{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:14:04Z","timestamp":1777706044240,"version":"3.51.4"},"reference-count":42,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,7,2]]},"abstract":"<jats:p>Transformer-based neural machine translation (NMT) has achieved state-of-the-art performance in the NMT paradigm. However, it relies on the availability of copious parallel corpora. For low-resource language pairs, the amount of parallel data is insufficient, resulting in poor translation quality. To alleviate this issue, this paper proposes an efficient data augmentation (DA) method named STA. Firstly, the pseudo-parallel sentence pairs are generated by translating sentence trunks with the target-to-source NMT model. Furthermore, two strategies are introduced to merge the original data and pseudo-parallel corpus to augment the training set. Experimental results on simulated and real low-resource translation tasks show that the proposed method improves the translation quality over the strong baseline, and also outperforms other data augmentation methods. Moreover, the STA method can further improve the translation quality when combined with the back-translation method with the extra monolingual data.<\/jats:p>","DOI":"10.3233\/jifs-230682","type":"journal-article","created":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T11:41:18Z","timestamp":1681818078000},"page":"121-132","source":"Crossref","is-referenced-by-count":7,"title":["STA: An efficient data augmentation method for low-resource neural machine translation"],"prefix":"10.1177","volume":"45","author":[{"given":"Fuxue","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, China"},{"name":"College of Electrical Engineering, Yingkou Institute of Technology, Yingkou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuncheng","family":"Chi","sequence":"additional","affiliation":[{"name":"Shenyang University of Chemical Technology, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Yingkou Institute of Technology, Yingkou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beibei","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenyang University of Chemical Technology, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhi","family":"Shao","sequence":"additional","affiliation":[{"name":"Shenyang University of Chemical Technology, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-230682_ref1","unstructured":"Bahdanau D. , Cho K. and Bengio Y. , Neural machine translation by jointly learning to align and translate[J], arXiv preprint arXiv:1409.0473, 2014."},{"key":"10.3233\/JIFS-230682_ref2","unstructured":"Wu Y. , Schuster M. , Chen Z. et al., Google\u2019s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation[J], 2016."},{"key":"10.3233\/JIFS-230682_ref3","unstructured":"Gehring J. , Auli M. , Grangier D. et al., Convolutional sequence to sequence learning[C], International conference on machine learning, PMLR, 2017:1243\u20131252."},{"key":"10.3233\/JIFS-230682_ref4","first-page":"30","article-title":"Attention is all you need[J]","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"10.3233\/JIFS-230682_ref5","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.18653\/v1\/D16-1163","article-title":"Transfer Learning for Low-Resource Neural Machine Translation[C]","author":"Zoph","year":"2016","journal-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing"},{"key":"10.3233\/JIFS-230682_ref6","doi-asserted-by":"crossref","unstructured":"Gu J. , Wang Y. , Chen Y. et al., Meta-learning for low-resource neural machine translation[C], Conference on Empirical Methods in Natural Language Processing (EMNLP) Proceedings, Association for Computational Linguistics 2018.","DOI":"10.18653\/v1\/D18-1398"},{"key":"10.3233\/JIFS-230682_ref7","doi-asserted-by":"crossref","first-page":"56","DOI":"10.18653\/v1\/P18-1006","article-title":"Triangular Architecture for Rare Language Translation[C]","volume":"1","author":"Ren","year":"2018","journal-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics"},{"key":"10.3233\/JIFS-230682_ref8","doi-asserted-by":"crossref","unstructured":"Sennrich R. , Haddow B. and Birch A. , Improving neural machine translation models with monolingual data[J], arXiv preprint arXiv:1511.06709 2015.","DOI":"10.18653\/v1\/P16-1009"},{"key":"10.3233\/JIFS-230682_ref9","first-page":"29","article-title":"Reward