{"id":"https://openalex.org/W1984911948","doi":"https://doi.org/10.14778/1920841.1920915","title":"Exploiting content redundancy for web information extraction","display_name":"Exploiting content redundancy for web information extraction","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W1984911948","doi":"https://doi.org/10.14778/1920841.1920915","mag":"1984911948"},"language":"en","primary_location":{"id":"doi:10.14778/1920841.1920915","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920915","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/A5069516740","display_name":"Pankaj Gulhane","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Pankaj Gulhane","raw_affiliation_strings":["Yahoo! Labs, Bangalore"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111717871","display_name":"Rajeev Rastogi","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rajeev Rastogi","raw_affiliation_strings":["Yahoo! Labs, Bangalore"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038858575","display_name":"Srinivasan H. Sengamedu","orcid":"https://orcid.org/0000-0003-1847-8398"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Srinivasan H. Sengamedu","raw_affiliation_strings":["Yahoo! Labs, Bangalore"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001061675","display_name":"Ashwin Tengli","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin Tengli","raw_affiliation_strings":["Microsoft IDC, Bangalore"],"affiliations":[{"raw_affiliation_string":"Microsoft IDC, Bangalore","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069516740"],"corresponding_institution_ids":["https://openalex.org/I2800095910"],"apc_list":null,"apc_paid":null,"fwci":5.5496,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95779347,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":"1-2","first_page":"578","last_page":"587"},"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/T11719","display_name":"Data Quality and Management","score":0.9976999759674072,"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":0.9763000011444092,"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":0.7565354108810425},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6830452680587769},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6084100008010864},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5725125074386597},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5159926414489746},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5102136135101318},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5083672404289246},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4928164780139923},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4686903953552246},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4545454680919647},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43117645382881165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2513827383518219},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16839492321014404},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10219073295593262},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07285416126251221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565354108810425},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6830452680587769},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6084100008010864},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5725125074386597},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5159926414489746},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5102136135101318},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5083672404289246},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4928164780139923},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4686903953552246},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4545454680919647},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43117645382881165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2513827383518219},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16839492321014404},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10219073295593262},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07285416126251221},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1920841.1920915","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920915","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":[{"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1484413656","https://openalex.org/W1489949474","https://openalex.org/W1532325895","https://openalex.org/W1553019137","https://openalex.org/W1616576116","https://openalex.org/W1973483159","https://openalex.org/W1977970897","https://openalex.org/W2007682403","https://openalex.org/W2029873015","https://openalex.org/W2038281398","https://openalex.org/W2067566391","https://openalex.org/W2088179629","https://openalex.org/W2103931177","https://openalex.org/W2104086170","https://openalex.org/W2105423800","https://openalex.org/W2108991785","https://openalex.org/W2116544254","https://openalex.org/W2117209866","https://openalex.org/W2121516976","https://openalex.org/W2124410446","https://openalex.org/W2135326109","https://openalex.org/W2143309843","https://openalex.org/W2154445423","https://openalex.org/W2164456230","https://openalex.org/W2171364811","https://openalex.org/W6628750762","https://openalex.org/W6633154970","https://openalex.org/W6680002762"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297"],"abstract_inverted_index":{"We":[0,21,36,130],"propose":[1],"a":[2,25,32,69],"novel":[3],"extraction":[4,165],"approach":[5],"that":[6,47,73,120],"exploits":[7],"content":[8],"redundancy":[9],"on":[10],"the":[11,41,53,75,85,118,161],"web":[12,19,157],"to":[13,97,109,136,159],"extract":[14],"structured":[15],"data":[16,158],"from":[17,31,91],"template-based":[18,128],"sites.":[20,35,129],"start":[22],"by":[23],"populating":[24],"seed":[26,54],"database":[27],"with":[28,62,142,155],"records":[29],"extracted":[30],"few":[33],"initial":[34],"then":[37],"identify":[38],"values":[39,50,61,90,103,122,145],"within":[40,127],"pages":[42],"of":[43,56,78,101,163],"each":[44],"new":[45,70],"site":[46],"match":[48,59],"attribute":[49,60,79,89,102,113,121,139],"contained":[51],"in":[52],"set":[55],"records.":[57],"To":[58],"diverse":[63],"representations":[64],"across":[65,146],"sites,":[66,93],"we":[67,116,149],"define":[68],"similarity":[71,106],"metric":[72,83],"leverages":[74],"templatized":[76],"structure":[77],"content.":[80],"Specifically,":[81],"our":[82,164],"discovers":[84],"matching":[86,144],"pattern":[87],"between":[88],"two":[92],"and":[94],"uses":[95],"this":[96],"ignore":[98],"extraneous":[99],"portions":[100],"when":[104],"computing":[105],"scores.":[107],"Further,":[108],"filter":[110],"out":[111],"noisy":[112],"value":[114],"matches,":[115],"exploit":[117],"fact":[119],"occur":[123],"at":[124],"fixed":[125],"positions":[126],"develop":[131],"an":[132,151],"efficient":[133],"Apriori-style":[134],"algorithm":[135],"systematically":[137],"enumerate":[138],"position":[140],"configurations":[141],"sufficient":[143],"pages.":[147],"Finally,":[148],"conduct":[150],"extensive":[152],"experimental":[153],"study":[154],"real-life":[156],"demonstrate":[160],"effectiveness":[162],"approach.":[166]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}