{"id":"https://openalex.org/W1994382199","doi":"https://doi.org/10.1145/1189740.1189746","title":"Adapting Web information extraction knowledge via mining site-invariant and site-dependent features","display_name":"Adapting Web information extraction knowledge via mining site-invariant and site-dependent features","publication_year":2007,"publication_date":"2007-02-01","ids":{"openalex":"https://openalex.org/W1994382199","doi":"https://doi.org/10.1145/1189740.1189746","mag":"1994382199"},"language":"en","primary_location":{"id":"doi:10.1145/1189740.1189746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1189740.1189746","pdf_url":null,"source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"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":"ACM Transactions on Internet Technology","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/A5101515462","display_name":"Tak-Lam Wong","orcid":"https://orcid.org/0000-0002-4581-9912"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tak-Lam Wong","raw_affiliation_strings":["City University of Hong Kong, Kowloon, Hong Kong","City University of Hong Kong , Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"City University of Hong Kong , Kowloon, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018582154","display_name":"Wai Lam","orcid":"https://orcid.org/0000-0001-5479-377X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4617,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96710138,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":"1","first_page":"6","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11719","display_name":"Data Quality and Management","score":0.9934999942779541,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.991599977016449,"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/computer-science","display_name":"Computer science","score":0.8116693496704102},{"id":"https://openalex.org/keywords/web-site","display_name":"Web site","score":0.6737493276596069},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.611768901348114},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5697254538536072},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5452710390090942},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5418160557746887},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.5006082057952881},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4697226583957672},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43619304895401},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4190065860748291},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41806524991989136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41292983293533325},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3033628463745117},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07060542702674866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116693496704102},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.6737493276596069},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.611768901348114},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5697254538536072},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5452710390090942},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5418160557746887},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.5006082057952881},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4697226583957672},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43619304895401},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4190065860748291},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41806524991989136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41292983293533325},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3033628463745117},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07060542702674866},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1189740.1189746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1189740.1189746","pdf_url":null,"source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"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":"ACM Transactions on Internet Technology","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.111.9640","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.9640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.cuhk.edu.hk/~wongtl/papers/wongtl-toit.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W48537574","https://openalex.org/W50894374","https://openalex.org/W138033052","https://openalex.org/W157725869","https://openalex.org/W197270748","https://openalex.org/W938539187","https://openalex.org/W1489949474","https://openalex.org/W1499578805","https://openalex.org/W1538404166","https://openalex.org/W1593345689","https://openalex.org/W1606262545","https://openalex.org/W1616576116","https://openalex.org/W1847465294","https://openalex.org/W1971695131","https://openalex.org/W1983326645","https://openalex.org/W1990061958","https://openalex.org/W1999595522","https://openalex.org/W2008214196","https://openalex.org/W2013725398","https://openalex.org/W2015551056","https://openalex.org/W2026080185","https://openalex.org/W2044030465","https://openalex.org/W2065568440","https://openalex.org/W2069388662","https://openalex.org/W2093559286","https://openalex.org/W2101007018","https://openalex.org/W2104086170","https://openalex.org/W2111625757","https://openalex.org/W2115770258","https://openalex.org/W2135479443","https://openalex.org/W2138405339","https://openalex.org/W2145948275","https://openalex.org/W2148540243","https://openalex.org/W2155714156","https://openalex.org/W2156909104","https://openalex.org/W2158941357","https://openalex.org/W2162340487","https://openalex.org/W2164456230","https://openalex.org/W2170902582","https://openalex.org/W2172549414","https://openalex.org/W2291485057","https://openalex.org/W2610179052","https://openalex.org/W2912161846","https://openalex.org/W2964041960","https://openalex.org/W4213245422","https://openalex.org/W4226054531","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2083329789","https://openalex.org/W36911888","https://openalex.org/W2376574812","https://openalex.org/W4385731361","https://openalex.org/W2004087619","https://openalex.org/W1982302668","https://openalex.org/W2362196274","https://openalex.org/W2557094866","https://openalex.org/W2757101400","https://openalex.org/W2240384024"],"abstract_inverted_index":{"We":[0,182],"develop":[1],"a":[2,16,21,52,77,141,187],"novel":[3],"framework":[4],"that":[5],"aims":[6],"at":[7],"automatically":[8,139,163,222],"adapting":[9],"previously":[10,115,122],"learned":[11,116],"information":[12,175,224],"extraction":[13,117,176],"knowledge":[14,118,177],"from":[15,39,63,89,102,114,126,194,212,225],"source":[17,128],"Web":[18,41,61,86,91,99,129,191,217],"site":[19,25],"to":[20,35,138,198],"new":[22,142,149,174],"unseen":[23,150],"target":[24,151,180],"in":[26,60,66,84,97,147,170],"the":[27,36,40,67,85,98,103,111,120,127,148,154,158,171,179,200],"same":[28,68,104],"domain.":[29,69],"Two":[30],"kinds":[31],"of":[32,48,73,144,161,173,189,202,237],"features":[33,56,81,113,134,156,160],"related":[34],"text":[37],"fragments":[38],"documents":[42],"are":[43,82,95],"investigated.":[44],"The":[45,70,131],"first":[46],"type":[47,72],"feature":[49,74],"is":[50,75],"called,":[51],"site-invariant":[53,112,133,159],"feature.":[54,79],"These":[55,80],"likely":[57],"remain":[58],"unchanged":[59],"pages":[62,87,100],"different":[64,83,90,196,227],"sites":[65,192,230],"second":[71],"called":[76],"site-dependent":[78,155],"collected":[88,123,193],"sites,":[92],"while":[93],"they":[94],"similar":[96],"originating":[101],"site.":[105,130,152,181],"In":[106],"our":[107,203,219],"framework,":[108],"we":[109],"derive":[110],"and":[119,157,235,239],"items":[121],"or":[124],"extracted":[125],"derived":[132],"will":[135,167],"be":[136,168],"exploited":[137],"seek":[140],"set":[143,188],"training":[145,165,210],"examples":[146,166,211],"Both":[153],"these":[162],"discovered":[164],"considered":[169],"learning":[172],"for":[178],"conducted":[183],"extensive":[184],"experiments":[185],"on":[186],"real-world":[190],"three":[195],"domains":[197],"demonstrate":[199],"performance":[201],"framework.":[204],"For":[205],"example,":[206],"by":[207],"just":[208],"providing":[209],"one":[213],"online":[214],"book":[215,228],"catalog":[216,229],"site,":[218],"approach":[220],"can":[221],"extract":[223],"ten":[226],"achieving":[231],"an":[232],"average":[233],"precision":[234],"recall":[236],"71.9%":[238],"84.0%":[240],"respectively":[241],"without":[242],"any":[243],"further":[244],"manual":[245],"intervention.":[246]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}