{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:03:28Z","timestamp":1786979008545,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319905952","type":"print"},{"value":"9783319905969","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-90596-9_7","type":"book-chapter","created":{"date-parts":[[2018,4,20]],"date-time":"2018-04-20T13:12:50Z","timestamp":1524229970000},"page":"90-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Language Identification with Scarce Data: A Case Study from Peru"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6719-2436","authenticated-orcid":false,"given":"Alexandra","family":"Espich\u00e1n-Linares","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7675-6208","authenticated-orcid":false,"given":"Arturo","family":"Oncevay-Marcos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,4,21]]},"reference":[{"key":"7_CR1","unstructured":"Bjerva, J.: Byte-based language identification with deep convolutional networks. arXiv preprint arXiv:1609.09004"},{"issue":"5","key":"7_CR2","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.csl.2012.01.004","volume":"26","author":"GR Botha","year":"2012","unstructured":"Botha, G.R., Barnard, E.: Factors that affect the accuracy of text-based language identification. Comput. Speech Lang. 26(5), 307\u2013320 (2012)","journal-title":"Comput. Speech Lang."},{"key":"7_CR3","unstructured":"Cavnar, W.B., Trenkle, J.M.: N-gram-based text categorization. In: Proceedings of the Third Annual Symposium on Document Analysis and Information Retrieval, pp. 161\u2013169 (1994)"},{"issue":"2","key":"7_CR4","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s10579-014-9287-y","volume":"49","author":"C Christodouloupoulos","year":"2015","unstructured":"Christodouloupoulos, C., Steedman, M.: A massively parallel corpus: the bible in 100 languages. Lang. Resour. Eval. 49(2), 375\u2013395 (2015)","journal-title":"Lang. Resour. Eval."},{"key":"7_CR5","unstructured":"D\u00edaz, D.P. (ed.): Relatos de Nopoki. Universidad Cat\u00f3lica Sedes Sapientiae (2012)"},{"key":"7_CR6","unstructured":"Forcada, M.: Open source machine translation: an opportunity for minor languages. In: Proceedings of the Workshop \u201cStrategies for Developing Machine Translation for Minority Languages\u201d, LREC, vol. 6, pp. 1\u20136. Citeseer (2006)"},{"key":"7_CR7","unstructured":"Grothe, L., De Luca, E.W., N\u00fcrnberger, A.: A comparative study on language identification methods. In: LREC (2008)"},{"key":"7_CR8","unstructured":"Hochreiter, S., Schmidhuber, J.: LSTM can solve hard long time lag problems. In: Advances in Neural Information Processing Systems, pp. 473\u2013479 (1997)"},{"key":"7_CR9","unstructured":"Jaech, A., Mulcaire, G., Hathi, S., Ostendorf, M., Smith, N.A.: Hierarchical character-word models for language identification (2016). arXiv preprint arXiv:1608.03030"},{"key":"7_CR10","unstructured":"Kocmi, T., Bojar, O.: LanideNN: Multilingual language identification on character window (2017). arXiv preprint arXiv:1701.03338"},{"key":"7_CR11","unstructured":"Koller, D., Sahami, M.: Hierarchically classifying documents using very few words. Technical report, Stanford InfoLab (1997)"},{"key":"7_CR12","unstructured":"Malmasi, S., Dras, M.: Automatic language identification for persian and dari texts. In: Proceedings of PACLING, pp. 59\u201364 (2015)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Martins, B., Silva, M.J.: Language identification in web pages. In: Proceedings of the 2005 ACM Symposium on Applied Computing, pp. 764\u2013768. ACM (2005)","DOI":"10.1145\/1066677.1066852"},{"key":"7_CR14","unstructured":"Mathur, P., Misra, A., Budur, E.: LIDE: Language identification from text documents (2017). arXiv preprint arXiv:1701.03682"},{"key":"7_CR15","unstructured":"McCallum, A., Rosenfeld, R., Mitchell, T.M., Ng, A.Y.: Improving text classification by shrinkage in a hierarchy of classes. In: ICML, vol. 98, pp. 359\u2013367 (1998)"},{"key":"7_CR16","unstructured":"Ministerio de Educaci\u00f3n, Per\u00fa: Documento nacional de lenguas originarias del Per\u00fa (2013). http:\/\/repositorio.minedu.gob.pe\/handle\/123456789\/3549"},{"key":"7_CR17","unstructured":"Pienaar, W., Snyman, D.: Spelling checker-based language identification for the eleven official south african languages. In: Proceedings of the 21st Annual Symposium of Pattern Recognition of SA, Stellenbosch, South Africa, pp. 213\u2013216 (2011)"},{"issue":"3","key":"7_CR18","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1080\/07421222.1999.11518257","volume":"16","author":"JM Prager","year":"1999","unstructured":"Prager, J.M.: Linguini: Language identification for multilingual documents. J. Manage. Inf. Syst. 16(3), 71\u2013101 (1999)","journal-title":"J. Manage. Inf. Syst."},{"key":"7_CR19","unstructured":"Quasthoff, U., Richter, M., Biemann, C.: Corpus portal for search in monolingual corpora. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation, vol. 17991802, p. 21 (2006)"},{"key":"7_CR20","unstructured":"Rios, A.: A Basic Language Technology Toolkit for Quechua (2016)"},{"issue":"4","key":"7_CR21","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.jksuci.2014.12.004","volume":"28","author":"A Selamat","year":"2016","unstructured":"Selamat, A., Akosu, N.: Word-length algorithm for language identification of under-resourced languages. J. King Saud Univ. Comput. Inf. Sci. 28(4), 457\u2013469 (2016)","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"7_CR22","unstructured":"Universidad Cat\u00f3lica Sedes Sapientiae: Relatos Matsigenkas. Universidad Cat\u00f3lica Sedes Sapientiae (2015)"},{"key":"7_CR23","unstructured":"Valenzuela, P.: Transitivity in shipibo-konibo grammar. Ph.D. thesis, University of Oregon (2003)"},{"key":"7_CR24","unstructured":"Zariquiey Biondi, R.: A grammar of Kashibo-Kakataibo. Ph.D. thesis, La Trobe University (2011)"}],"container-title":["Communications in Computer and Information Science","Information Management and Big Data"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-90596-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T16:40:30Z","timestamp":1751560830000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-90596-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319905952","9783319905969"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-90596-9_7","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}