{"id":"https://openalex.org/W2143309843","doi":"https://doi.org/10.1145/1060745.1060761","title":"Web data extraction based on partial tree alignment","display_name":"Web data extraction based on partial tree alignment","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2143309843","doi":"https://doi.org/10.1145/1060745.1060761","mag":"2143309843"},"language":"en","primary_location":{"id":"doi:10.1145/1060745.1060761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web - WWW '05","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5053521782","display_name":"Yanhong Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanhong Zhai","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, IL","University of Illinois at Chicago, Chicago IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, IL","institution_ids":["https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Illinois at Chicago, Chicago IL","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339927","display_name":"Bing Liu","orcid":"https://orcid.org/0000-0002-4096-6980"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bing Liu","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, IL","University of Illinois at Chicago, Chicago IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, IL","institution_ids":["https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Illinois at Chicago, Chicago IL","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":497,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"76"},"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":0.9882000088691711,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9836000204086304,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.852729320526123},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6119152307510376},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5689966082572937},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5652961730957031},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5177168250083923},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5099190473556519},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5098249316215515},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.44909438490867615},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.44246265292167664},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4158182740211487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3007638454437256},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14465820789337158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.852729320526123},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6119152307510376},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5689966082572937},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5652961730957031},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5177168250083923},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5099190473556519},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5098249316215515},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.44909438490867615},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.44246265292167664},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4158182740211487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3007638454437256},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14465820789337158},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1060745.1060761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web - WWW '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.277","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uic.edu/~liub/publications/www05-p516.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.96.4297","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.96.4297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2005.org/cdrom/docs/p76.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W124283286","https://openalex.org/W1506845741","https://openalex.org/W1527979595","https://openalex.org/W1974326986","https://openalex.org/W1975009259","https://openalex.org/W1988217119","https://openalex.org/W1990061958","https://openalex.org/W1996681309","https://openalex.org/W2002393437","https://openalex.org/W2015551056","https://openalex.org/W2026080185","https://openalex.org/W2034797903","https://openalex.org/W2040075907","https://openalex.org/W2049461910","https://openalex.org/W2057294899","https://openalex.org/W2064716575","https://openalex.org/W2065568440","https://openalex.org/W2069388662","https://openalex.org/W2078206655","https://openalex.org/W2085533860","https://openalex.org/W2093559286","https://openalex.org/W2096496923","https://openalex.org/W2104086170","https://openalex.org/W2122282348","https://openalex.org/W2128613007","https://openalex.org/W2128836931","https://openalex.org/W2129595335","https://openalex.org/W2135479443","https://openalex.org/W2143513829","https://openalex.org/W2150721933","https://openalex.org/W2153072229","https://openalex.org/W2160196229","https://openalex.org/W2166407869","https://openalex.org/W2167859982","https://openalex.org/W2394167421"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W3135843367","https://openalex.org/W2611741382","https://openalex.org/W3112355890","https://openalex.org/W2613685774","https://openalex.org/W4301594054","https://openalex.org/W4220741973","https://openalex.org/W2794488505","https://openalex.org/W2326464900","https://openalex.org/W36911888"],"abstract_inverted_index":{"This":[0,39,121,228],"paper":[1,122],"studies":[2],"the":[3,33,91,99,129,153,222,225,252],"problem":[4,40],"of":[5,58,69,94,104,134,206,224,234,244],"extracting":[6,81,149],"data":[7,16,24,27,34,82,140,150,155,170,201,207,226,236,260,265],"from":[8,29,72,152,247,266],"a":[9,36,124,143,162,184,204,241],"Web":[10,74,245],"page":[11],"that":[12,76,196,209,251],"contains":[13],"several":[14,45],"structured":[15],"records.":[17,156,237],"The":[18,55,84,101],"objective":[19],"is":[20,60,78,86,106,173,256],"to":[21,90,127,168,258],"segment":[22,169,259],"these":[23],"records,":[25,171,261],"extract":[26,264],"items/fields":[28],"them":[30,267],"and":[31,96,145,148,217,263],"put":[32],"in":[35,80,142,203],"database":[37],"table.":[38],"has":[41],"been":[42],"studied":[43],"by":[44],"researchers.":[46],"However,":[47],"existing":[48,177],"methods":[49,59,113],"still":[50],"have":[51],"some":[52],"serious":[53],"limitations.":[54],"first":[56],"class":[57,103],"based":[61,107,164,189],"on":[62,98,108,165,190,221],"machine":[63],"learning,":[64],"which":[65,172],"requires":[66],"human":[67],"labeling":[68],"many":[70,119],"examples":[71],"each":[73],"site":[75],"one":[77],"interested":[79],"from.":[83],"process":[85],"time":[87],"consuming":[88],"due":[89],"large":[92,242],"number":[93,243],"sites":[95],"pages":[97,246],"Web.":[100],"second":[102],"algorithms":[105],"automatic":[109],"pattern":[110],"discovery.":[111],"These":[112],"are":[114],"either":[115],"inaccurate":[116],"or":[117],"make":[118,218],"assumptions.":[120],"proposes":[123],"new":[125],"method":[126,163],"perform":[128],"task":[130],"automatically.":[131],"It":[132],"consists":[133],"two":[135],"steps,":[136],"(1)":[137],"identifying":[138],"individual":[139],"records":[141,208],"page,":[144],"(2)":[146],"aligning":[147],"items":[151],"identified":[154],"For":[157,179],"step":[158,180],"1,":[159],"we":[160,182,197],"propose":[161,183],"visual":[166],"information":[167],"more":[174],"accurate":[175,232],"than":[176],"methods.":[178],"2,":[181],"novel":[185],"partial":[186],"alignment":[187,194,233],"technique":[188,255],"tree":[191],"matching.":[192],"Partial":[193],"means":[195],"align":[198,262],"only":[199],"those":[200],"fields":[202],"pair":[205],"can":[210],"be":[211],"aligned":[212],"(or":[213],"matched)":[214],"with":[215],"certainty,":[216],"no":[219],"commitment":[220],"rest":[223],"fields.":[227],"approach":[229],"enables":[230],"very":[231,268],"multiple":[235],"Experimental":[238],"results":[239],"using":[240],"diverse":[248],"domains":[249],"show":[250],"proposed":[253],"two-step":[254],"able":[257],"accurately.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":30},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":23},{"year":2013,"cited_by_count":47},{"year":2012,"cited_by_count":38}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}