{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T16:22:27Z","timestamp":1788798147638,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031705625","type":"print"},{"value":"9783031705632","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70563-2_6","type":"book-chapter","created":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T22:29:51Z","timestamp":1725143391000},"page":"71-84","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Continual Learning Under Language Shift"],"prefix":"10.1007","author":[{"given":"Evangelia","family":"Gogoulou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timoth\u00e9e","family":"Lesort","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Magnus","family":"Boman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joakim","family":"Nivre","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,1]]},"reference":[{"key":"6_CR1","unstructured":"Abnar, S., Dehghani, M., Neyshabur, B., Sedghi, H.: Exploring the limits of large scale pre-training. In: International Conference on Learning Representations (2021)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Aljundi, R., et al.: Online continual learning with maximal interfered retrieval. In: Advances in Neural Information Processing Systems (2019)","DOI":"10.1109\/CVPR.2019.01151"},{"key":"6_CR3","unstructured":"de\u00a0Masson\u00a0d\u2019Autume, C., Ruder, S., Kong, L., Yogatama, D.: Episodic memory in lifelong language learning. In: Advances in Neural Information Processing Systems (2019)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Badola, K., Dave, S., Talukdar, P.: Parameter-efficient finetuning for robust continual multilingual learning. arXiv preprint arXiv:2209.06767 (2022)","DOI":"10.18653\/v1\/2023.findings-acl.619"},{"key":"6_CR5","unstructured":"Barkarson, S., Steingr\u00edmsson, S., Hafsteinsd\u00f3ttir, H.: Evolving large text corpora: Four versions of the Icelandic Gigaword Corpus. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 2371\u20132381 (2022)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Blevins, T., Zettlemoyer, L.: Language contamination helps explains the cross-lingual capabilities of English pretrained models. In: Proceedings of the 2022 Conference on EMNLP (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.233"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: Proceedings of the 58th Annual Meeting of the ACL, pp. 8440\u20138451 (2020)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"6_CR8","unstructured":"Coria, J.M., et al.: Analyzing BERT cross-lingual transfer capabilities in continual sequence labeling. In: Proceedings of the First Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models, pp. 15\u201325. International Conference on Computational Linguistics (2022)"},{"key":"6_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. 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), pp. 4171\u20134186 (Jun 2019)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Douillard, A., Ram\u00e9, A., Couairon, G., Cord, M.: Dytox: transformers for continual learning with dynamic token expansion. arXiv preprint arXiv:2111.11326 (2021)","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"6_CR11","unstructured":"Ekgren, A., et al.: GPT-SW3: an autoregressive language model for the Nordic languages. arXiv preprint arXiv:2305.12987 (2023)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cognit. Sci. 128\u2013135 (1999)","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"6_CR13","unstructured":"Gao, L., et\u00a0al.: The Pile: an 800GB dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027 (2020)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Garcia, X., Constant, N., Parikh, A.P., Firat, O.: Towards continual learning for multilingual machine translation via vocabulary substitution. arXiv preprint arXiv:2103.06799 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.93"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Han, R., Ren, X., Peng, N.: ECONET: effective continual pretraining of language models for event temporal reasoning. In: EMNLP 2021, pp. 5367\u20135380 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.436"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Jang, J., et al.: TemporalWiki: a lifelong benchmark for training and evaluating ever-evolving language models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 6237\u20136250 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.418"},{"key":"6_CR17","unstructured":"Jiang, A.Q., et\u00a0al.: Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759 (2016)","DOI":"10.18653\/v1\/E17-2068"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Ke, Z., Shao, Y., Lin, H., Konishi, T., Kim, G., Liu, B.: Continual pre-training of language models. In: The Eleventh International Conference on Learning Representations (2023)","DOI":"10.18653\/v1\/2022.emnlp-main.695"},{"key":"6_CR20","unstructured":"Kummervold, P., Wetjen, F., de\u00a0la Rosa, J.: The Norwegian colossal corpus: a text corpus for training large Norwegian language models. