{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:44:20Z","timestamp":1742913860538,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794362"},{"type":"electronic","value":"9789819794379"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-9437-9_18","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:27:22Z","timestamp":1730392042000},"page":"227-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Understanding and\u00a0Improving Low-Resource Neural Machine Translation with\u00a0Shallow Features"],"prefix":"10.1007","author":[{"given":"Yanming","family":"Sun","sequence":"first","affiliation":[]},{"given":"Xuebo","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Derek F.","family":"Wong","sequence":"additional","affiliation":[]},{"given":"Yuchu","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Bei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Runzhe","family":"Zhan","sequence":"additional","affiliation":[]},{"given":"Lidia S.","family":"Chao","sequence":"additional","affiliation":[]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"18_CR1","unstructured":"Abbott, J., Martinus, L.: Benchmarking neural machine translation for Southern African languages. In: Proceedings of the 2019 Workshop on Widening NLP (2019)"},{"key":"18_CR2","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/s10590-021-09284-y","volume":"35","author":"I Abdulmumin","year":"2021","unstructured":"Abdulmumin, I., Galadanci, B.S., Garba, A.: Tag-less back-translation. Mach. Transl. 35, 519\u2013549 (2021)","journal-title":"Mach. Transl."},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Baziotis, C., Haddow, B., Birch, A.: Language model prior for low-resource neural machine translation. In: Proceedings of EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.615"},{"key":"18_CR4","unstructured":"Biljon, E.V., Pretorius, A., Kreutzer, J.: On optimal transformer depth for low-resource language translation. CoRR (2020)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Domhan, T., Hieber, F.: Using target-side monolingual data for neural machine translation through multi-task learning. In: Proceedings of EMNLP (2017)","DOI":"10.18653\/v1\/D17-1158"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Fadaee, M., Bisazza, A., Monz, C.: Data augmentation for low-resource neural machine translation. In: Proceedings of ACL (Volume 2: Short Papers) (2017)","DOI":"10.18653\/v1\/P17-2090"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Kambhatla, N., Born, L., Sarkar, A.: CipherDAug: ciphertext based data augmentation for neural machine translation. In: Proceedings of ACL (2022)","DOI":"10.18653\/v1\/2022.acl-long.17"},{"key":"18_CR8","unstructured":"Kasai, J., Pappas, N., Peng, H., Cross, J., Smith, N.A.: Deep encoder, shallow decoder: reevaluating non-autoregressive machine translation. In: 9th ICLR (2021)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Kim, Y., Rush, A.M.: Sequence-level knowledge distillation. In: Proceedings of EMNLP (2016)","DOI":"10.18653\/v1\/D16-1139"},{"key":"18_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd ICLR (2015)"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Kong, X., Renduchintala, A., Cross, J., Tang, Y., Gu, J., Li, X.: Multilingual neural machine translation with deep encoder and multiple shallow decoders. In: Proceedings of EACL: Main Volume (2021)","DOI":"10.18653\/v1\/2021.eacl-main.138"},{"key":"18_CR12","unstructured":"Lample, G., Conneau, A., Denoyer, L., Ranzato, M.: Unsupervised machine translation using monolingual corpora only. In: 6th ICLR (2018)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Li, B., et al.: Shallow-to-deep training for neural machine translation. In: Proceedings of EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.72"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, X., Wong, D.F., Chao, L.S., Zhang, M.: ConsistTL: modeling consistency in transfer learning for low-resource neural machine translation. In: Proceedings of EMNLP (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.574"},{"key":"18_CR15","unstructured":"Liang, X., et al.: R-Drop: regularized dropout for neural networks. In: NIPS (2021)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Liu, L., Liu, X., Gao, J., Chen, W., Han, J.: Understanding the difficulty of training transformers. In: Proceedings of EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.463"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: KNN-TL: K-nearest-neighbor transfer