augmented maximum likelihood for neural structured prediction[J]","author":"Norouzi","year":"2016","journal-title":"Advances In Neural Information Processing Systems"},{"key":"10.3233\/JIFS-230682_ref10","doi-asserted-by":"crossref","first-page":"1535","DOI":"10.18653\/v1\/D16-1160","article-title":"Exploiting source-side monolingual data in neural machine translation[C],:","author":"Zhang","year":"2016","journal-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing"},{"key":"10.3233\/JIFS-230682_ref11","doi-asserted-by":"crossref","unstructured":"Fadaee M. , Bisazza A. and Monz C. , Data augmentation for low-resource neural machine translation[J], arXiv preprint arXiv:1705.00440 2017.","DOI":"10.18653\/v1\/P17-2090"},{"key":"10.3233\/JIFS-230682_ref12","doi-asserted-by":"crossref","unstructured":"Wang X. , Pham H. , Dai Z. et al., SwitchOut: an efficient data augmentation algorithm for neural machine translation[J], arXiv preprint arXiv:1808.07512 2018.","DOI":"10.18653\/v1\/D18-1100"},{"issue":"01","key":"10.3233\/JIFS-230682_ref13","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1609\/aaai.v33i01.3301443","article-title":"Regularizing neural machine translation by target-bidirectional agreement[C]","volume":"33","author":"Zhang","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.3233\/JIFS-230682_ref14","doi-asserted-by":"crossref","unstructured":"Edunov S. , Ott M. , Auli M. et al., Understanding back-translation at scale[J], arXiv preprint arXiv:1808.09381 2018.","DOI":"10.18653\/v1\/D18-1045"},{"key":"10.3233\/JIFS-230682_ref15","doi-asserted-by":"crossref","unstructured":"Fadaee M. and Monz C. , Back-translation sampling by targeting difficult words in neural machine translation[J], arXiv preprint arXiv:1808.09006 2018.","DOI":"10.18653\/v1\/D18-1040"},{"key":"10.3233\/JIFS-230682_ref16","first-page":"2016","article-title":"Edinburgh neural machine translation systems for WMT 16[J]","author":"Sennrich","journal-title":"arXiv preprint arXiv:1606.02891"},{"key":"10.3233\/JIFS-230682_ref17","first-page":"29","article-title":"A theoretically grounded application of dropout in recurrent neural networks[J]","author":"Gal","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-230682_ref18","doi-asserted-by":"crossref","first-page":"5539","DOI":"10.18653\/v1\/P19-1555","article-title":"Soft contextual data augmentation for neural machine translation[C]","author":"Gao","year":"2019","journal-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics"},{"key":"10.3233\/JIFS-230682_ref19","unstructured":"Poncelas A. , Shterionov D. , Way A. et al., Investigating Backtranslation in Neural Machine Translation[J], 2018."},{"key":"10.3233\/JIFS-230682_ref20","first-page":"25","article-title":"Transductive learning for statistical machine translation","author":"Ueffing","year":"2007","journal-title":"Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics"},{"key":"10.3233\/JIFS-230682_ref21","doi-asserted-by":"crossref","first-page":"55","DOI":"10.3115\/v1\/P14-5010","article-title":"The stanford corenlp natural language processing toolkit","author":"Manning","year":"2014","journal-title":"Proceedings of 52nd annual meeting of the association for computational linguistics: System demonstrations"},{"key":"10.3233\/JIFS-230682_ref22","doi-asserted-by":"crossref","unstructured":"Burlot F. and Yvon F. , Using Monolingual Data in Neural Machine Translation: a Systematic Study[C], Conference on Machine Translation 2018.","DOI":"10.18653\/v1\/W18-6315"},{"key":"10.3233\/JIFS-230682_ref23","unstructured":"Cotterell R. and Kreutzer J. , Explaining and generalizing back-translation through wake-sleep, arXiv 2018, arXiv:1806.04402."},{"key":"10.3233\/JIFS-230682_ref24","first-page":"820","article-title":"Dual learning for machine translation","author":"He","year":"2016","journal-title":"Proceedings of the 30th Conference on Neural Information Processing Systems (NIPS 2016)"},{"key":"10.3233\/JIFS-230682_ref25","doi-asserted-by":"crossref","first-page":"18","DOI":"10.18653\/v1\/W18-2703","article-title":"Iterative back-translation for neural machine translation","author":"Hoang","year":"2018","journal-title":"Proceedings of the 2nd Workshop on Neural Machine Translation and Generation"},{"key":"10.3233\/JIFS-230682_ref26","unstructured":"Zhang J. and Matsumoto T. , Corpus Augmentation by Sentence Segmentation for Low-Resource Neural Machine Translation, arXiv 2019, arXiv:1905.08945."