{"id":"https://openalex.org/W1824331018","doi":"https://doi.org/10.1007/3-540-45164-1_11","title":"Wrapper Generation via Grammar Induction","display_name":"Wrapper Generation via Grammar Induction","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W1824331018","doi":"https://doi.org/10.1007/3-540-45164-1_11","mag":"1824331018"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-45164-1_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-45164-1_11","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/A5046897413","display_name":"Boris Chidlovskii","orcid":"https://orcid.org/0000-0002-2958-2361"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Boris Chidlovskii","raw_affiliation_strings":["Xerox Research Centre Europe, 6, Chemin de Maupertuis, 38240, Meylan, France"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, 6, Chemin de Maupertuis, 38240, Meylan, France","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072111046","display_name":"Jon Ragetli","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jon Ragetli","raw_affiliation_strings":["ILLC, University of Amsterdam, Pl. Muidergracht 24, 1018 TV, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"ILLC, University of Amsterdam, Pl. Muidergracht 24, 1018 TV, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten de Rijke","raw_affiliation_strings":["ILLC, University of Amsterdam, Pl. Muidergracht 24, 1018 TV, Amsterdam, The Netherlands"],"affiliations":[{"raw_affiliation_string":"ILLC, University of Amsterdam, Pl. Muidergracht 24, 1018 TV, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046897413"],"corresponding_institution_ids":["https://openalex.org/I33976269"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":5.3573,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95567867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"108"},"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":0.996999979019165,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8528916835784912},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.747912585735321},{"id":"https://openalex.org/keywords/metasearch-engine","display_name":"Metasearch engine","score":0.6347874402999878},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6096312999725342},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5055849552154541},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4676377773284912},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4530888795852661},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.4143088459968567},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3602498769760132},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.3216395378112793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8528916835784912},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.747912585735321},{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.6347874402999878},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6096312999725342},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5055849552154541},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4676377773284912},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4530888795852661},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.4143088459968567},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3602498769760132},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3216395378112793},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1007/3-540-45164-1_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-45164-1_11","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:dare.uva.nl:openaire_cris_publications/a0156dcb-ed9f-4253-9960-f60b84d64401","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/wrapper-generation-via-grammar-induction(a0156dcb-ed9f-4253-9960-f60b84d64401).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Chidlovskii, B, Ragetli, H J N & de Rijke, M 2000, 'Wrapper generation via grammar induction', Lecture Notes in Computer Science, vol. 1810.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.7090","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.7090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.146.1522","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.146.1522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://remote.science.uva.nl/~mdr/Publications/File/ecml2000.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.29.8433","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.8433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://turing.wins.uva.nl/~ragetli/documents/chidlovskii.ps","raw_type":"text"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/a0156dcb-ed9f-4253-9960-f60b84d64401","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/wrapper-generation-via-grammar-induction(a0156dcb-ed9f-4253-9960-f60b84d64401).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lecture Notes in Computer Science, 1810. Springer Verlag","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1487227972","https://openalex.org/W1553019137","https://openalex.org/W1564013439","https://openalex.org/W2065568440","https://openalex.org/W2072881690","https://openalex.org/W2100985186","https://openalex.org/W2105976259","https://openalex.org/W2124918383","https://openalex.org/W2136500370","https://openalex.org/W2137096228","https://openalex.org/W2164765168"],"related_works":["https://openalex.org/W2222022498","https://openalex.org/W1672860847","https://openalex.org/W2374021970","https://openalex.org/W2185312392","https://openalex.org/W2060088491","https://openalex.org/W2181560882","https://openalex.org/W2351412568","https://openalex.org/W4233958997","https://openalex.org/W3210975432","https://openalex.org/W2184474188"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