learning for low-resource neural machine translation. In: Proceedings of ACL (2023)","DOI":"10.18653\/v1\/2023.acl-long.105"},{"key":"18_CR18","unstructured":"Liu, X., Duh, K., Liu, L., Gao, J.: Very deep transformers for neural machine translation. CoRR (2020)"},{"key":"18_CR19","unstructured":"Liu, X., Wang, L., Wong, D.F., Ding, L., Chao, L.S., Tu, Z.: Understanding and improving encoder layer fusion in sequence-to-sequence learning. In: 9th ICLR (2021)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Marie, B., Rubino, R., Fujita, A.: Tagged back-translation revisited: why does it really work? In: Proceedings of ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.532"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Meng, F., Zhang, J.: DTMT: a novel deep transition architecture for neural machine translation. In: The Thirty-Third AAAI (2019)","DOI":"10.1609\/aaai.v33i01.3301224"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Miceli\u00a0Barone, A.V., Helcl, J., Sennrich, R., Haddow, B., Birch, A.: Deep architectures for neural machine translation. In: Proceedings of WMT (2017)","DOI":"10.18653\/v1\/W17-4710"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Ott, M., et al.: fairseq: a fast, extensible toolkit for sequence modeling. In: Proceedings of NAACL (Demonstrations) (2019)","DOI":"10.18653\/v1\/N19-4009"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Ramachandran, P., Liu, P., Le, Q.: Unsupervised pretraining for sequence to sequence learning. In: Proceedings of EMNLP (2017)","DOI":"10.18653\/v1\/D17-1039"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Riley, P., Caswell, I., Freitag, M., Grangier, D.: Translationese as a language in \u201cmultilingual\u201d NMT. In: Proceedings of ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.691"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez-Cartagena, V.M., Espl\u00e0-Gomis, M., P\u00e9rez-Ortiz, J.A., S\u00e1nchez-Mart\u00ednez, F.: Rethinking data augmentation for low-resource neural machine translation: a multi-task learning approach. In: Proceedings of EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.669"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. In: Proceedings of ACL (2016)","DOI":"10.18653\/v1\/P16-1009"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of ACL (2016)","DOI":"10.18653\/v1\/P16-1162"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Zhang, B.: Revisiting low-resource neural machine translation: a case study. In: Proceedings of ACL (2019)","DOI":"10.18653\/v1\/P19-1021"},{"key":"18_CR31","unstructured":"Snover, M., Dorr, B., Schwartz, R., Micciulla, L., Makhoul, J.: A study of translation edit rate with targeted human annotation. In: Proceedings of AMTA: Technical Papers (2006)"},{"key":"18_CR32","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS (2014)"},{"key":"18_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Learning deep transformer models for machine translation. In: Proceedings of ACL (2019)","DOI":"10.18653\/v1\/P19-1176"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Weng, R., Yu, H., Luo, W., Zhang, M.: Deep fusing pre-trained models into neural machine translation. In: Proceedings of AAAI (2022)","DOI":"10.1609\/aaai.v36i10.21399"},{"key":"18_CR36","unstructured":"Xiong, R., et al.: On layer normalization in the transformer architecture. In: Proceedings of ICML (2020)"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Zhan, R., Liu, X., Wong, D.F., Chao, L.S.: Meta-curriculum learning for domain adaptation in neural machine translation. In: The Thirty-Fifth AAAI (2021)","DOI":"10.1609\/aaai.v35i16.17683"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zong, C.: Exploiting source-side monolingual data in neural machine translation. In: Proceedings of EMNLP (2016)","DOI":"10.18653\/v1\/D16-1160"},{"key":"18_CR39","unstructured":"Zhou, C., Gu, J., Neubig, G.: Understanding knowledge distillation in non-autoregressive machine translation. In: 8th ICLR (2020)"},{"key":"18_CR40","unstructured":"Zhu, J., et al.: Incorporating BERT into neural machine translation. In: 8th ICLR (2020)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9437-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:30:06Z","timestamp":1730392206000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9437-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794362","9789819794379"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9437-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}