{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T01:36:12Z","timestamp":1771464972850,"version":"3.50.1"},"reference-count":49,"publisher":"Cambridge University Press (CUP)","issue":"3","license":[{"start":{"date-parts":[[2020,6,17]],"date-time":"2020-06-17T00:00:00Z","timestamp":1592352000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Nat. Lang. Eng."],"published-print":{"date-parts":[[2021,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Neural machine translation (NMT) has recently shown promising results on publicly available benchmark datasets and is being rapidly adopted in various production systems. However, it requires high-quality large-scale parallel corpus, and it is not always possible to have sufficiently large corpus as it requires time, money, and professionals. Hence, many existing large-scale parallel corpus are limited to the specific languages and domains. In this paper, we propose an effective approach to improve an NMT system in low-resource scenario without using any additional data. Our approach aims at augmenting the original training data by means of parallel phrases extracted from the original training data itself using a statistical machine translation (SMT) system. Our proposed approach is based on the gated recurrent unit (GRU) and transformer networks. We choose the Hindi\u2013English, Hindi\u2013Bengali datasets for Health, Tourism, and Judicial (only for Hindi\u2013English) domains. We train our NMT models for 10 translation directions, each using only 5\u201323k parallel sentences. Experiments show the improvements in the range of 1.38\u201315.36 BiLingual Evaluation Understudy points over the baseline systems. Experiments show that transformer models perform better than GRU models in low-resource scenarios. In addition to that, we also find that our proposed method outperforms SMT\u2014which is known to work better than the neural models in low-resource scenarios\u2014for some translation directions. In order to further show the effectiveness of our proposed model, we also employ our approach to another interesting NMT task, for example, old-to-modern English translation, using a tiny parallel corpus of only 2.7K sentences. For this task, we use publicly available old-modern English text which is approximately 1000 years old. Evaluation for this task shows significant improvement over the baseline NMT.<\/jats:p>","DOI":"10.1017\/s1351324920000303","type":"journal-article","created":{"date-parts":[[2020,6,17]],"date-time":"2020-06-17T06:08:38Z","timestamp":1592374118000},"page":"271-292","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":23,"title":["Neural machine translation of low-resource languages using SMT phrase pair injection"],"prefix":"10.1017","volume":"27","author":[{"given":"Sukanta","family":"Sen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed","family":"Hasanuzzaman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asif","family":"Ekbal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pushpak","family":"Bhattacharyya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andy","family":"Way","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"56","published-online":{"date-parts":[[2020,6,17]]},"reference":[{"key":"S1351324920000303_ref30","doi-asserted-by":"crossref","unstructured":"Papineni, K. , Roukos, S. , Ward, T. and Zhu, W.-J. (2002). BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, Philadelphia, Pennsylvania, pp. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"S1351324920000303_ref42","doi-asserted-by":"crossref","unstructured":"Wang, X. , Lu, Z. , Tu, Z. , Li, H. , Xiong, D. and Zhang, M. (2017). Neural machine translation advised by statistical machine translation. In Thirty-First AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v31i1.10975"},{"key":"S1351324920000303_ref34","unstructured":"Sen, S. , Hasanuzzaman, M. , Ekbal, A. , Bhattacharyya, P. and Way, A. (in press). Take help from elder brother: old to modern english nmt with phrase pair feedback. In Proceedings of the International Conference on Computational Linguistics and Intelligent Text Processing."},{"key":"S1351324920000303_ref39","unstructured":"Sutskever, I. , Vinyals, O. and Le, Q.V. (2014). Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems, pp. 3104\u20133112."},{"key":"S1351324920000303_ref22","unstructured":"Koehn, P. (2004). Statistical significance tests for machine translation evaluation. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing."},{"key":"S1351324920000303_ref19","unstructured":"Kalchbrenner, N. and Blunsom, P. (2013). Recurrent continuous translation models. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1700\u20131709."},{"key":"S1351324920000303_ref31","unstructured":"Paszke, A. , Gross, S. , Chintala, S. , Chanan, G. , Yang, E. , DeVito, Z. , Lin, Z. , Desmaison, A. , Antiga, L. and Lerer, A. (2017). Automatic differentiation in pytorch. In NIPS 2017 Autodiff Workshop: The Future of Gradient-based Machine Learning Software and Techniques."},{"key":"S1351324920000303_ref33","doi-asserted-by":"crossref","unstructured":"Ren, S. , Zhang, Z. , Liu, S. , Zhou, M. and Ma, S. (2019). Unsupervised neural machine translation with smt as posterior regularization. arXiv preprint arXiv:1901.04112.","DOI":"10.1609\/aaai.v33i01.3301241"},{"key":"S1351324920000303_ref3","unstructured":"Bahdanau, D. , Cho, K. and Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. In International Conference on Learning Representation (ICLR)."},{"key":"S1351324920000303_ref29","unstructured":"Niehues, J. , Cho, E. , Ha, T.-L. and Waibel, A. (2016). Pre-translation for neural machine translation. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Osaka, Japan. The COLING 2016 Organizing Committee, pp. 1828\u20131836."},{"key":"S1351324920000303_ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/641"},{"key":"S1351324920000303_ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1100"},{"key":"S1351324920000303_ref17","unstructured":"Jha, G.N. (2010). The tdil program and the indian langauge corpora intitiative (ilci). In LREC."},{"key":"S1351324920000303_ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"S1351324920000303_ref28","doi-asserted-by":"crossref","unstructured":"Lample, G. , Ott, M. , Conneau, A. , Denoyer, L. and Ranzato, M. (2018). Phrase-based & neural unsupervised machine translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium. Association for Computational Linguistics, pp. 5039\u20135049.","DOI":"10.18653\/v1\/D18-1549"},{"key":"S1351324920000303_ref5","unstructured":"Bojar, O. , Diatka, V. , Stran\u00e1k, P. , Suchomel, V. , Tamchyna, A. and Zeman, D. (2014). Hindencorp-hindi-english and hindi-only corpus for machine translation. In LREC, pp. 3550\u20133555."},{"key":"S1351324920000303_ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-3017"},{"key":"S1351324920000303_ref20","unstructured":"Kingma, D.P. and Ba, J. (2015). Adam: a method for stochastic optimization. In International Conference on Learning Representation (ICLR)."},{"key":"S1351324920000303_ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.014"},{"key":"S1351324920000303_ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1163"},{"key":"S1351324920000303_ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1160"},{"key":"S1351324920000303_ref38","unstructured":"Song, K. , Zhang, Y. , Yu, H. , Luo, W. , Wang, K. and Zhang, M. (2019). Code-switching for enhancing NMT with pre-specified 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), Minneapolis, Minnesota. Association for Computational Linguistics, pp. 449\u2013459."},{"key":"S1351324920000303_ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2860287"},{"key":"S1351324920000303_ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073462"},{"key":"S1351324920000303_ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"S1351324920000303_ref27","unstructured":"Lample, G. and Conneau, A. (2019). Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291."},{"key":"S1351324920000303_ref13","doi-asserted-by":"crossref","unstructured":"He, W. , He, Z. , Wu, H. and Wang, H. (2016). Improved neural machine translation with smt features. In Thirtieth AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v30i1.9983"},{"key":"S1351324920000303_ref7","unstructured":"Crego, J. , Kim, J. , Klein, G. , Rebollo, A. , Yang, K. , Senellart, J. , Akhanov, E. , Brunelle, P. , Coquard, A. , Deng, Y. , Enoue, S. , Geiss, C. , Johanson, J. , Khalsa, A. , Khiari, R. , Ko, B. , Kobus, C. , Lorieux, J. , Martins, L. , Nguyen, D.-C. , Priori, A. , Riccardi, T. , Segal, N. , Servan, C. , Tiquet, C. , Wang, B. , Yang, J. , Zhang, D. , Zhou, J. and Zoldan, P. et al. (2016). Systran\u2019s pure neural machine translation systems. arXiv preprint arXiv:1610.05540."