{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:41:00Z","timestamp":1775666460727,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030602758","type":"print"},{"value":"9783030602765","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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":[[2020]]},"DOI":"10.1007\/978-3-030-60276-5_63","type":"book-chapter","created":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:02:44Z","timestamp":1601794964000},"page":"657-666","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["KazNLP: A Pipeline for Automated Processing of Texts Written in Kazakh Language"],"prefix":"10.1007","author":[{"given":"Zhandos","family":"Yessenbayev","sequence":"first","affiliation":[]},{"given":"Zhanibek","family":"Kozhirbayev","sequence":"additional","affiliation":[]},{"given":"Aibek","family":"Makazhanov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"63_CR1","unstructured":"Assylbekov, Z., et al.: A free\/open-source hybrid morphological disambiguation tool for kazakh (2016)"},{"key":"63_CR2","unstructured":"Baldwin, T., Lui, M.: 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, pp. 229\u2013237. Association for Computational Linguistics, Los Angeles, California (2010)"},{"key":"63_CR3","doi-asserted-by":"crossref","unstructured":"Bird, S., Loper, E.: NLTK: the natural language toolkit. In: Proceedings of the ACL Interactive Poster and Demonstration Sessions, pp. 214\u2013217. Association for Computational Linguistics (2004)","DOI":"10.3115\/1219044.1219075"},{"key":"63_CR4","unstructured":"Evang, K., Basile, V., Chrupa\u0142a, G., Bos, J.: Elephant: sequence labeling for word and sentence segmentation. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1422\u20131426. Association for Computational Linguistics (2013)"},{"key":"63_CR5","doi-asserted-by":"crossref","unstructured":"Hakkani-T\u00fcr, D.Z., Oflazer, K., T\u00fcr, G.: Statistical morphological disambiguation for agglutinative languages. In: Proceedings of the 18th Conference on Computational Linguistics - Volume 1, pp. 285\u2013291. Association for Computational Linguistics (2000)","DOI":"10.3115\/990820.990862"},{"key":"63_CR6","unstructured":"Han, B., Baldwin, T.: Lexical normalisation of short text messages: makn sens a #twitter. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 368\u2013378. Association for Computational Linguistics (2011)"},{"key":"63_CR7","doi-asserted-by":"crossref","unstructured":"Kessikbayeva, G., Cicekli, I.: Rule based morphological analyzer of kazakh language. In: Proceedings of the 2014 Joint Meeting of SIGMORPHON and SIGFSM, pp. 46\u201354. Association for Computational Linguistics (2014)","DOI":"10.3115\/v1\/W14-2806"},{"key":"63_CR8","doi-asserted-by":"crossref","unstructured":"Klein, G., Kim, Y., Deng, Y., Senellart, J., Rush, A.: OpenNMT: open-source toolkit for neural machine translation. In: Proceedings of ACL 2017, System Demonstrations, pp. 67\u201372. Association for Computational Linguistics, Vancouver, Canada July 2017 https:\/\/www.aclweb.org\/anthology\/P17-4012","DOI":"10.18653\/v1\/P17-4012"},{"key":"63_CR9","doi-asserted-by":"crossref","unstructured":"Kozhirbayev, Z., Yessenbayev, Z., Makazhanov, A.: Document and word-level language identification for noisy user generated text. In: 2018 IEEE 12th International Conference on Application of Information and Communication Technologies (AICT), pp. 1\u20134 (2018)","DOI":"10.1109\/ICAICT.2018.8747138"},{"key":"63_CR10","doi-asserted-by":"crossref","unstructured":"Kozhirbayev, Z., Yessenbayev, Z.: Named entity recognition for the kazakh language. Journal of Mathematics, Mechanics and Computer Science, 106(2) (2020) (Submitted)","DOI":"10.26577\/JMMCS.2020.v107.i3.06"},{"key":"63_CR11","unstructured":"Lui, M., Baldwin, T.: Langid.py: an off-the-shelf language identification tool. In: Proceedings of the ACL 2012 System Demonstrations, pp. 25\u201330. Association for Computational Linguistics (2012)"},{"key":"63_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-540-71701-0_45","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"V Cheng","year":"2007","unstructured":"Cheng, V., Li, C.H.: Combining supervised and semi-supervised classifier for personalized spam filtering. In: Zhou, Z.H., Li, H., Yang, Q. (eds.) PAKDD 2007. LNCS (LNAI), vol. 4426, pp. 449\u2013456. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-71701-0_45"},{"key":"63_CR13","unstructured":"Makazhanov, A., Sultangazina, A., Makhambetov, O., Yessenbayev, Z.: Syntactic annotation of kazakh: following the universal dependencies guidelines. a report. In: 3rd International Conference on Turkic Languages Processing, (TurkLang 2015), pp. 338\u2013350 (2015)"},{"key":"63_CR14","unstructured":"Makazhanov, A., Yessenbayev, Z.: NLA-NU Kazakh Dependency Treebank. https:\/\/github.com\/nlacslab\/kazdet . Accessed 10 June 2020"},{"key":"63_CR15","unstructured":"Makazhanov, A., Yessenbayev, Z., Kozhirbayev, Z.: KazNLP: NLP Tools for Kazakh Language. https:\/\/github.com\/nlacslab\/kaznlp . Accessed 10 June 2020"},{"key":"63_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-3-319-18111-0_12","volume-title":"Computational Linguistics and Intelligent Text Processing","author":"O Makhambetov","year":"2015","unstructured":"Makhambetov, O., Makazhanov, A., Sabyrgaliyev, I., Yessenbayev, Z.: Data-driven morphological analysis and disambiguation for kazakh. In: Gelbukh, A. (ed.) CICLing 2015. LNCS, vol. 9041, pp. 151\u2013163. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-18111-0_12"},{"key":"63_CR17","unstructured":"Makhambetov, O., Makazhanov, A., Yessenbayev, Z., Matkarimov, B., Sabyrgaliyev, I., Sharafudinov, A.: Assembling the kazakh language corpus. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1022\u20131031. Association for Computational Linguistics (2013)"},{"key":"63_CR18","unstructured":"McDonald, R., Pereira, F.: Online learning of approximate dependency parsing algorithms. In: 11th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics (2006)"},{"key":"63_CR19","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Cotterell, R., Fraser, A., Sch\u00fctze, H.: Joint lemmatization and morphological tagging with lemming. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 2268\u20132274. Association for Computational Linguistics (2015)","DOI":"10.18653\/v1\/D15-1272"},{"key":"63_CR20","unstructured":"Mussayeva, A.: Kazakh language spelling with hunspell in openoffice.org. Tech. rep., The University of Nottingham (2008)"},{"key":"63_CR21","doi-asserted-by":"crossref","unstructured":"Myrzakhmetov, B., Yessenbayev, Z., Makazhanov, A.: Initial normalization of user generated content: case study in a multilingual setting. In: 2018 IEEE 12th International Conference on Application of Information and Communication Technologies (AICT), pp. 1\u20134 (2018)","DOI":"10.1109\/ICAICT.2018.8747161"},{"key":"63_CR22","unstructured":"Myzakhmetov, B., Yessenbayev, Z.: Normalization of noisy user comments in kazakh language using statistical machine translation approach. Bulletin of the Eurasian National University (2020) (Submitted)"},{"key":"63_CR23","unstructured":"Nivre, J.: Universal Dependencies. https:\/\/universaldependencies.org\/ . Accessed 10 June 2020"},{"key":"63_CR24","unstructured":"Nivre, J., Hall, J., Nilsson, J.: MaltParser: a data-driven parser-generator for dependency parsing. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC\u201906). European Language Resources Association (ELRA) (2006)"},{"key":"63_CR25","doi-asserted-by":"crossref","unstructured":"Oflazer, K., Guzey, C.: Spelling correction in agglutinative languages. In: Fourth Conference on Applied Natural Language Processing, pp. 194\u2013195. Association for Computational Linguistics (1994)","DOI":"10.3115\/974358.974406"},{"key":"63_CR26","unstructured":"OpenNLP: The Apache OpenNLP Library. https:\/\/opennlp.apache.org\/ . Accessed 13 June 2020"},{"key":"63_CR27","unstructured":"Straka, M., Haji\u010d, J., Strakov\u00e1, J.: UDPipe: trainable pipeline for processing CoNLL-u files performing tokenization, morphological analysis, POS tagging and parsing. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), pp. 4290\u20134297. European Language Resources Association (ELRA) (2016)"},{"key":"63_CR28","unstructured":"Tolegen, G., Toleu, A.: Named entity recognition for kazakh using conditional random fields. In: The 4-th International Conference on Computer Processing of Turkic Languages (TurkLang 2016) (2016)"},{"key":"63_CR29","doi-asserted-by":"crossref","unstructured":"Toleu, A., Tolegen, G., Makazhanov, A.: Character-aware neural morphological disambiguation. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 666\u2013671. Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/P17-2105"},{"key":"63_CR30","unstructured":"Toleu, A., Tolegen, G., Makazhanov, A.: Character-based deep learning models for token and sentence segmentation. In: The 5-th International Conference on Computer Processing of Turkic Languages (TurkLang 2017) (2017)"},{"key":"63_CR31","unstructured":"Washington, J., Salimzyanov, I., Tyers, F.: Finite-state morphological transducers for three kypchak languages. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014), pp. 3378\u20133385. European Language Resources Association (ELRA) (2014)"},{"key":"63_CR32","unstructured":"Yessenbayev, Z., Kozhirbayev, Z.: Data-driven dependency parsing for kazakh. Bulletin of the Eurasian National University (2020) (Submitted)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60276-5_63","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T02:09:41Z","timestamp":1617674981000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60276-5_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602758","9783030602765"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60276-5_63","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St. Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"160","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"65","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the Corona pandemic SPECOM 2020 was held as a virtual event","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}