{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T19:40:15Z","timestamp":1743622815733,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819642069","type":"print"},{"value":"9789819642076","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\/978-981-96-4207-6_37","type":"book-chapter","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T19:17:09Z","timestamp":1743621429000},"page":"401-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on\u00a0Two-Stage Text Language Identification Algorithm for\u00a0Chinese, Japanese, and\u00a0Korean"],"prefix":"10.1007","author":[{"given":"Mamtimin","family":"Qasim","sequence":"first","affiliation":[]},{"given":"Wushour","family":"Silamu","sequence":"additional","affiliation":[]},{"given":"Minghui","family":"Qiu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"37_CR1","unstructured":"Automatic language identification in text-gcld3. https:\/\/notepub.io\/notes\/artificial-intelligence\/speech-and-language-processing\/language-identification\/lid-gcld3\/. Accessed 2 May 2024"},{"key":"37_CR2","unstructured":"Chinese and Japanese. https:\/\/unicode.org\/faq\/han_cjk.html. Accessed 8 July 2024"},{"key":"37_CR3","unstructured":"langdetect 1.0.9. https:\/\/pypi.org\/project\/langdetect\/. Accessed 2 May 2024"},{"key":"37_CR4","unstructured":"Language detection-polyglot 16.07.04 documentation. https:\/\/polyglot.readthedocs.io\/en\/latest\/Detection.html. Accessed 2 May 2024"},{"key":"37_CR5","unstructured":"Language identification.fasttext. https:\/\/fasttext.cc\/docs\/en\/language-identification.html. Accessed 2 May 2024"},{"key":"37_CR6","unstructured":"Leipzig corpora collection download page. https:\/\/cls.corpora.uni-leipzig.de\/en. Accessed 2 May 2024"},{"issue":"4","key":"37_CR7","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1016\/j.ipm.2015.12.003","volume":"52","author":"K Abainia","year":"2016","unstructured":"Abainia, K., Ouamour, S., Sayoud, H.: Effective language identification of forum texts based on statistical approaches. Inf. Process. Manag. 52(4), 491\u2013512 (2016). https:\/\/doi.org\/10.1016\/j.ipm.2015.12.003","journal-title":"Inf. Process. Manag."},{"key":"37_CR8","unstructured":"Apple: Language identification from very short strings (2019). https:\/\/machinelearning.apple.com\/research\/language-identification-from-very-short-strings. Accessed 10 Feb 2021"},{"issue":"5","key":"37_CR9","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). https:\/\/doi.org\/10.1016\/j.csl.2012.01.004","journal-title":"Comput. Speech Lang."},{"issue":"2","key":"37_CR10","doi-asserted-by":"publisher","first-page":"21","DOI":"10.4038\/icter.v2i2.1385","volume":"2","author":"YC Chew","year":"2009","unstructured":"Chew, Y.C., Mikami, Y., Marasinghe, C.A., Nandasara, S.T.: Optimizing n-gram order of an n-gram based language identification algorithm for 68 written languages. Int. J. Adv. ICT Emerg. Reg. (ICTer) 2(2), 21\u201328 (2009). https:\/\/doi.org\/10.4038\/icter.v2i2.1385","journal-title":"Int. J. Adv. ICT Emerg. Reg. (ICTer)"},{"key":"37_CR11","unstructured":"Goldhahn, D., Eckart, T., Quasthoff, U., et\u00a0al.: Building large monolingual dictionaries at the Leipzig corpora collection: from 100 to 200 languages. In: Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC 2012), vol.\u00a029, pp. 31\u201343 (2012)"},{"key":"37_CR12","unstructured":"Goutte, C., L\u00e9ger, S., Malmasi, S., Zampieri, M.: Discriminating similar languages: evaluations and explorations. In: Calzolari, N., et al. (eds.) Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), pp. 1800\u20131807. European Language Resources Association (ELRA), Portoro\u017e, Slovenia (2016). https:\/\/aclanthology.org\/L16-1284"},{"issue":"4","key":"37_CR13","doi-asserted-by":"publisher","first-page":"534","DOI":"10.3923\/itj.2007.534.540","volume":"6","author":"F Hanif","year":"2007","unstructured":"Hanif, F., Latif, F., Khiyal, M.S.H.: Unicode aided language identification across multiple scripts and heterogeneous data. Inf. Technol. J. 6(4), 534\u2013540 (2007). https:\/\/doi.org\/10.3923\/itj.2007.534.540","journal-title":"Inf. Technol. J."},{"issue":"6","key":"37_CR14","first-page":"354","volume":"15","author":"M Hasimu","year":"2017","unstructured":"Hasimu, M., Silamu, W.: Three-stage short text language identification algorithm. J. Digit. Inf. Manag. 15(6), 354\u2013371 (2017)","journal-title":"J. Digit. Inf. Manag."},{"key":"37_CR15","doi-asserted-by":"publisher","unstructured":"Hasimu, M., Silamu, W.: On hierarchical text language-identification algorithms. Algorithms 11(4) (2018). https:\/\/doi.org\/10.3390\/a11040039","DOI":"10.3390\/a11040039"},{"key":"37_CR16","doi-asserted-by":"publisher","unstructured":"Jauhiainen, T., Lui, M., Zampieri, M., Baldwin, T., Lind\u00e9n, K.: Automatic language identification in texts: a survey. J. Artif. Intell. Res. 65 (2019). https:\/\/doi.org\/10.1613\/jair.1.11675","DOI":"10.1613\/jair.1.11675"},{"key":"37_CR17","unstructured":"Lui, M., Baldwin, T.: langid.py: an off-the-shelf language identification tool. In: Zhang, M. (ed.) Proceedings of the ACL 2012 System Demonstrations, Jeju Island, Korea, pp. 25\u201330. Association for Computational Linguistics (2012). https:\/\/aclanthology.org\/P12-3005"},{"key":"37_CR18","unstructured":"Lui, M.H.: Generalized language identification. Ph.D. thesis, University of Melbourne, Department of Computing and Information Systems (2014)"},{"issue":"4","key":"37_CR19","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1016\/j.jksuci.2014.12.004","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"37_CR20","doi-asserted-by":"publisher","unstructured":"Toftrup, M., Asger\u00a0S\u00f8rensen, S., Ciosici, M.R., Assent, I.: A reproduction of apple\u2019s bi-directional LSTM models for language identification in short strings. In: Sorodoc, I.T., Sushil, M., Takmaz, E., Agirre, E. (eds.) Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pp. 36\u201342. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.eacl-srw.6","DOI":"10.18653\/v1\/2021.eacl-srw.6"}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Computing, Applications and Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-4207-6_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T19:17:55Z","timestamp":1743621475000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-4207-6_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819642069","9789819642076"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-4207-6_37","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":"1 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no conflicts of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"PDCAT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel and Distributed Computing: Applications and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pdcat2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/hpcc.siat.ac.cn\/meeting\/pdcat2024\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}