},{"key":"S1351324920000303_ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3204"},{"key":"S1351324920000303_ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2301"},{"key":"S1351324920000303_ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0032504"},{"key":"S1351324920000303_ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1399"},{"key":"S1351324920000303_ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1039"},{"key":"S1351324920000303_ref23","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"S1351324920000303_ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"S1351324920000303_ref45","unstructured":"Wu, Y. , Schuster, M. , Chen, Z. , Le, Q.V. , Norouzi, M. , Macherey, W. , Krikun, M. , Cao, Y. , Gao, Q. , Macherey, K. , Klingner, J. , Shah, A. , Johnson, M. , Liu, X. , Kaiser, U. , Gouws, S. , Kato, Y. , Kudo, T. , Kazawa, H. , Stevens, K. , Kurian, G. , Patil, N. , Wang, W. , Young, C. , Smith, J. , Riesa, J. , Rudnick, A. , Vinyals, O. , Corrado, G. , Hughes, M. and Dean, J. (2016). Google\u2019s neural machine translation system: bridging the gap between human and machine translation. CoRR ."},{"key":"S1351324920000303_ref15","unstructured":"Hieber, F. , Domhan, T. , Denkowski, M. , Vilar, D. , Sokolov, A. , Clifton, A. and Post, M. (2017). Sockeye: a toolkit for neural machine translation. arXiv preprint arXiv:1712.05690."},{"key":"S1351324920000303_ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1162"},{"key":"S1351324920000303_ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"S1351324920000303_ref40","unstructured":"Tang, Y. , Meng, F. , Lu, Z. , Li, H. and Yu, P.L. (2016). Neural machine translation with external phrase memory. arXiv preprint arXiv:1606.01792."},{"key":"S1351324920000303_ref41","unstructured":"Vaswani, A. , Shazeer, N. , Parmar, N. , Uszkoreit, J. , Jones, L. , Gomez, A.N. , Kaiser, \u0141. and Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, pp. 5998\u20136008."},{"key":"S1351324920000303_ref47","doi-asserted-by":"crossref","unstructured":"Zhang, Z. , Liu, S. , Li, M. , Zhou, M. and Chen, E. (2018). Joint training for neural machine translation models with monolingual data. In Thirty-Second AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v32i1.11248"},{"key":"S1351324920000303_ref12","doi-asserted-by":"crossref","unstructured":"Guzm\u00e1n, F. , Chen, P.-J. , Ott, M. , Pino, J. , Lample, G. , Koehn, P. , Chaudhary, V. and Ranzato, M. (2019). Two new evaluation datasets for low-resource machine translation: Nepali-English and Sinhala-English. arXiv preprint arXiv:1902.01382.","DOI":"10.18653\/v1\/D19-1632"},{"key":"S1351324920000303_ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1146"},{"key":"S1351324920000303_ref18","unstructured":"Junczys-Dowmunt, M. , Dwojak, T. and Hoang, H. (2016). Is neural machine translation ready for deployment? a case study on 30 translation directions. In Proceedings of the International Workshop on Spoken Language Translation (IWSLT)."},{"key":"S1351324920000303_ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"S1351324920000303_ref26","unstructured":"Kunchukuttan, A. , Mehta, P. and Bhattacharyya, P. (2018). The IIT Bombay English-Hindi parallel corpus. In Calzolari N., Choukri K., Cieri C., Declerck T., Goggi S., Hasida K., Isahara H., Maegaard B., Mariani J., Mazo H., Moreno A., Odijk J., Piperidis S. and Tokunaga T. (eds), Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Paris, France. European Language Resources Association (ELRA)."},{"key":"S1351324920000303_ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2090"},{"key":"S1351324920000303_ref14","unstructured":"Heafield, K. (2011). Kenlm: faster and smaller language model queries. In Proceedings of the Sixth Workshop on Statistical Machine Translation. Association for Computational Linguistics, pp. 187\u2013197."}],"container-title":["Natural Language Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1351324920000303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T23:19:02Z","timestamp":1666999142000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1351324920000303\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,17]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["S1351324920000303"],"URL":"https:\/\/doi.org\/10.1017\/s1351324920000303","relation":{},"ISSN":["1351-3249","1469-8110"],"issn-type":[{"value":"1351-3249","type":"print"},{"value":"1469-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,17]]},"assertion":[{"value":"\u00a9 The Author(s), 2020. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}]}}