{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:05:05Z","timestamp":1775815505340,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819500192","type":"print"},{"value":"9789819500208","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-95-0020-8_41","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T09:18:27Z","timestamp":1753262307000},"page":"482-493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Advancing Low-Resource Machine Translation: A Unified Data Selection and Scoring Optimization Framework"],"prefix":"10.1007","author":[{"given":"Zhixiang","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peichen","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ding","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyu","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haochen","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mian","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angelos","family":"Stefanidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jionglong","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyong","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"41_CR1","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"140","key":"41_CR2","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"41_CR3","unstructured":"OpenAI.: GPT-4o System Card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"41_CR4","unstructured":"Lu, H., et al.: DeepSeek-VL: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525 (2024)"},{"key":"41_CR5","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"41_CR6","unstructured":"Song, Y., et al.: Is LLM the silver bullet to low-resource languages machine translation? arXiv preprint arXiv:2503.24102 (2025)"},{"issue":"3","key":"41_CR7","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1162\/coli_a_00446","volume":"48","author":"B Haddow","year":"2022","unstructured":"Haddow, B., Bawden, R., Miceli Barone, A.V., Helcl, J., Birch, A.: Survey of low-resource machine translation. Comput. Linguist. 48(3), 673\u2013732 (2022)","journal-title":"Comput. Linguist."},{"key":"41_CR8","unstructured":"Hedderich, M.A., Yates, A., Klakow, D., Nyamsuren, E.: A survey on recent approaches for low-resource neural machine translation. arXiv preprint arXiv:2204.05868 (2022)"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Zoph, B., Yuret, D., May, J., Knight, K.: Transfer learning for low-resource neural machine translation. arXiv preprint arXiv:1604.02201 (2016)","DOI":"10.18653\/v1\/D16-1163"},{"key":"41_CR10","unstructured":"Ding, Z., et al.: Foundation models for low-resource language education. arXiv preprint arXiv:2412.04774 (2024)"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2020)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Merx, R., Suominen, H., Correia, A.J.G., Cohn, T., Vylomova, E.: Low-resource machine translation: what for? Who for? An observational study on a dedicated tetun language translation service. arXiv preprint arXiv:2411.12262 (2024)","DOI":"10.18653\/v1\/2025.loresmt-1.7"},{"key":"41_CR13","unstructured":"Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 9147\u20139157. ACL (2020)"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Soto Martinez, W., Parmentier, Y., Gardent, C.: Generating from AMRs into high and low-resource languages using phylogenetic knowledge and hierarchical QLoRA training (HQL). In: Proceedings of the 17th International Natural Language Generation Conference (INLG 2024), pp. 70\u201381. ACL (2024)","DOI":"10.18653\/v1\/2024.inlg-main.7"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Pahwa, B.: BpHigh at WASSA 2023: using contrastive learning to build sentence transformer models for multi-class emotion classification in code-mixed Urdu. In: Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA), pp. 606\u2013610. Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.wassa-1.59"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3982\u20133992. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"41_CR17","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1162\/tacl_a_00447","volume":"10","author":"I Caswell","year":"2022","unstructured":"Caswell, I., Kreutzer, J., Wang, W.: Quality at a glance: an audit of web-crawled multilingual datasets. Trans. Assoc. Comput. Linguistics 10, 50\u201372 (2022)","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"41_CR18","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1162\/tacl_a_00330","volume":"8","author":"M Fomicheva","year":"2020","unstructured":"Fomicheva, M., et al.: Unsupervised quality estimation for neural machine translation. Trans. Assoc. Comput. Linguistics 8, 539\u2013555 (2020)","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Hu, M., et al.: Uncertainty-aware unlikelihood learning improves generative aspect sentiment quad prediction. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 13481\u201313494. Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.findings-acl.851"},{"key":"41_CR20","unstructured":"Zheng, Z., Zhang, Y., Liu, J., Huang, M.: Uncertainty-aware unlikelihood learning improves generative aspect sentiment quad prediction. arXiv preprint arXiv:2306.00418 (2023)"},{"issue":"13","key":"41_CR21","first-page":"13","volume":"68","author":"WH Gomaa","year":"2013","unstructured":"Gomaa, W.H., Fahmy, A.A.: A survey of text similarity approaches. Int. J. Comput. Appl. 68(13), 13\u201318 (2013)","journal-title":"Int. J. Comput. Appl."},{"key":"41_CR22","unstructured":"Nakov, P., Tiedemann, J., Hoang, H.T., Nanchen, A.: Findings of the WMT 2020 shared task on quality estimation. In: Proceedings of the Fifth Conference on Machine Translation (WMT), pp. 763\u2013777. Association for Computational Linguistics (2020)"},{"key":"41_CR23","unstructured":"Specia, L., Turchi, M., Cohn, T.: Estimating the sentence-level quality of machine translation systems. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp. 900\u2013908. Association for Computational Linguistics (2009)"},{"key":"41_CR24","unstructured":"Kunchukuttan, A., Bhattacharyya, P.: An Indian corpus for the evaluation of machine translation (ICEMT) and translationese. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC), European Language Resources Association (2018)"},{"key":"41_CR25","unstructured":"Specia, L., Turchi, M., Cohn, T.: QuEst - a translation quality estimation framework. In: Proceedings of the Seventh Workshop on Statistical Machine Translation (WMT), pp. 79\u201385. Association for Computational Linguistics (2013)"},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"van der Wees, M., Bisazza, A., Monz, C.: Dynamic data selection for neural machine translation. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1621\u20131631. Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/D17-1147"},{"key":"41_CR27","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2020)"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, pp. 785\u2013794. ACM (2016)","DOI":"10.1145\/2939672.2939785"},{"key":"41_CR29","unstructured":"Tiedemann, J.: Parallel data, tools and interfaces in OPUS. In: Calzolari, N., et al. (eds.) Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC), pp. 2214\u20132218. European Language Resources Association (ELRA), Istanbul (2012)"},{"key":"41_CR30","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 (ACL), pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"41_CR31","doi-asserted-by":"crossref","unstructured":"Post, M.: A call for clarity in reporting BLEU scores. In: Proceedings of the Third Conference on Machine Translation: Research Papers, pp. 186\u2013191. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/W18-6319"},{"issue":"1","key":"41_CR32","doi-asserted-by":"publisher","first-page":"79","DOI":"10.3354\/cr030079","volume":"30","author":"CJ Willmott","year":"2005","unstructured":"Willmott, C.J., Matsuura, K.: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 30(1), 79\u201382 (2005)","journal-title":"Clim. Res."},{"issue":"347\u2013352","key":"41_CR33","first-page":"240","volume":"58","author":"K Pearson","year":"1895","unstructured":"Pearson, K.: Note on regression and inheritance in the case of two parents. Proc. R. Soc. Lond. 58(347\u2013352), 240\u2013242 (1895)","journal-title":"Proc. R. Soc. Lond."},{"key":"41_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (NeurIPS 2017), pp. 5998\u20136008 (2017)"},{"issue":"107","key":"41_CR35","first-page":"1","volume":"22","author":"A Fan","year":"2021","unstructured":"Fan, A., Grangier, D., Auli, M.: Beyond English-centric multilingual machine translation. J. Mach. Learn. Res. 22(107), 1\u201348 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"41_CR36","unstructured":"NLLB Team, Costa-juss\u00e0, M.R., et al.: No language left behind: scaling human-centered machine translation. arXiv preprint arXiv:2207.04672 (2022)"},{"key":"41_CR37","unstructured":"Qwen Team: Qwen2.5 Technical report. arXiv preprint arXiv:2412.15115 (2024)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0020-8_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T19:46:42Z","timestamp":1757274402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0020-8_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500192","9789819500208"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0020-8_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}