{"id":"https://openalex.org/W200042785","doi":null,"title":"Boosted Wrapper Induction","display_name":"Boosted Wrapper Induction","publication_year":2000,"publication_date":"2000-07-30","ids":{"openalex":"https://openalex.org/W200042785","mag":"200042785"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.23.4524","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.23.4524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucd.ie/staff/nick/home/research/download/freitag-aaai2000.ps.gz","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5080437721","display_name":"Dayne Freitag","orcid":"https://orcid.org/0009-0001-0016-5097","observed_orcids":["https://orcid.org/0009-0001-0016-5097"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dayne Freitag","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051886728","display_name":"Nicholas Kushmerick","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Nicholas Kushmerick","raw_affiliation_strings":["university college dublin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university college dublin","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":42.2035,"has_fulltext":false,"cited_by_count":234,"citation_normalized_percentile":{"value":0.99733508,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"577","last_page":"583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":9.999999747378752e-05,"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/T10181","display_name":"Natural Language Processing Techniques","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/wrapper-induction","display_name":"wrapper induction","score":0.9959999918937683},{"id":"https://openalex.org/keywords/boosting","display_name":"boosting","score":0.9580000042915344},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.9599999785423279},{"id":"https://openalex.org/keywords/extraction-patterns","display_name":"extraction patterns","score":0.5400000214576721},{"id":"https://openalex.org/keywords/web-page-extraction","display_name":"web page extraction","score":0.46700000762939453}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8769989013671875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886192798614502},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6608569025993347},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6396878957748413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5879181623458862},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5626362562179565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5420061945915222},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44430011510849},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36074742674827576},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10521957278251648},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.23.4524","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.23.4524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucd.ie/staff/nick/home/research/download/freitag-aaai2000.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.26.3949","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.3949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.fac.cs.cmu.edu/afs/cs.cmu.edu/user/dayne/www/ps/bwi.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.164","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/AAAI/2000/AAAI00-088.pdf","raw_type":"text"},{"id":"mag:200042785","doi":null,"is_oa":false,"landing_page_url":"https://www.aaai.org/Papers/AAAI/2000/AAAI00-088.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"National Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.800000011920929,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1547214099","https://openalex.org/W1553019137","https://openalex.org/W1553229631","https://openalex.org/W1554734378","https://openalex.org/W1602152045","https://openalex.org/W1616576116","https://openalex.org/W2032210760","https://openalex.org/W2046491822","https://openalex.org/W2065568440","https://openalex.org/W2135479443","https://openalex.org/W2147810216","https://openalex.org/W2162340487","https://openalex.org/W2163915185","https://openalex.org/W2163918411"],"related_works":["https://openalex.org/W2163915185","https://openalex.org/W2162340487","https://openalex.org/W2143349571","https://openalex.org/W2135479443","https://openalex.org/W1616576116","https://openalex.org/W1553019137","https://openalex.org/W2160196229","https://openalex.org/W2104086170","https://openalex.org/W2115461474","https://openalex.org/W2065568440","https://openalex.org/W1999595522","https://openalex.org/W1499578805","https://openalex.org/W1602152045","https://openalex.org/W2066636486","https://openalex.org/W1553229631","https://openalex.org/W2145948275","https://openalex.org/W2093559286","https://openalex.org/W2015551056","https://openalex.org/W2153072229","https://openalex.org/W138033052"],"abstract_inverted_index":{"Recent":[0],"work":[1],"in":[2,151],"machine":[3,93],"learning":[4,31,94],"for":[5,36,76,86],"information":[6,79,125,136],"extraction":[7,33,80,117,126,137],"has":[8],"focused":[9],"on":[10],"two":[11],"distinct":[12],"sub-problems:":[13],"the":[14,26,67,88,101],"conventional":[15,78,124],"problem":[16,27],"of":[17,28,70,90],"filling":[18],"template":[19],"slots":[20],"from":[21],"natural":[22],"language":[23],"text,":[24],"and":[25,63,144],"wrapper":[29,53],"induction,":[30],"simple":[32,62,92],"procedures":[34],"(\"wrappers\")":[35],"highly":[37,64],"structured":[38],"text":[39],"such":[40],"as":[41],"Web":[42],"pages":[43],"produced":[44],"by":[45,96],"CGI":[46],"scripts.":[47],"For":[48],"suitably":[49],"regular":[50],"domains,":[51],"existing":[52],"induction":[54],"algorithms":[55,72],"can":[56],"efficiently":[57],"learn":[58],"wrappers":[59],"that":[60,112],"are":[61],"accurate,":[65],"but":[66],"regularity":[68],"bias":[69,143],"these":[71],"makes":[73],"them":[74],"unsuitable":[75],"most":[77],"tasks.":[81],"Boosting":[82],"is":[83,132],"a":[84,91,134,140],"technique":[85],"improving":[87],"performance":[89,146],"algorithm":[95,111],"repeatedly":[97],"applying":[98],"it":[99],"to":[100,123],"training":[102],"set":[103],"with":[104,139],"different":[105],"example":[106],"weightings.":[107],"We":[108],"describe":[109],"an":[110],"learns":[113],"simple,":[114],"low-coverage":[115],"wrapper-like":[116],"patterns,":[118],"which":[119],"we":[120],"then":[121],"apply":[122],"problems":[127],"using":[128],"boosting.":[129],"The":[130],"result":[131],"BWI,":[133],"trainable":[135],"system":[138],"strong":[141],"precision":[142],"F1":[145],"better":[147],"than":[148],"state-of-the-art":[149],"techniques":[150],"many":[152],"domains.":[153]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}