{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T01:06:07Z","timestamp":1752282367387},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,4,15]],"date-time":"2014-04-15T00:00:00Z","timestamp":1397520000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1186\/1687-4722-2014-14","type":"journal-article","created":{"date-parts":[[2014,4,15]],"date-time":"2014-04-15T01:02:47Z","timestamp":1397523767000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Classification of heterogeneous text data for robust domain-specific language modeling"],"prefix":"10.1186","volume":"2014","author":[{"given":"J\u00e1n","family":"Sta\u0161","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jozef","family":"Juh\u00e1r","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Hl\u00e1dek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,4,15]]},"reference":[{"key":"106_CR1","first-page":"261","volume-title":"New Technologies - Trends, Innovations and Research","author":"J Juh\u00e1r","year":"2012","unstructured":"Juh\u00e1r J, Sta\u0161 J, Hl\u00e1dek D: Recent progress in development language model for Slovak large vocabulary continuous speech recognition. In New Technologies - Trends, Innovations and Research. Edited by: C Volosencu, C Volosencu . InTech Open Access, Rijeka; 2012:261-276."},{"key":"106_CR2","first-page":"555","volume-title":"Proceedings of the 6th Language and Technology Conference on HLT","author":"J Juh\u00e1r","year":"2013","unstructured":"Juh\u00e1r J, Trnka M, Darjaa S, Hl\u00e1dek D, Sabo R, Pleva M, Rusko M: Recent advances in the Slovak dictation system for the judicial domain. In Proceedings of the 6th Language and Technology Conference on HLT. Pozna\u0144, LTC; 2013:555-560."},{"key":"106_CR3","first-page":"49","volume-title":"Proceedings of the 6th New Zealand Computer Science Research Student Conference","author":"A Huang","year":"2008","unstructured":"Huang A: Similarity measures for text document clustering. In Proceedings of the 6th New Zealand Computer Science Research Student Conference. Christchurch, NZCSRSC; 2008:49-56."},{"key":"106_CR4","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1109\/MEC.2011.6025502","volume-title":"Proceedings of 2011 International Conference on Mechatronic Science, Electric Engineering and Computer","author":"L Yue","year":"2011","unstructured":"Yue L, Xiao S, Lv X, Wang T: Topic detection based on keyword. In Proceedings of 2011 International Conference on Mechatronic Science, Electric Engineering and Computer. Jilin, MEC; 2011:464-467."},{"key":"106_CR5","volume-title":"Introduction to Information Retrieval","author":"CD Manning","year":"2009","unstructured":"Manning CD, Raghavan P, Sch\u00fctze H: Introduction to Information Retrieval. Cambridge: Cambridge University Press; 2009."},{"key":"106_CR6","first-page":"317","volume-title":"Augmenting na\u00efve Bayes classifiers with statistical language models. Inf. Retr","author":"F Peng","year":"2004","unstructured":"Peng F, Schuurmans D, Wang S: Augmenting na\u00efve Bayes classifiers with statistical language models. Inf. Retr. 2004, 7(3\u20134):317-345."},{"issue":"2","key":"106_CR7","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.eswa.2005.07.019","volume":"30","author":"S Tan","year":"2006","unstructured":"Tan S: An effective refinement strategy for KNN text classifier. Expert Syst. Appl 2006, 30(2):290-298. 10.1016\/j.eswa.2005.07.019","journal-title":"Expert Syst. Appl"},{"issue":"4","key":"106_CR8","doi-asserted-by":"crossref","first-page":"551","DOI":"10.15388\/Informatica.2004.078","volume":"15","author":"N Remeikis","year":"2004","unstructured":"Remeikis N, Sku\u010das I, Melninkait\u00e9 V: Text categorization using neural networks initialized with decision trees. Informatica 2004, 15(4):551-564.","journal-title":"Informatica"},{"key":"106_CR9","first-page":"137","volume-title":"Proceedings of the 10th European Conference on ML","author":"T Joachims","year":"1998","unstructured":"Joachims T: Text categorization with support vector machines: learning with many relevant features. In Proceedings of the 10th European Conference on ML. Chemnitz, ECML; 1998:137-142."},{"key":"106_CR10","first-page":"197","volume-title":"Proceedings of the 2nd International Conference on Business Intelligence and Financial Engineering","author":"W Zhang","year":"2009","unstructured":"Zhang W, Yoshida T, Tang X: Text classification using semi-supervised clustering. In Proceedings of the 2nd International Conference on Business Intelligence and Financial Engineering. Beijing, BIFE; 2009:197-200."},{"key":"106_CR11","doi-asserted-by":"crossref","first-page":"1717","DOI":"10.21437\/Interspeech.2011-190","volume-title":"Proceeding of INTERSPEECH 2011","author":"S Darjaa","year":"2011","unstructured":"Darjaa S, Cer\u0148ak M, Trnka M, Rusko M: Effective triphone mapping for acoustic modeling in speech recognition. In Proceeding of INTERSPEECH 2011. Florence, INTERSPEECH; 2011:1717-1720."},{"issue":"2A","key":"106_CR12","doi-asserted-by":"crossref","first-page":"124","DOI":"10.26552\/com.C.2013.2A.124-128","volume":"15","author":"M Pleva","year":"2013","unstructured":"Pleva M, Juh\u00e1r J: Building of broadcast news database for evaluation of the automated subtitling service. Communications 2013, 15(2A):124-128.","journal-title":"Communications"},{"key":"106_CR13","first-page":"195","volume-title":"Proceedings of the 54th International Symposium ELMAR 2012","author":"D Hl\u00e1dek","year":"2012","unstructured":"Hl\u00e1dek D, Juh\u00e1r J, Sta\u0161 J: the Slovak morphological classifier. In Proceedings of the 54th International Symposium ELMAR 2012. Zadar, ELMAR; 2012:195-198."