{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:06:06Z","timestamp":1743069966430,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031780134"},{"type":"electronic","value":"9783031780141"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-78014-1_22","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T12:23:48Z","timestamp":1732191828000},"page":"295-307","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing Knowledge Distillation for\u00a0Enhanced Text-to-Text Translation in\u00a0Low-Resource Languages"],"prefix":"10.1007","author":[{"given":"Manar","family":"Ouled Ahmed","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1094-3112","authenticated-orcid":false,"given":"Zuheng","family":"Ming","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3442-0578","authenticated-orcid":false,"given":"Alice","family":"Othmani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"22_CR1","unstructured":"Adhikari, A., Ram, A., Tang, R., Lin, J.: DocBERT: BERT for document classification. arXiv preprint arXiv:1904.08398 (2019)"},{"key":"22_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"issue":"D1","key":"22_CR3","doi-asserted-by":"publisher","first-page":"D296","DOI":"10.1093\/nar\/gkx1067","volume":"46","author":"CH Chou","year":"2018","unstructured":"Chou, C.H., et al.: miRTarbase update 2018: a resource for experimentally validated microRNA-target interactions. Nucleic Acids Res. 46(D1), D296\u2013D302 (2018)","journal-title":"Nucleic Acids Res."},{"key":"22_CR4","volume-title":"The Translanguaging Classroom: Leveraging Student Bilingualism for Learning","author":"O Garc\u00eda","year":"2017","unstructured":"Garc\u00eda, O., Johnson, S.I., Seltzer, K., Vald\u00e9s, G.: The Translanguaging Classroom: Leveraging Student Bilingualism for Learning. Caslon Philadelphia, PA (2017)"},{"key":"22_CR5","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"22_CR6","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"issue":"10","key":"22_CR7","doi-asserted-by":"publisher","first-page":"e3000385","DOI":"10.1371\/journal.pbio.3000385","volume":"17","author":"BI Hutchins","year":"2019","unstructured":"Hutchins, B.I., et al.: The NIH open citation collection: a public access, broad coverage resource. PLoS Biol. 17(10), e3000385 (2019)","journal-title":"PLoS Biol."},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Jia, Y., Ding, Y., Bapna, A., Cherry, C., Zhang, Y., Conneau, A., Morioka, N.: Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation. arXiv preprint arXiv:2203.13339 (2022)","DOI":"10.21437\/Interspeech.2022-10938"},{"key":"22_CR9","unstructured":"Joulin, A., Ciss\u00e9, M., Grangier, D., J\u00e9gou, H., et\u00a0al.: Efficient softmax approximation for GPUs. In: International conference on machine learning, pp. 1302\u20131310. PMLR (2017)"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Kim, Y., Rush, A.M.: Sequence-level knowledge distillation. arXiv preprint arXiv:1606.07947 (2016)","DOI":"10.18653\/v1\/D16-1139"},{"issue":"13","key":"22_CR11","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Koehn, P.: Statistical Machine Translation. Cambridge University Press (2009)","DOI":"10.1017\/CBO9780511815829"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. nature 521(7553), 436\u2013444 (2015)","DOI":"10.1038\/nature14539"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"22_CR15","unstructured":"Li, B., et al.: Shallow-to-deep training for neural machine translation. arXiv preprint arXiv:2010.03737 (2020)"},{"key":"22_CR16","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. Trans. Assoc. Comput. Linguist. 8, 726\u2013742 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation, vol.\u00a024, pp. 109\u2013165. Elsevier (1989)","DOI":"10.1016\/S0079-7421(08)60536-8"},{"key":"22_CR18","unstructured":"Molchanov, D., Ashukha, A., Vetrov, D.: Variational dropout sparsifies deep neural networks. In: International Conference on Machine Learning, pp. 2498\u20132507. PMLR (2017)"},{"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: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"22_CR20","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Schoneveld, L., Othmani, A.: Towards a general deep feature extractor for facial expression recognition. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 2339\u20132342 (2021)","DOI":"10.1109\/ICIP42928.2021.9506025"},{"key":"22_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patrec.2021.03.007","volume":"146","author":"L Schoneveld","year":"2021","unstructured":"Schoneveld, L., Othmani, A., Abdelkawy, H.: Leveraging recent advances in deep learning for audio-visual emotion recognition. Pattern Recogn. Lett. 146, 1\u20137 (2021)","journal-title":"Pattern Recogn. Lett."},{"issue":"Suppl 2","key":"22_CR23","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11577-017-0454-1","volume":"69","author":"J Schoonenboom","year":"2017","unstructured":"Schoonenboom, J., Johnson, R.B.: How to construct a mixed methods research design. Kolner Zeitschrift fur Soziologie und Sozialpsychologie 69(Suppl 2), 107 (2017)","journal-title":"Kolner Zeitschrift fur Soziologie und Sozialpsychologie"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Edinburgh neural machine translation systems for wmt 16. arXiv preprint arXiv:1606.02891 (2016)","DOI":"10.18653\/v1\/W16-2323"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for modern deep learning research. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 13693\u201313696 (2020)","DOI":"10.1609\/aaai.v34i09.7123"},{"key":"22_CR26","unstructured":"Tang, R., Lu, Y., Liu, L., Mou, L., Vechtomova, O., Lin, J.: Distilling task-specific knowledge from BERT into simple neural networks. arXiv preprint arXiv:1903.12136 (2019)"},{"key":"22_CR27","unstructured":"Tiedemann, J.: The tatoeba translation challenge\u2013realistic data sets for low resource and multilingual MT. arXiv preprint arXiv:2010.06354 (2020)"},{"key":"22_CR28","unstructured":"Tiedemann, J., Nygaard, L.: The opus corpus-parallel and free: http:\/\/logos.uio.no\/opus. In: Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC\u201904) (2004)"},{"key":"22_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"22_CR30","unstructured":"Wang, Q., et al.: Learning deep transformer models for machine translation. arXiv preprint arXiv:1906.01787 (2019)"},{"key":"22_CR31","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"22_CR32","unstructured":"Xu, C., et al.: Recent advances in direct speech-to-text translation. arXiv preprint arXiv:2306.11646 (2023)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Zafar, M., Castaldo, A., Nayak, P., Haque, R., Gajakos, N., Way, A.: The SETU-DCU submissions to IWSLT 2024 low-resource speech-to-text translation tasks. In: Salesky, E., Federico, M., Carpuat, M. (eds.) Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pp. 80\u201385. Association for Computational Linguistics, Bangkok, Thailand (in-person and online) (Aug 2024), https:\/\/aclanthology.org\/2024.iwslt-1.12","DOI":"10.18653\/v1\/2024.iwslt-1.12"},{"key":"22_CR34","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1016\/j.ijid.2020.05.055","volume":"96","author":"F Zeng","year":"2020","unstructured":"Zeng, F., et al.: Association of inflammatory markers with the severity of COVID-19: a meta-analysis. Int. J. Infect. Dis. 96, 467\u2013474 (2020)","journal-title":"Int. J. Infect. Dis."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78014-1_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:07:57Z","timestamp":1736348877000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78014-1_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031780134","9783031780141"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78014-1_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}