},{"key":"10.3233\/JIFS-230682_ref27","doi-asserted-by":"crossref","first-page":"55","DOI":"10.18653\/v1\/W18-2707","article-title":"Enhancement of encoder and attention using target monolingual corpora in neural machine translation","author":"Imamura","year":"2018","journal-title":"Proceedings of the 2nd Workshop on Neural Machine Translation and Generation"},{"key":"10.3233\/JIFS-230682_ref28","doi-asserted-by":"crossref","unstructured":"Artetxe M. , Labaka G. , Agirre E. et al., Unsupervised neural machine translation[C], 6th International Conference on Learning Representations, ICLR 2018. 2018.","DOI":"10.18653\/v1\/D18-1399"},{"key":"10.3233\/JIFS-230682_ref29","unstructured":"Xie Z. , Wang S.I. , Li J. et al., Data Noising as Smoothing in Neural Network Language Models[J], 2016."},{"key":"10.3233\/JIFS-230682_ref30","first-page":"84","article-title":"Conditional BERT contextual augmentation","author":"Wu","year":"2019","journal-title":"Proceedings of the International Conference on Computational Science"},{"key":"10.3233\/JIFS-230682_ref31","first-page":"452","article-title":"Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations[C]","author":"Kobayashi","year":"2018","journal-title":"Proceedings of NAACL-HLT"},{"key":"10.3233\/JIFS-230682_ref32","doi-asserted-by":"crossref","first-page":"358","DOI":"10.18653\/v1\/2020.acl-main.34","article-title":"Content word aware neural machine translation,","author":"Chen","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"10.3233\/JIFS-230682_ref33","first-page":"48","article-title":"fairseq: A fast, extensible toolkit for sequence modeling","author":"Ott","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)"},{"key":"10.3233\/JIFS-230682_ref34","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural Machine Translation of Rare Words with Subword Units","author":"Sennrich","year":"2016","journal-title":"54th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL)"},{"key":"10.3233\/JIFS-230682_ref35","first-page":"5148","article-title":"Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model[C]","author":"Cheng","year":"2022","journal-title":"Proceedings of the 29th International Conference on Computational Linguistics"},{"key":"10.3233\/JIFS-230682_ref36","unstructured":"Werlen L.M. , Ram D. , Pappas N. et al., Document-Level Neural Machine Translation with Hierarchical Attention Networks[C], EMNLP 2018."},{"key":"10.3233\/JIFS-230682_ref37","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.18653\/v1\/2020.acl-main.147","article-title":"Enhancing Machine Translation with Dependency-Aware Self-Attention[C]","author":"Bugliarello","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"10.3233\/JIFS-230682_ref38","unstructured":"Kingma D.P. and Adam Ba J.L., A Method for Stochastic Optimization[J], 2015."},{"key":"10.3233\/JIFS-230682_ref39","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation[C]","author":"Papineni","year":"2002","journal-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics"},{"key":"10.3233\/JIFS-230682_ref40","doi-asserted-by":"crossref","first-page":"186","DOI":"10.18653\/v1\/W18-6319","article-title":"A Call for Clarity in Reporting BLEU Scores[C]","author":"Post","year":"2018","journal-title":"Proceedings of the Third Conference on Machine Translation: Research Papers"},{"issue":"1","key":"10.3233\/JIFS-230682_ref41","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1002\/int.22616","article-title":"Data augmentation for low-resource languages NMT guided by constrained sampling[J]","volume":"37","author":"Maimaiti","year":"2022","journal-title":"International Journal of Intelligent Systems"},{"key":"10.3233\/JIFS-230682_ref42","doi-asserted-by":"crossref","first-page":"2676","DOI":"10.18653\/v1\/P18-1249","article-title":"Constituency Parsing with a Self-Attentive Encoder[C]","volume":"1","author":"Kitaev","year":"2018","journal-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-230682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:45:53Z","timestamp":1777455953000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-230682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,2]]},"references-count":42,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/jifs-230682","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,2]]}}}