{"id":"https://openalex.org/W1971415141","doi":"https://doi.org/10.1145/1772690.1772826","title":"Exploiting content redundancy for web information extraction","display_name":"Exploiting content redundancy for web information extraction","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W1971415141","doi":"https://doi.org/10.1145/1772690.1772826","mag":"1971415141"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772826","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pankaj Gulhane","raw_affiliation_strings":["Yahoo!, Bangalore, India","Yahoo , Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo , Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111717871","display_name":"Rajeev Rastogi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajeev Rastogi","raw_affiliation_strings":["Yahoo!, Bangalore, India","Yahoo , Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo , Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038858575","display_name":"Srinivasan H. Sengamedu","orcid":"https://orcid.org/0000-0003-1847-8398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivasan H. Sengamedu","raw_affiliation_strings":["Yahoo!, Bangalore, India","Yahoo , Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo , Bangalore, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001061675","display_name":"Ashwin Tengli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashwin Tengli","raw_affiliation_strings":["Yahoo!, Bangalore, India","Yahoo , Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo , Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069516740"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.569,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.98494429,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1105","last_page":"1106"},"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":0.996399998664856,"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":0.9794999957084656,"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":0.8172341585159302},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7320820689201355},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7044455409049988},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6126585006713867},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5515518188476562},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5515154600143433},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5404937863349915},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.4779343903064728},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42283207178115845},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42181649804115295},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4159855246543884},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3308961093425751},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1594228446483612},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09809926152229309}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172341585159302},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7320820689201355},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7044455409049988},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6126585006713867},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5515518188476562},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5515154600143433},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5404937863349915},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.4779343903064728},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42283207178115845},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42181649804115295},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4159855246543884},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3308961093425751},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1594228446483612},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09809926152229309},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1772690.1772826","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.5930","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.5930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/%7Evldb2010/proceedings/files/papers/R51.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","score":0.4099999964237213,"display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"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"],"related_works":["https://openalex.org/W2002428578","https://openalex.org/W2897258045","https://openalex.org/W3005646551","https://openalex.org/W2018406690","https://openalex.org/W2072332896","https://openalex.org/W2951748633","https://openalex.org/W2057691131","https://openalex.org/W2542042335","https://openalex.org/W2952039693","https://openalex.org/W4280621979"],"abstract_inverted_index":{"We":[0,21,36,79],"propose":[1],"a":[2,25,32],"novel":[3],"extraction":[4,114],"approach":[5],"that":[6,47,69],"exploits":[7],"content":[8],"redundancy":[9],"on":[10],"the":[11,41,53,67,110],"web":[12,19,106],"to":[13,85,108],"extract":[14],"structured":[15],"data":[16,107],"from":[17,31],"template-based":[18,77],"sites.":[20,35,78],"start":[22],"by":[23],"populating":[24],"seed":[26,54],"database":[27],"with":[28,91,104],"records":[29],"extracted":[30],"few":[33],"initial":[34],"then":[37],"identify":[38],"values":[39,50,71,94],"within":[40,76],"pages":[42],"of":[43,56,112],"each":[44],"new":[45],"site":[46],"match":[48],"attribute":[49,62,70,88],"contained":[51],"in":[52],"set":[55],"records.":[57],"To":[58],"filter":[59],"out":[60],"noisy":[61],"value":[63],"matches,":[64],"we":[65,98],"exploit":[66],"fact":[68],"occur":[72],"at":[73],"fixed":[74],"positions":[75],"develop":[80],"an":[81,100],"efficient":[82],"Apriori-style":[83],"algorithm":[84],"systematically":[86],"enumerate":[87],"position":[89],"configurations":[90],"sufficient":[92],"matching":[93],"across":[95],"pages.":[96],"Finally,":[97],"conduct":[99],"extensive":[101],"experimental":[102],"study":[103],"real-life":[105],"demonstrate":[109],"effectiveness":[111],"our":[113],"approach.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}