{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T23:43:25Z","timestamp":1777333405542,"version":"3.51.4"},"publisher-location":"Berlin, Heidelberg","reference-count":9,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642235375","type":"print"},{"value":"9783642235382","type":"electronic"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-23538-2_9","type":"book-chapter","created":{"date-parts":[[2011,8,27]],"date-time":"2011-08-27T07:11:37Z","timestamp":1314429097000},"page":"64-71","source":"Crossref","is-referenced-by-count":12,"title":["Automatic Topic Identification for Large Scale Language Modeling Data Filtering"],"prefix":"10.1007","author":[{"given":"Lucie","family":"Skorkovsk\u00e1","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Ircing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ale\u0161","family":"Pra\u017e\u00e1k","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Lehe\u010dka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"9_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/BFb0026683","volume-title":"Machine Learning: ECML-98","author":"T. Joachims","year":"1998","unstructured":"Joachims, T.: Text categorization with support vector machines: Learning with many relevant features. In: N\u00e9dellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol.\u00a01398, pp. 137\u2013142. Springer, Heidelberg (1998)"},{"key":"9_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/978-3-642-15760-8_13","volume-title":"Text, Speech and Dialogue","author":"J. Kanis","year":"2010","unstructured":"Kanis, J., Skorkovsk\u00e1, L.: Comparison of different lemmatization approaches through the means of information retrieval performance. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2010. LNCS, vol.\u00a06231, pp. 93\u2013100. Springer, Heidelberg (2010)"},{"key":"9_CR3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"C.D. Manning","year":"2008","unstructured":"Manning, C.D., Raghavan, P., Sch\u00fctze, H.: Introduction to Information Retrieval. Cambridge University Press, New York (2008)"},{"key":"9_CR4","unstructured":"Pra\u017e\u00e1k, A., Loose, Z., Psutka, J., Radov\u00e1, V., M\u00fcller, L.: Four-phase re-speaker training system. In: Proceedings of SIGMAP 2011, Seville (2011)"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Psutka, J., Ircing, P., Psutka, J.V., Radov\u00e1, V., Byrne, W., Haji\u010d, J., M\u00edrovsk\u00fd, J., Gustman, S.: Large vocabulary ASR for spontaneous Czech in the MALACH project. In: Proceedings of Eurospeech 2003, Geneva, pp. 1821\u20131824 (2003)","DOI":"10.21437\/Eurospeech.2003-551"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM - an extensible language modeling toolkit. In: Proceedings of ICSLP 2002, Denver, pp. 901\u2013904 (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"9_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-642-15760-8_55","volume-title":"Text, Speech and Dialogue","author":"J. Van\u011bk","year":"2010","unstructured":"Van\u011bk, J., Psutka, J.: Gender-dependent acoustic models fusion developed for automatic subtitling of parliament meetings broadcasted by the Czech TV. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2010. LNCS, vol.\u00a06231, pp. 431\u2013438. Springer, Heidelberg (2010)"},{"key":"9_CR8","series-title":"LNCS(LNAI)","first-page":"356","volume-title":"TSD 2011","author":"J. \u0160vec","year":"2011","unstructured":"\u0160vec, J., Hoidekr, J., Soutner, D., Vavru\u0161ka, J.: Web text data mining for building large scale language modelling corpus. In: Habernal, I., Matou\u0161ek, V. (eds.) TSD 2011. LNCS(LNAI), vol.\u00a06836, pp. 356\u2013363. Springer, Heidelberg (2011)"},{"key":"9_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1007\/978-3-642-15760-8_59","volume-title":"Text, Speech and Dialogue","author":"Z. Zaj\u00edc","year":"2010","unstructured":"Zaj\u00edc, Z., Machlica, L., M\u00fcller, L.: Robust statistic estimates for adaptation in the task of speech recognition. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2010. LNCS, vol.\u00a06231, pp. 464\u2013471. Springer, Heidelberg (2010)"}],"container-title":["Lecture Notes in Computer Science","Text, Speech and Dialogue"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23538-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T01:10:00Z","timestamp":1686273000000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23538-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642235375","9783642235382"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23538-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011]]}}}