{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:05:35Z","timestamp":1757617535543,"version":"3.44.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T00:00:00Z","timestamp":1740355200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T00:00:00Z","timestamp":1740355200000},"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":["AI &amp; Soc"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00146-025-02223-y","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T14:52:21Z","timestamp":1740408741000},"page":"4461-4471","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning methods for isolating indigenous language catalog descriptions"],"prefix":"10.1007","volume":"40","author":[{"given":"Yi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carrie","family":"Heitman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leen-Kiat","family":"Soh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Whiteley","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,24]]},"reference":[{"key":"2223_CR1","doi-asserted-by":"crossref","unstructured":"Allison-Cassin S, Callison C (2023) The Respectful Terminologies Platform Project and Envisioning Indigenous Governance. In: Proceedings of the Annual Conference of CAIS\/Actes Du Congr\u00e8s Annuel de l\u2019ACSI. http:\/\/hdl.handle.net\/10222\/83247","DOI":"10.29173\/cais1854"},{"key":"2223_CR2","doi-asserted-by":"publisher","DOI":"10.1515\/9780748628889","author":"G Aston","year":"2022","unstructured":"Aston G, Burnard L (2022) The BNC handbook: exploring the British national corpus with SARA. Edinburgh University Press. https:\/\/doi.org\/10.1515\/9780748628889","journal-title":"Edinburgh University Press"},{"key":"2223_CR3","unstructured":"Baldwin T, Lui M (2010) Language identification: The long and the short of the matter. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 229\u2013237. https:\/\/aclanthology.org\/N10-1027.pdf"},{"key":"2223_CR4","doi-asserted-by":"publisher","DOI":"10.4324\/9781003123354","volume-title":"Pragmatic Imagination and the New Museum Anthropology","author":"MM Bruchac","year":"2024","unstructured":"Bruchac MM (2024) A pragmatic approach to reconciliation: thoughts on transforming repatriation. In: Hodge CJ, Kreps C (eds) Pragmatic Imagination and the New Museum Anthropology, 1st edn. Routledge, London. https:\/\/doi.org\/10.4324\/9781003123354","edition":"1"},{"issue":"1","key":"2223_CR5","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1177\/15501906241234943","volume":"20","author":"L Carreau","year":"2024","unstructured":"Carreau L, Gunn I (2024) Moving on: rethinking practice and transforming data at the museum of archaeology and anthropology, University of Cambridge. Collections 20(1):8\u201326. https:\/\/doi.org\/10.1177\/15501906241234943","journal-title":"Collections"},{"key":"2223_CR6","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1007\/978-81-322-3972-7_19","volume-title":"Fundamentals of Artificial Intelligence","author":"KR Chowdhary","year":"2020","unstructured":"Chowdhary KR (2020) Natural language processing. In: Chowdhary KR (ed) Fundamentals of Artificial Intelligence. Springer, India, pp 603\u2013649. https:\/\/doi.org\/10.1007\/978-81-322-3972-7_19"},{"key":"2223_CR7","unstructured":"Dongen N (2017) Analysis and Prediction of Dutch-English Code-switching in Dutch Social Media Messages [Report]. https:\/\/eprints.illc.uva.nl\/id\/eprint\/1527\/"},{"key":"2223_CR8","unstructured":"Elfardy H, Diab M (2013) Sentence level dialect identification in Arabic. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 456\u2013461. https:\/\/aclanthology.org\/P13-2081.pdf"},{"key":"2223_CR9","unstructured":"Franco-Salvador M, Rosso P, Rangel F (2015) Distributed representations of words and documents for discriminating similar languages. In: Proceedings of the Joint Workshop on Language Technology for Closely Related Languages, Varieties and Dialects. pp 11\u201316."