{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:53:02Z","timestamp":1742914382444,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"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_22","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:28:10Z","timestamp":1730392090000},"page":"280-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Pruning Residual Networks in\u00a0Multilingual Neural Machine Translation to\u00a0Improve Zero-Shot Translation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6327-9171","authenticated-orcid":false,"given":"Kaiwen","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2639-3944","authenticated-orcid":false,"given":"Yating","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4110-3976","authenticated-orcid":false,"given":"Rui","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3082-648X","authenticated-orcid":false,"given":"Bo","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6685-0858","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2867-1765","authenticated-orcid":false,"given":"Xi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6660-8989","authenticated-orcid":false,"given":"Ahtamjan","family":"Ahmat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"22_CR1","series-title":"Springer Theses","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/978-981-32-9748-7_4","volume-title":"Joint Training for Neural Machine Translation","author":"Y Cheng","year":"2019","unstructured":"Cheng, Y.: Joint training for pivot-based neural machine translation. In: Joint Training for Neural Machine Translation. ST, pp. 41\u201354. Springer, Singapore (2019). https:\/\/doi.org\/10.1007\/978-981-32-9748-7_4"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Dong, D., Wu, H., He, W., Yu, D., Wang, H.: Multi-task learning for multiple language translation. In: Association for Computational Linguistics, Beijing, pp. 1723\u20131732 (2015)","DOI":"10.3115\/v1\/P15-1166"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Firat, O., Cho, K., Bengio, Y.: Multi-way, multilingual neural machine translation with a shared attention mechanism. In: Association for Computational Linguistics, San Diego, pp. 866\u2013875. (2016)","DOI":"10.18653\/v1\/N16-1101"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Firat, O., Sankaran, B., Al-onaizan, Y., Yarman\u00a0Vural, F.T., Cho, K.: Zero-resource translation with multi-lingual neural machine translation. In: Association for Computational Linguistics, Austin, pp. 268\u2013277 (2016)","DOI":"10.18653\/v1\/D16-1026"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Gao, P., Zhang, L.: Improving zero-shot multilingual neural machine translation by leveraging cross-lingual consistency regularization (2023)","DOI":"10.18653\/v1\/2023.findings-acl.766"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Gu, J., Wang, Y., Cho, K., Li, V.O.: Improved zero-shot neural machine translation via ignoring spurious correlations. In: Association for Computational Linguistics, pp. 1258\u20131268 (2019)","DOI":"10.18653\/v1\/P19-1121"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Gu, S., Feng, Y.: Improving zero-shot multilingual translation with universal representations and cross-mapping. In: Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 6492\u20136504 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.485"},{"key":"22_CR8","unstructured":"Ha, T.L., Niehues, J., Waibel, A.: Toward multilingual neural machine translation with universal encoder and decoder. In: International Workshop on Spoken Language Translation, Seattle (2016)"},{"key":"22_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"22_CR10","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)"},{"key":"22_CR11","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"22_CR12","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.: Google\u2019s multilingual neural machine translation system: enabling zero-shot translation. Trans. Assoc. Comput. Linguist. 5, 339\u2013351 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"22_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"22_CR14","unstructured":"Koehn, P.: Europarl: a parallel corpus for statistical machine translation. In: Proceedings of Machine Translation Summit X: Papers, Phuket, pp. 79\u201386 (2005)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Kudugunta, S., Bapna, A., Caswell, I., Firat, O.: Investigating multilingual NMT representations at scale. In: Conference on Empirical Methods in Natural Language Processing, pp. 1565\u20131575. Association for Computational Linguistics, Hong Kong (2019)","DOI":"10.18653\/v1\/D19-1167"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Liu, D., Niehues, J., Cross, J., Guzm\u00e1n, F., Li, X.: Improving zero-shot translation by disentangling positional information. In: Association for Computational Linguistics, pp. 1259\u20131273 (2021)","DOI":"10.18653\/v1\/2021.acl-long.101"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Lu, Y., Keung, P., Ladhak, F., Bhardwaj, V., Zhang, S., Sun, J.: A neural interlingua for multilingual machine translation. In: Association for Computational Linguistics, Brussels, pp. 84\u201392 (2018)","DOI":"10.18653\/v1\/W18-6309"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Ott, M., et al.: fairseq: a fast, extensible toolkit for sequence modeling. arXiv preprint arXiv:1904.01038 (2019)","DOI":"10.18653\/v1\/N19-4009"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Association for Computational Linguistics, Philadelphia, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Qi, Y., Sachan, D., Felix, M., Padmanabhan, S., Neubig, G.: When and why are pre-trained word embeddings useful for neural machine translation? In: Association for Computational Linguistics, New Orleans, pp. 529\u2013535 (2018)","DOI":"10.18653\/v1\/N18-2084"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Association for Computational Linguistics, Berlin, pp. 1715\u20131725 (2016)","DOI":"10.18653\/v1\/P16-1162"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Tan, S., Monz, C.: Towards a better understanding of variations in zero-shot neural machine translation performance. In: The 2023 Conference on Empirical Methods in Natural Language Processing (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.836"},{"key":"22_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"22_CR24","unstructured":"Veit, A., Wilber, M.J., Belongie, S.: Residual networks behave like ensembles of relatively shallow networks. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhang, Z.: Rethinking zero-shot neural machine translation: from a perspective of latent variables. In: EMNLP 2021, Punta Cana, pp. 4321\u20134327 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.366"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Wang, W., Tu, Z.: Rethinking the value of transformer components. In: Proceedings of the 28th International Conference on Computational Linguistics, Barcelona (Online), pp. 6019\u20136029 (2020)","DOI":"10.18653\/v1\/2020.coling-main.529"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yang, Y.: ASCM: an answer space clustered prompting method without answer engineering. In: ACL 2022, Dublin (2022)","DOI":"10.18653\/v1\/2022.findings-acl.193"},{"key":"22_CR28","unstructured":"Ziemski, M., Junczys-Dowmunt, M., Pouliquen, B.: The United Nations parallel corpus v1.0. In: European Language Resources Association (ELRA), Portoro\u017e, pp. 3530\u20133534 (2016)"}],"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_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:31:35Z","timestamp":1730392295000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9437-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794362","9789819794379"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9437-9_22","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"}}]}}