{"id":"https://openalex.org/W1488191400","doi":"https://doi.org/10.1007/978-3-540-72035-5_30","title":"Automatic Document Structure Detection for Data Integration","display_name":"Automatic Document Structure Detection for Data Integration","publication_year":2007,"publication_date":"2007-06-05","ids":{"openalex":"https://openalex.org/W1488191400","doi":"https://doi.org/10.1007/978-3-540-72035-5_30","mag":"1488191400"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-72035-5_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-72035-5_30","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/A5040028014","display_name":"Radek Burget","orcid":"https://orcid.org/0000-0001-5233-0456"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Radek Burget","raw_affiliation_strings":["Faculty of Information Technology, Brno University of Technology Bozetechova 2, 612 66 Brno, Czech Republic","Faculty of Information Technology, Brno University of Technology, Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Brno University of Technology Bozetechova 2, 612 66 Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040028014"],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.4865,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82919792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"391","last_page":"397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8149428367614746},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7051247358322144},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5573712587356567},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.5509893894195557},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4981801509857178},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.45635297894477844},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25296550989151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19663646817207336},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13820910453796387},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.1321641206741333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149428367614746},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7051247358322144},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5573712587356567},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.5509893894195557},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4981801509857178},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.45635297894477844},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25296550989151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19663646817207336},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13820910453796387},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.1321641206741333},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-540-72035-5_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-72035-5_30","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W141724566","https://openalex.org/W1602839414","https://openalex.org/W1748877974","https://openalex.org/W1803802947","https://openalex.org/W2008237558","https://openalex.org/W2012575882","https://openalex.org/W2015933107","https://openalex.org/W2095680579","https://openalex.org/W2096031153","https://openalex.org/W2121871415","https://openalex.org/W2155758288","https://openalex.org/W2167859982","https://openalex.org/W3162013555","https://openalex.org/W4247368390","https://openalex.org/W6638151354"],"related_works":["https://openalex.org/W166250124","https://openalex.org/W2027019938","https://openalex.org/W2089356193","https://openalex.org/W2105363053","https://openalex.org/W343133241","https://openalex.org/W1562544158","https://openalex.org/W2074700442","https://openalex.org/W2886783053","https://openalex.org/W1971234693","https://openalex.org/W3116857864"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
