{"id":"https://openalex.org/W1554892943","doi":"https://doi.org/10.1007/3-540-45681-3_25","title":"Information Extraction in Structured Documents Using Tree Automata Induction","display_name":"Information Extraction in Structured Documents Using Tree Automata Induction","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W1554892943","doi":"https://doi.org/10.1007/3-540-45681-3_25","mag":"1554892943"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-45681-3_25","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-45681-3_25","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":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/123456789/132023","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083941850","display_name":"Raymond Kosala","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Raymond Kosala","raw_affiliation_strings":["Department of Computer Science, Katholieke Universiteit Leuven, Celestijnenlaan 200A, B-3001, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Katholieke Universiteit Leuven, Celestijnenlaan 200A, B-3001, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089823917","display_name":"Jan Van den Bussche","orcid":"https://orcid.org/0000-0003-0072-3252"},"institutions":[{"id":"https://openalex.org/I4210127597","display_name":"Transnational University Limburg","ror":"https://ror.org/02xyaf767","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210127597"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jan Van den Bussche","raw_affiliation_strings":["Department WNI, University of Limburg (LUC), Universitaire Campus, B-3590, Diepenbeek, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department WNI, University of Limburg (LUC), Universitaire Campus, B-3590, Diepenbeek, Belgium","institution_ids":["https://openalex.org/I4210127597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004343076","display_name":"Maurice Bruynooghe","orcid":"https://orcid.org/0000-0002-6881-1462"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Maurice Bruynooghe","raw_affiliation_strings":["Department of Computer Science, Katholieke Universiteit Leuven, Celestijnenlaan 200A, B-3001, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Katholieke Universiteit Leuven, Celestijnenlaan 200A, B-3001, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086906175","display_name":"Hendrik Blockeel","orcid":"https://orcid.org/0000-0003-0378-3699"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hendrik Blockeel","raw_affiliation_strings":["Department of Computer Science, Katholieke Universiteit Leuven, Celestijnenlaan 200A, B-3001, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Katholieke Universiteit Leuven, Celestijnenlaan 200A, B-3001, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":7.1522,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.9770716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9975000023841858,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9030941724777222},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6898378133773804},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6733108162879944},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6009602546691895},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5740872025489807},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5736422538757324},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5510905981063843},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4847961962223053},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.4538598358631134},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.453387588262558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4223899245262146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4125126004219055},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39943206310272217},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3559299111366272},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23759371042251587},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13721534609794617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9030941724777222},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6898378133773804},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6733108162879944},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6009602546691895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5740872025489807},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5736422538757324},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5510905981063843},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4847961962223053},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.4538598358631134},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.453387588262558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4223899245262146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4125126004219055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39943206310272217},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3559299111366272},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23759371042251587},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13721534609794617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1007/3-540-45681-3_25","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-45681-3_25","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"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/132023","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/132023","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"6th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2002), Helsinki, Finland, 19-23 August 2002","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/167177","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/167177","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Belgian-Dutch Conference on Artificial Intelligence, Leuven, Belgium, 21-22 October 2002","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.9159","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.9159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.kuleuven.ac.be/~dtai/publications/files/38956.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.6952","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.6952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.kuleuven.ac.be/~dtai/publications/files/39328.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.16.5360","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.5360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://alpha.luc.ac.be/~vdbuss/ta_paper.ps.gz","raw_type":"text"},{"id":"pmh:oai:documentserver.uhasselt.be:1942/701","is_oa":true,"landing_page_url":"http://hdl.handle.net/1942/701","pdf_url":null,"source":{"id":"https://openalex.org/S4306401926","display_name":"Document Server@UHasselt (UHasselt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I878454856","host_organization_name":"Hasselt University","host_organization_lineage":["https://openalex.org/I878454856"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/132023","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/132023","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"6th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2002), Helsinki, Finland, 19-23 August 2002","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W117692269","https://openalex.org/W200042785","https://openalex.org/W1503682011","https://openalex.org/W1543832372","https://openalex.org/W1553161581","https://openalex.org/W1553229631","https://openalex.org/W1593799327","https://openalex.org/W1616576116","https://openalex.org/W1824331018","https://openalex.org/W1965014786","https://openalex.org/W1969005071","https://openalex.org/W1999595522","https://openalex.org/W2003304137","https://openalex.org/W2019363670","https://openalex.org/W2029752177","https://openalex.org/W2051146345","https://openalex.org/W2065568440","https://openalex.org/W2083367980","https://openalex.org/W2139709458","https://openalex.org/W2143349571","https://openalex.org/W2145948275","https://openalex.org/W2153752143","https://openalex.org/W2162340487","https://openalex.org/W2164765168","https://openalex.org/W2169852020","https://openalex.org/W2341078838","https://openalex.org/W2953142849","https://openalex.org/W4232438669","https://openalex.org/W4238893454","https://openalex.org/W6635485671","https://openalex.org/W6835032760"],"related_works":["https://openalex.org/W2372453241","https://openalex.org/W2371387875","https://openalex.org/W2531660186","https://openalex.org/W1987871343","https://openalex.org/W2064670891","https://openalex.org/W1508699539","https://openalex.org/W2025988984","https://openalex.org/W2013559555","https://openalex.org/W2030846031","https://openalex.org/W4387591332"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
