{"id":"https://openalex.org/W1934339046","doi":"https://doi.org/10.1007/978-3-540-45194-5_10","title":"Classification and Focused Crawling for Semistructured Data","display_name":"Classification and Focused Crawling for Semistructured Data","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1934339046","doi":"https://doi.org/10.1007/978-3-540-45194-5_10","mag":"1934339046"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-45194-5_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-45194-5_10","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/A5060837952","display_name":"Martin Theobald","orcid":"https://orcid.org/0000-0003-4067-7609"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin Theobald","raw_affiliation_strings":["Universit\u00e4t des Saarlandes, Fachrichtung 6.2 Informatik, Postfach 151150, 66041, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t des Saarlandes, Fachrichtung 6.2 Informatik, Postfach 151150, 66041, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049745760","display_name":"Ralf Schenkel","orcid":"https://orcid.org/0000-0001-5379-5191"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schenkel","raw_affiliation_strings":["Max-Planck-Institut f\u00fcr Informatik, Saarbr\u00fccken, Germany","Universit\u00e4t des Saarlandes, Fachrichtung 6.2 Informatik, Postfach 151150, 66041, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max-Planck-Institut f\u00fcr Informatik, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Universit\u00e4t des Saarlandes, Fachrichtung 6.2 Informatik, Postfach 151150, 66041, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088135366","display_name":"Gerhard Weikum","orcid":"https://orcid.org/0000-0003-4959-6098"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Weikum","raw_affiliation_strings":["Max-Planck-Institut f\u00fcr Informatik, Saarbr\u00fccken, Germany","Universit\u00e4t des Saarlandes, Fachrichtung 6.2 Informatik, Postfach 151150, 66041, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max-Planck-Institut f\u00fcr Informatik, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Universit\u00e4t des Saarlandes, Fachrichtung 6.2 Informatik, Postfach 151150, 66041, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060837952"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.23987777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"145","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11719","display_name":"Data Quality and Management","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9677000045776367,"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":0.8666867613792419},{"id":"https://openalex.org/keywords/xquery","display_name":"XQuery","score":0.7434802651405334},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.6800615787506104},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.58517986536026},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5515609979629517},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5461013913154602},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.543552577495575},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5302398204803467},{"id":"https://openalex.org/keywords/semi-structured-data","display_name":"Semi-structured data","score":0.49913620948791504},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42861172556877136},{"id":"https://openalex.org/keywords/xml-schema-editor","display_name":"XML Schema Editor","score":0.42372581362724304},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.3521595895290375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8666867613792419},{"id":"https://openalex.org/C2780512708","wikidata":"https://www.wikidata.org/wiki/Q850661","display_name":"XQuery","level":4,"score":0.7434802651405334},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.6800615787506104},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.58517986536026},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5515609979629517},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5461013913154602},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.543552577495575},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5302398204803467},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.49913620948791504},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42861172556877136},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.42372581362724304},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.3521595895290375},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-540-45194-5_10","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-45194-5_10","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:edoc.mpg.de:201792","is_oa":false,"landing_page_url":"http://edoc.mpg.de/201792","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Intelligent Search on XML Data : Applications, Languages, Models, Implementations, and Benchmarks, 145-157 (2003)","raw_type":"InBook"},{"id":"pmh:oai:pure.mpg.de:item_1330006","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000F-2C7E-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Intelligent Search on XML Data : Applications, Languages, Models, Implementations, and Benchmarks","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2355446901","https://openalex.org/W2486756614","https://openalex.org/W2073024456","https://openalex.org/W4213327256","https://openalex.org/W2062115694","https://openalex.org/W1997305375","https://openalex.org/W4252166815","https://openalex.org/W214946328","https://openalex.org/W4253215314","https://openalex.org/W4206947581"],"abstract_inverted_index":null,"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