},{"key":"2223_CR10","doi-asserted-by":"publisher","DOI":"10.3390\/e22010126","author":"M Gerlach","year":"2020","unstructured":"Gerlach M, Font-Clos F (2020) A standardized project gutenberg corpus for statistical analysis of natural language and quantitative linguistics. Entropy. https:\/\/doi.org\/10.3390\/e22010126","journal-title":"Entropy"},{"key":"2223_CR11","doi-asserted-by":"publisher","unstructured":"Hakkinen J, Tian J (2001) N-gram and decision tree based language identification for written words. In: IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU \u201901. pp. 335\u2013338. https:\/\/doi.org\/10.1109\/ASRU.2001.1034655","DOI":"10.1109\/ASRU.2001.1034655"},{"key":"2223_CR12","doi-asserted-by":"publisher","unstructured":"He J, Zhang Z, Zhao X, Li P, Yan Y (2016) Similar Language Identification for Uyghur and Kazakh on Short Spoken Texts. In: 2016 8th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), 02, 496\u2013499. https:\/\/doi.org\/10.1109\/IHMSC.2016.115","DOI":"10.1109\/IHMSC.2016.115"},{"key":"2223_CR13","doi-asserted-by":"crossref","unstructured":"Henrich P (1989) Language identification for the automatic grapheme-to-phoneme conversion of foreign words in a German text-to-speech system. In: Proceedings of Eurospeech 1989, 220\u2013223","DOI":"10.21437\/Eurospeech.1989-197"},{"key":"2223_CR14","doi-asserted-by":"publisher","unstructured":"Jauhiainen T, Lui M, Zampieri M, et al (2019) Automatic Language Identification in Texts: A Survey. Journal of Artificial Intelligence Research 65:675\u2013782. https:\/\/doi.org\/10.1613\/jair.1.11675","DOI":"10.1613\/jair.1.11675"},{"key":"2223_CR15","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, Le QV, Krikun M, Wu Y, Chen Z, Thorat N, Vi\u00e9gas F, Wattenberg M, Corrado G, Hughes M, Dean J (2017) Google\u2019s multilingual neural machine translation system: enabling zero-shot translation. Trans Assoc Comput Linguist 5:339\u2013351. https:\/\/doi.org\/10.1162\/tacl_a_00065","journal-title":"Trans Assoc Comput Linguist"},{"key":"2223_CR16","doi-asserted-by":"crossref","unstructured":"Joulin A, Grave E, Bojanowski P, Mikolov T (2017) Bag of Tricks for Efficient Text Classification. In: M Lapata, P Blunsom, A Koller (Eds) Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers. pp. 427\u2013431. Association for Computational Linguistics. https:\/\/aclanthology.org\/E17-2068","DOI":"10.18653\/v1\/E17-2068"},{"issue":"2","key":"2223_CR17","doi-asserted-by":"publisher","first-page":"63","DOI":"10.14361\/dcs-2020-0205","volume":"6","author":"R Kahn","year":"2020","unstructured":"Kahn R (2020) Man, woman, child: ethical aspects of metadata at the Pitt Rivers Museum. Digital Culture & Soc 6(2):63\u201386. https:\/\/doi.org\/10.14361\/dcs-2020-0205","journal-title":"Digital Culture & Soc"},{"key":"2223_CR18","doi-asserted-by":"crossref","unstructured":"Kalchbrenner N, Blunsom P (2013) Recurrent continuous translation models. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. pp. 1700\u20131709. https:\/\/aclanthology.org\/D13-1176.pdf","DOI":"10.18653\/v1\/D13-1176"},{"key":"2223_CR19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.410","author":"AH Kargaran","year":"2023","unstructured":"Kargaran AH, Imani A, Yvon F, Sch\u00fctze H (2023) GlotLID: language identification for low-resource languages. Find Assoc Comput Linguist. https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.410","journal-title":"Find Assoc Comput Linguist"},{"key":"2223_CR20","unstructured":"Kerwin T (2006) Classification of natural language based on