{"id":"https://openalex.org/W1817992165","doi":"https://doi.org/10.1007/978-3-642-23538-2_45","title":"Web Text Data Mining for Building Large Scale Language Modelling Corpus","display_name":"Web Text Data Mining for Building Large Scale Language Modelling Corpus","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W1817992165","doi":"https://doi.org/10.1007/978-3-642-23538-2_45","mag":"1817992165"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-23538-2_45","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-23538-2_45","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072542443","display_name":"J\u00e1n \u0160vec","orcid":"https://orcid.org/0000-0001-8362-5927"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Jan \u0160vec","raw_affiliation_strings":["Faculty of Applied Sciences, Dept. of Cybernetics, University of West Bohemia, Univerzitn\u00ed 8, 306 14, Plze\u0148, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Dept. of Cybernetics, University of West Bohemia, Univerzitn\u00ed 8, 306 14, Plze\u0148, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032416308","display_name":"Jan Hoidekr","orcid":null},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Hoidekr","raw_affiliation_strings":["Faculty of Applied Sciences, Dept. of Cybernetics, University of West Bohemia, Univerzitn\u00ed 8, 306 14, Plze\u0148, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Dept. of Cybernetics, University of West Bohemia, Univerzitn\u00ed 8, 306 14, Plze\u0148, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047501594","display_name":"Daniel Soutner","orcid":"https://orcid.org/0000-0002-8899-8260"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Daniel Soutner","raw_affiliation_strings":["Faculty of Applied Sciences, Dept. of Cybernetics, University of West Bohemia, Univerzitn\u00ed 8, 306 14, Plze\u0148, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Dept. of Cybernetics, University of West Bohemia, Univerzitn\u00ed 8, 306 14, Plze\u0148, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035947906","display_name":"Jan Vavru\u0161ka","orcid":"https://orcid.org/0000-0001-7713-3950"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Vavru\u0161ka","raw_affiliation_strings":["Faculty of Applied Sciences, Dept. of Cybernetics, University of West Bohemia, Univerzitn\u00ed 8, 306 14, Plze\u0148, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Applied Sciences, Dept. of Cybernetics, University of West Bohemia, Univerzitn\u00ed 8, 306 14, Plze\u0148, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072542443"],"corresponding_institution_ids":["https://openalex.org/I92715842"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":4.4716,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.9523482,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"356","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8891588449478149},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.8610571026802063},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6738396286964417},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6053234338760376},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5233739614486694},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.5104609727859497},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5048554539680481},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47549378871917725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4694492518901825},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46799060702323914},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4639289975166321},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4277164936065674},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4119328260421753},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.338478684425354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8891588449478149},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8610571026802063},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6738396286964417},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6053234338760376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5233739614486694},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.5104609727859497},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5048554539680481},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.47549378871917725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4694492518901825},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46799060702323914},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4639289975166321},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4277164936065674},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4119328260421753},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.338478684425354},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-23538-2_45","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-23538-2_45","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1495542223","https://openalex.org/W1511655776","https://openalex.org/W1550982044","https://openalex.org/W1570515258","https://openalex.org/W1621432539","https://openalex.org/W1811872306","https://openalex.org/W1882516017","https://openalex.org/W2075310404","https://openalex.org/W2136780519","https://openalex.org/W2144556654","https://openalex.org/W2152565070","https://openalex.org/W4211148787"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4287323699","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