},{"key":"106_CR14","first-page":"2","volume-title":"Proceedings of the 1st Workshop on Intelligent and Knowledge Oriented Technologies","author":"R Garab\u00edk","year":"2006","unstructured":"Garab\u00edk R: Slovak morphology analyzer based on Levenshtein edit operations. In Proceedings of the 1st Workshop on Intelligent and Knowledge Oriented Technologies. Bratislava, WIKT; 2006:2-5."},{"key":"106_CR15","first-page":"228","volume-title":"Proceedings of the 7th International Conference on Natural Language Processing, Corpus Linguistics and E-learning","author":"D Hl\u00e1dek","year":"2013","unstructured":"Hl\u00e1dek D, Juh\u00e1r J, Olo\u0161tiak M, Sta\u0161 J: Automatic extraction of multiword units from Slovak text corpora. In Proceedings of the 7th International Conference on Natural Language Processing, Corpus Linguistics and E-learning. Bratislava, SLOVKO; 2013:228-237."},{"key":"106_CR16","first-page":"258","volume-title":"Proceedings of the 5th International Conference on Machine Learning and Applications","author":"JW Reed","year":"2006","unstructured":"Reed JW, Jiao Y, Potok TE, Klump BA, Elmore MT, Hurson AR, TF-ICF: a new term weighting scheme for clustering dynamic data sets. In Proceedings of the 5th International Conference on Machine Learning and Applications. Orlando: ICMLA; 2006:258-263."},{"key":"106_CR17","first-page":"163","volume-title":"Term weighting schemes for Slovak text document clustering","author":"D Zlack\u00fd","year":"2013","unstructured":"Zlack\u00fd D, Sta\u0161 J, J Juh\u00e1r, A \u010ci\u017em\u00e1r, Term weighting schemes for Slovak text document clustering. (J. Electr. Electron. Eng, ed.), vol. 6, (2013), pp. 163\u2013166"},{"key":"106_CR18","first-page":"83","volume-title":"Proceedings of the 24th Annual International ACM Conference on Research and Development in Information Retrieval","author":"R Jin","year":"2001","unstructured":"Jin R, Falusos C, Hauptmann AG: Meta-scoring: automatically evaluating term weighting schemes in IR without precision-recall. In Proceedings of the 24th Annual International ACM Conference on Research and Development in Information Retrieval. New Orleans, USA, SIGIR ACM, New York; 2001:83-89."},{"key":"106_CR19","first-page":"109","volume-title":"Proceedings of the 3rd Text Retrieval Conference","author":"SE Robertson","year":"1996","unstructured":"Robertson SE, Walker S, Jones S, Hancock-Beaulieu MM, Gatford M: Okapi at TREC-3. In Proceedings of the 3rd Text Retrieval Conference. Gaithersburg, TREC-3; 1996:109-126."},{"issue":"5","key":"106_CR20","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1007\/s10791-011-9163-y","volume":"14","author":"JS Whissell","year":"2011","unstructured":"Whissell JS, Clarke ChLA: Improving document clustering using Okapi BM25 feature weighting. Inf. Retr 2011, 14(5):466-487. 10.1007\/s10791-011-9163-y","journal-title":"Inf. Retr"},{"key":"106_CR21","first-page":"215","volume-title":"Proceedings of the 6th Text Retrieval Conference","author":"A Singhal","year":"1998","unstructured":"Singhal A: AT&T at TREC-6. In Proceedings of the 6th Text Retrieval Conference. Gaithersburg, TREC-6; 1998:215-226."},{"issue":"1","key":"106_CR22","first-page":"1","volume":"51","author":"S Lee","year":"2010","unstructured":"Lee S, Song J, Kim Y: An empirical comparison of four text mining methods. J. Comp. Inf. Sys 2010, 51(1):1-10.","journal-title":"J. Comp. Inf. Sys"},{"issue":"4","key":"106_CR23","first-page":"300","volume":"1","author":"SH Cha","year":"2007","unstructured":"Cha SH: Comprehensive survey on distance\/similarity measures between probability density functions. Intl. J. Math. Model. Methods Appl. Sci 2007, 1(4):300-307.","journal-title":"Intl. J. Math. Model. Methods Appl. Sci"},{"key":"106_CR24","volume-title":"Technical Note No. I.95.58: Institute for Remote Sensing Applications","author":"PL Rosin","year":"1995","unstructured":"Rosin PL: Edges: saliency measures and automatic thresholding. Technical Note No. I.95.58: Institute for Remote Sensing Applications 1995."},{"key":"106_CR25","first-page":"131","volume-title":"em Proceedings of the 2009 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","author":"A Lee","year":"2009","unstructured":"Lee A, Kawahara T: Recent development of open-source speech recognition engine Julius. In em Proceedings of the 2009 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Sapporo, APSIPA ASC; 2009:131-137."},{"key":"106_CR26","first-page":"5 pages","volume-title":"Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop","author":"A Stolcke","year":"2011","unstructured":"Stolcke A, Zheng J, Wang W, Abrash V: SRILM at sixteen: update and outlook. In Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop. Waikoloa, ASRU; 2011:5 pages-5 pages."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2014-14\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2014-14.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2014-14.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T17:06:43Z","timestamp":1648832803000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2014-14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,15]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["106"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2014-14","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4,15]]},"assertion":[{"value":"20 November 2013","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2014","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2014","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"14"}}