0019_ref_031_w2aab3b7c18b1b6b1ab1ac31Aa","unstructured":"[31] Cohn T., Huang C. D. V., Vymolova E., Yao K., Dyer C., Haffari G., Incorporating structural alignment biases into an attentional neural translation model, Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies, 2016, 876\u201388510.18653\/v1\/N16-1102"},{"key":"2022042707443480022_j_comp-2019-0019_ref_032_w2aab3b7c18b1b6b1ab1ac32Aa","doi-asserted-by":"crossref","unstructured":"[32] Mikolov T., Karafiat M., Burget L., Cernocky J., Khudanpur S., Recurrent neural network based language model, Proceedings of INTERSPEECH, 2010, 1045\u2013104810.21437\/Interspeech.2010-343","DOI":"10.21437\/Interspeech.2010-343"},{"key":"2022042707443480022_j_comp-2019-0019_ref_033_w2aab3b7c18b1b6b1ab1ac33Aa","doi-asserted-by":"crossref","unstructured":"[33] Papineni K., Roukos S., Ward T., Zhu W.J., BLEU: A method for automatic evaluation of machine translation, Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, 2001, 311\u201331810.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"2022042707443480022_j_comp-2019-0019_ref_034_w2aab3b7c18b1b6b1ab1ac34Aa","doi-asserted-by":"crossref","unstructured":"[34] Ahmadnia B., Kordjamshidi P., Haffari G., Neural machine translation advised by statistical machine translation: The case of Farsi-Spanish bilingually low-resource scenario, Proceedings of the 17th IEEE International Conference on Machine Learning and Applications, 2018, 1209\u2013121310.1109\/ICMLA.2018.00196","DOI":"10.1109\/ICMLA.2018.00196"}],"container-title":["Open Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyter.com\/view\/journals\/comp\/9\/1\/article-p268.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/comp-2019-0019\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/comp-2019-0019\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T16:15:52Z","timestamp":1695312952000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/comp-2019-0019\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,1]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,9,26]]},"published-print":{"date-parts":[[2019,1,1]]}},"alternative-id":["10.1515\/comp-2019-0019"],"URL":"https:\/\/doi.org\/10.1515\/comp-2019-0019","relation":{},"ISSN":["2299-1093"],"issn-type":[{"value":"2299-1093","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1,1]]}}}