{"id":"https://openalex.org/W2116595366","doi":"https://doi.org/10.14778/1453856.1453931","title":"Learning to extract form labels","display_name":"Learning to extract form labels","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2116595366","doi":"https://doi.org/10.14778/1453856.1453931","mag":"2116595366"},"language":"en","primary_location":{"id":"doi:10.14778/1453856.1453931","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453931","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","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/A5101764273","display_name":"Hoa T. Nguyen","orcid":"https://orcid.org/0000-0001-6904-6312"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hoa Nguyen","raw_affiliation_strings":["University of Utah Salt Lake City, UT","University of Utah; Salt Lake City; UT"],"affiliations":[{"raw_affiliation_string":"University of Utah Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah; Salt Lake City; UT","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040718465","display_name":"Thanh Nguyen","orcid":"https://orcid.org/0009-0003-5122-2981"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thanh Nguyen","raw_affiliation_strings":["University of Utah Salt Lake City, UT","University of Utah; Salt Lake City; UT"],"affiliations":[{"raw_affiliation_string":"University of Utah Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah; Salt Lake City; UT","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006773757","display_name":"Juliana Freire","orcid":"https://orcid.org/0000-0003-3915-7075"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana Freire","raw_affiliation_strings":["University of Utah Salt Lake City, UT","University of Utah; Salt Lake City; UT"],"affiliations":[{"raw_affiliation_string":"University of Utah Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah; Salt Lake City; UT","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101764273"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":20.3025,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.99170403,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":"1","first_page":"684","last_page":"694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10260","display_name":"Software Engineering Research","score":0.9921000003814697,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8095606565475464},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7240819931030273},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7136869430541992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5293636322021484},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.444210410118103},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4287261664867401},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42261913418769836},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4059803783893585},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3733453154563904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095606565475464},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7240819931030273},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7136869430541992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5293636322021484},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.444210410118103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4287261664867401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42261913418769836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4059803783893585},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3733453154563904},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1453856.1453931","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453931","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W162532313","https://openalex.org/W291262356","https://openalex.org/W343945789","https://openalex.org/W1660981512","https://openalex.org/W1968832971","https://openalex.org/W2026263225","https://openalex.org/W2066636486","https://openalex.org/W2087189381","https://openalex.org/W2101168711","https://openalex.org/W2107539537","https://openalex.org/W2108489852","https://openalex.org/W2110034127","https://openalex.org/W2117058208","https://openalex.org/W2120642948","https://openalex.org/W2123853152","https://openalex.org/W2145102654","https://openalex.org/W2155031665","https://openalex.org/W2160794449","https://openalex.org/W2164896748","https://openalex.org/W2168714803","https://openalex.org/W2170188121","https://openalex.org/W3203633735","https://openalex.org/W6681291871","https://openalex.org/W6685116542","https://openalex.org/W6738852829","https://openalex.org/W7066556469"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W2401723157","https://openalex.org/W2952904874","https://openalex.org/W324626582","https://openalex.org/W4389302559","https://openalex.org/W1690653314"],"abstract_inverted_index":{"In":[0],"this":[1,70],"paper":[2],"we":[3],"describe":[4],"a":[5,20,55,63,86,97,111],"new":[6],"approach":[7,126],"to":[8,27,69,90,105,138],"extract":[9],"element":[10],"labels":[11,18,61],"from":[12],"Web":[13,41,119],"form":[14,36,51,141],"interfaces.":[15],"Having":[16],"these":[17,60],"is":[19,33,62,127,135],"requirement":[21],"for":[22],"several":[23],"techniques":[24],"that":[25,32,124],"attempt":[26],"retrieve":[28],"and":[29,43,76,94,134],"integrate":[30],"information":[31],"hidden":[34,40],"behind":[35],"interfaces,":[37],"such":[38],"as":[39],"crawlers":[42],"metasearchers.":[44],"However,":[45],"given":[46],"the":[47,102],"wide":[48],"variation":[49],"in":[50,140],"layout,":[52],"even":[53],"within":[54],"well-defined":[56],"domain,":[57],"automatically":[58],"extracting":[59],"challenging":[64],"problem.":[65],"Whereas":[66],"previous":[67,144],"approaches":[68],"problem":[71],"have":[72],"relied":[73],"on":[74],"heuristics":[75],"manually":[77],"specified":[78],"extraction":[79,107,146],"rules,":[80],"our":[81,125],"technique":[82],"makes":[83],"use":[84],"of":[85],"learning":[87],"classifier":[88],"ensemble":[89],"identify":[91],"element-label":[92],"mappings;":[93],"it":[95,129],"applies":[96],"reconciliation":[98],"step":[99],"which":[100],"leverages":[101],"classifier-derived":[103],"mappings":[104],"boost":[106],"accuracy.":[108],"We":[109],"present":[110],"detailed":[112],"experimental":[113],"evaluation":[114],"using":[115],"over":[116],"three":[117],"thousand":[118],"forms.":[120],"Our":[121],"results":[122],"show":[123],"effective:":[128],"obtains":[130],"significantly":[131],"higher":[132],"accuracy":[133],"more":[136],"robust":[137],"variability":[139],"layout":[142],"than":[143],"label":[145],"techniques.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":12}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}