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 3852\u20133860 (Jun 2022)"},{"key":"6_CR21","unstructured":"Lazaridou, A., et al..: Mind the gap: assessing temporal generalization in neural language models. In: Advances in Neural Information Processing Systems, pp. 29348\u201329363 (2021)"},{"key":"6_CR22","unstructured":"Lesort, T., et al..: Challenging common assumptions about catastrophic forgetting and knowledge accumulation. In: Chandar, S., Pascanu, R., Sedghi, H., Precup, D. (eds.) Proceedings of The 2nd Conference on Lifelong Learning Agents. Proceedings of Machine Learning Research, 22\u201325 Aug 2023, vol.\u00a0232, pp. 43\u201365. PMLR (2023). https:\/\/proceedings.mlr.press\/v232\/lesort23a.html"},{"key":"6_CR23","unstructured":"Lesort, T., Caccia, M., Rish, I.: Understanding continual learning settings with data distribution drift analysis. arXiv:2104.01678 (2021). https:\/\/arxiv.org\/abs\/2104.01678"},{"key":"6_CR24","unstructured":"Lin, X.V., et al.: Few-shot learning with multilingual generative language models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 9019\u20139052 (2022)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Littell, P., Mortensen, D.R., Lin, K., Kairis, K., Turner, C., Levin, L.: URIEL and lang2vec: representing languages as typological, geographical, and phylogenetic vectors. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pp. 8\u201314 (2017)","DOI":"10.18653\/v1\/E17-2002"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Loureiro, D., Barbieri, F., Neves, L., Espinosa\u00a0Anke, L., Camacho-collados, J.: TimeLMs: diachronic language models from Twitter. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations (2022)","DOI":"10.18653\/v1\/2022.acl-demo.25"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Magdalena\u00a0Biesialska, Katarzyna\u00a0Biesialska, M.R.C.J.: Continual lifelong learning in natural language processing: a survey. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 6523\u20136541 (2020)","DOI":"10.18653\/v1\/2020.coling-main.574"},{"key":"6_CR28","unstructured":"Mao, Y., et al.: Less-forgetting multi-lingual fine-tuning. In: Advances in Neural Information Processing Systems, pp. 14917\u201314928 (2022)"},{"key":"6_CR29","unstructured":"\u00d6hman, J., et al.: The Nordic Pile: A 1.2 TB Nordic dataset for language modeling. arXiv preprint arXiv:2303.17183 (2023)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Ortiz\u00a0Su\u00e1rez, P.J., Romary, L., Sagot, B.: A monolingual approach to contextualized word embeddings for mid-resource languages. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1703\u20131714 (2020)","DOI":"10.18653\/v1\/2020.acl-main.156"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual lifelong learning with neural networks: a review. Neural Networks 54 \u2013 71 (2019)","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Philippy, F., Guo, S., Haddadan, S.: Towards a common understanding of contributing factors for cross-lingual transfer in multilingual language models: a review. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5877\u20135891 (2023)","DOI":"10.18653\/v1\/2023.acl-long.323"},{"key":"6_CR33","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training. OpenAI (2018)"},{"key":"6_CR34","unstructured":"Ramasesh, V.V., Lewkowycz, A., Dyer, E.: Effect of scale on catastrophic forgetting in neural networks. In: International Conference on Learning Representations (2022)"},{"key":"6_CR35","unstructured":"Scao, T.L., et\u00a0al.: BLOOM: a 176B-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Scialom, T., Chakrabarty, T., Muresan, S.: Fine-tuned language models are continual learners. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 6107\u20136122 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.410"},{"key":"6_CR37","unstructured":"Stollenwerk, F.: Training and evaluation of a multilingual tokenizer for GPT-SW3. arXiv preprint arXiv:2304.14780 (2023)"},{"key":"6_CR38","unstructured":"Str\u00f8mberg-Derczynski, L., et al.: The Danish Gigaword corpus. In: Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), pp. 413\u2013421 (2021)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Winata, G.I., et al..: Overcoming catastrophic forgetting in massively multilingual continual learning. arXiv preprint arXiv:2305.16252 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.48"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: mT5: a massively multilingual pre-trained text-to-text transformer. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 483\u2013498 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.41"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70563-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T22:33:10Z","timestamp":1725143590000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70563-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705625","9783031705632"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70563-2_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brno","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"9 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.tsdconference.org\/tsd2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}