character frequency. Ohio Supercomputer Center. https:\/\/www.researchgate.net\/profile\/Thomas-Kerwin\/publication\/242399551_Classification_of_natural_language_based_on_character_frequency\/links\/0a85e5327047816675000000\/Classification-of-natural-language-based-on-character-frequency.pdf"},{"key":"2223_CR21","doi-asserted-by":"crossref","unstructured":"King L, Baucom E, Gilmanov T, K\u00fcbler S, Whyatt D, Maier W, Rodrigues P (2014) The iucl+ system: Word-level language identification via extended markov models. In: Proceedings of the First Workshop on Computational Approaches to Code Switching. pp. 102\u2013106. https:\/\/aclanthology.org\/W14-3912.pdf","DOI":"10.3115\/v1\/W14-3912"},{"key":"2223_CR22","doi-asserted-by":"publisher","DOI":"10.4324\/9781003123354","volume-title":"Pragmatic Imagination and the New Museum Anthropology","author":"C Krmpotich","year":"2024","unstructured":"Krmpotich C (2024) Museum anthropology in an age of reconciliation. In: Hodge CJ, Kreps C (eds) Pragmatic Imagination and the New Museum Anthropology, 1st edn. Routledge, London. https:\/\/doi.org\/10.4324\/9781003123354","edition":"1"},{"issue":"4","key":"2223_CR23","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1145\/146370.146380","volume":"24","author":"K Kukich","year":"1992","unstructured":"Kukich K (1992) Techniques for automatically correcting words in text. ACM Comput Surv 24(4):377\u2013439. https:\/\/doi.org\/10.1145\/146370.146380","journal-title":"ACM Comput Surv"},{"key":"2223_CR24","unstructured":"Language support | Cloud Translation | Google Cloud. (n.d.). Retrieved September 9, 2024, from https:\/\/cloud.google.com\/translate\/docs\/languages"},{"issue":"1","key":"2223_CR25","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1177\/15501906241234046","volume":"20","author":"K Lewis","year":"2024","unstructured":"Lewis K (2024) Toward centering indigenous knowledge in museum collections management systems. Collections 20(1):27\u201350. https:\/\/doi.org\/10.1177\/15501906241234046","journal-title":"Collections"},{"key":"2223_CR26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.07264","author":"A Magueresse","year":"2020","unstructured":"Magueresse A, Carles V, Heetderks E (2020) Low-resource languages: a review of past work and future challenges. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2006.07264","journal-title":"arXiv"},{"key":"2223_CR27","doi-asserted-by":"crossref","unstructured":"Meyer CM, Gurevych I (2012) Wiktionary: a new rival for expert-built lexicons? Exploring the possibilities of collaborative lexicography. na. https:\/\/download.hrz.tu-darmstadt.de\/media\/FB20\/Dekanat\/Publikationen\/UKP\/oup-elex2012-meyer-wiktionary.pdf","DOI":"10.1093\/acprof:oso\/9780199654864.003.0013"},{"key":"2223_CR28","unstructured":"Norvig P (2016) How to Write a Spelling Corrector. https:\/\/norvig.com\/spell-correct.html"},{"issue":"3\u20134","key":"2223_CR29","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1080\/13500775.2022.2234193","volume":"74","author":"RL Punzalan","year":"2022","unstructured":"Punzalan RL, de la Cruz D (2022) Reparative approaches to philippine collections at the University of Michigan. Museum Int 74(3\u20134):72\u201381. https:\/\/doi.org\/10.1080\/13500775.2022.2234193","journal-title":"Museum Int"},{"key":"2223_CR30","doi-asserted-by":"publisher","unstructured":"Sefara TJ, Zwane SG, Gama N, Sibisi H, Senoamadi PN, Marivate V (2021). Transformer-based Machine Translation for Low-resourced Languages embedded with Language Identification. In: 2021 Conference on Information Communications Technology and Society (ICTAS). pp. 127\u2013132. https:\/\/doi.org\/10.1109\/ICTAS50802.2021.9394996","DOI":"10.1109\/ICTAS50802.2021.9394996"},{"key":"2223_CR31","doi-asserted-by":"publisher","unstructured":"Soto V, Hirschberg J (2018) Joint Part-of-Speech and Language ID Tagging for Code-Switched Data. In: Aguilar G, AlGhamdi F, Soto V, Solorio V, Diab M, Hirschberg J (ed) Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching (pp. 1\u201310). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/W18-3201","DOI":"10.18653\/v1\/W18-3201"},{"key":"2223_CR32","doi-asserted-by":"publisher","first-page":"118837","DOI":"10.1109\/ACCESS.2021.3104106","volume":"9","author":"S Thara","year":"2021","unstructured":"Thara S, Poornachandran P (2021) Transformer based language identification for Malayalam-English code-mixed text. IEEE Access 9:118837\u2013118850. https:\/\/doi.org\/10.1109\/ACCESS.2021.3104106","journal-title":"IEEE Access"},{"key":"2223_CR33","doi-asserted-by":"publisher","DOI":"10.59962\/9780774863940","volume-title":"Cataloguing culture: Legacies of colonialism in museum documentation","author":"H Turner","year":"2020","unstructured":"Turner H (2020) Cataloguing culture: Legacies of colonialism in museum documentation. UBC Press, Vancouver"},{"key":"2223_CR34","doi-asserted-by":"publisher","unstructured":"van der Lee C, van den Bosch A (2017) Exploring Lexical and Syntactic Features for Language Variety Identification. In: Nakov P, Zampieri M, Ljube\u0161i\u0107 N, Tiedemann J, Malmasi S, Ali A (ed) Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial). pp. 190\u2013199. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/W17-1224","DOI":"10.18653\/v1\/W17-1224"},{"key":"2223_CR35","doi-asserted-by":"publisher","DOI":"10.1002\/asi.24746","author":"TL Wagner","year":"2023","unstructured":"Wagner TL, Marsh D, Curliss L (2023) Theories and implications for centering Indigenous and queer embodiment within sociotechnical systems. J Assoc Inform Sci Technol. https:\/\/doi.org\/10.1002\/asi.24746","journal-title":"J Assoc Inform Sci Technol"},{"key":"2223_CR36","unstructured":"Windisch G, Csink L (2005) Language identification using global statistics of natural languages. In: Proceedings of the 2nd Romanian-Hungarian Joint Symposium on Applied Computational Intelligence (SACI). pp 243\u2013255."},{"key":"2223_CR37","doi-asserted-by":"publisher","unstructured":"Yeong Y-L, Tan T-P (2011) Applying Grapheme, Word, and Syllable Information for Language Identification in Code Switching Sentences. In: 2011 International Conference on Asian Language Processing. pp. 111\u2013114. https:\/\/doi.org\/10.1109\/IALP.2011.34","DOI":"10.1109\/IALP.2011.34"},{"key":"2223_CR38","doi-asserted-by":"publisher","DOI":"10.4159\/harvard.9780674434929","volume-title":"Selected studies of the principle of relative frequency in language","author":"GK Zipf","year":"1932","unstructured":"Zipf GK (2013) Selected studies of the principle of relative frequency in language. Harvard University Press, Cambridge"}],"container-title":["AI &amp; SOCIETY"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00146-025-02223-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00146-025-02223-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00146-025-02223-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T06:32:51Z","timestamp":1757140371000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00146-025-02223-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,24]]},"references-count":38,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2223"],"URL":"https:\/\/doi.org\/10.1007\/s00146-025-02223-y","relation":{},"ISSN":["0951-5666","1435-5655"],"issn-type":[{"type":"print","value":"0951-5666"},{"type":"electronic","value":"1435-5655"}],"subject":[],"published":{"date-parts":[[2025,2,24]]},"assertion":[{"value":"1 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}