{"id":"https://openalex.org/W2134491992","doi":"https://doi.org/10.1145/1718487.1718535","title":"Learning URL patterns for webpage de-duplication","display_name":"Learning URL patterns for webpage de-duplication","publication_year":2010,"publication_date":"2010-02-04","ids":{"openalex":"https://openalex.org/W2134491992","doi":"https://doi.org/10.1145/1718487.1718535","mag":"2134491992"},"language":"en","primary_location":{"id":"doi:10.1145/1718487.1718535","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1718487.1718535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the third ACM international conference on Web search and data mining","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/A5064400393","display_name":"Hema Swetha Koppula","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hema Swetha Koppula","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069768149","display_name":"Krishna P. Leela","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Krishna P. Leela","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103174125","display_name":"Amit Agarwal","orcid":"https://orcid.org/0000-0002-7642-1341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amit Agarwal","raw_affiliation_strings":["Picsquare.com, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Picsquare.com, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049093178","display_name":"Krishna Prasad Chitrapura","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Krishna Prasad Chitrapura","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100896317","display_name":"Sachin Garg","orcid":"https://orcid.org/0009-0004-6719-5866"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sachin Garg","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017186997","display_name":"Amit Sasturkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Amit Sasturkar","raw_affiliation_strings":["Yahoo! Inc., Sunnyvale, CA, USA","Yahoo, Inc., Sunnyvale, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5064400393"],"corresponding_institution_ids":["https://openalex.org/I1325784139"],"apc_list":null,"apc_paid":null,"fwci":10.0552,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.97972866,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"381","last_page":"390"},"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":0.9991999864578247,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8254748582839966},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6789377927780151},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.6120352745056152},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5730452537536621},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.557738721370697},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5564621686935425},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.5523836016654968},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.548225462436676},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5330290794372559},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.49837589263916016},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.46959319710731506},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.31268617510795593},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2997409701347351}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8254748582839966},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6789377927780151},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.6120352745056152},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5730452537536621},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.557738721370697},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5564621686935425},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5523836016654968},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.548225462436676},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5330290794372559},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.49837589263916016},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.46959319710731506},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31268617510795593},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2997409701347351},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1718487.1718535","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1718487.1718535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the third ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.362.630","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.362.630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.wsdm-conference.org/2010/proceedings/docs/p381.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.9959","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.9959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/~hema/papers/wsdm157-koppula.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1587314265","https://openalex.org/W1775663022","https://openalex.org/W1854214752","https://openalex.org/W1986968077","https://openalex.org/W1990061958","https://openalex.org/W2003471189","https://openalex.org/W2012833704","https://openalex.org/W2016746605","https://openalex.org/W2081620935","https://openalex.org/W2085922539","https://openalex.org/W2112104357","https://openalex.org/W2132069633","https://openalex.org/W2139532006","https://openalex.org/W2145349611","https://openalex.org/W2149706766","https://openalex.org/W2152805927","https://openalex.org/W2158601853","https://openalex.org/W2173213060","https://openalex.org/W4241558715"],"related_works":["https://openalex.org/W1506122440","https://openalex.org/W2026132847","https://openalex.org/W4255854114","https://openalex.org/W2120136770","https://openalex.org/W2783570127","https://openalex.org/W3160284424","https://openalex.org/W2152505903","https://openalex.org/W3179756121","https://openalex.org/W2051135816","https://openalex.org/W2297488618"],"abstract_inverted_index":{"Presence":[0],"of":[1,21,31,57,65,96,109,138,175,189],"duplicate":[2],"documents":[3],"in":[4,144,160],"the":[5,17,50,59,93,107,113,134,165,169,176,195],"World":[6],"Wide":[7],"Web":[8],"adversely":[9],"affects":[10],"crawling,":[11],"indexing":[12],"and":[13,38,62,136],"relevance,":[14],"which":[15,72,111],"are":[16,73,125],"core":[18],"building":[19],"blocks":[20],"web":[22],"search.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"present":[28,100],"a":[29,101,182,187],"set":[30,108,188],"techniques":[32,124],"to":[33,68,75,79,92,105,116,168],"mine":[34],"rules":[35,41,166],"from":[36],"URLs":[37,77,146],"utilize":[39],"these":[40],"for":[42,86,147],"de-duplication":[43,87],"using":[44,145,194],"just":[45],"URL":[46,130],"strings":[47],"without":[48],"fetching":[49],"content":[51],"explicitly.":[52],"Our":[53],"technique":[54,104],"is":[55,88,178],"composed":[56],"mining":[58],"crawl":[60],"logs":[61],"utilizing":[63],"clusters":[64],"similar":[66],"pages":[67],"extract":[69],"transformation":[70],"rules,":[71,110],"used":[74],"normalize":[76],"belonging":[78],"each":[80,83],"cluster.":[81],"Preserving":[82],"mined":[84],"rule":[85,122],"not":[89],"efficient":[90],"due":[91],"large":[94,183],"number":[95],"such":[97],"rules.":[98],"We":[99,132],"machine":[102],"learning":[103],"generalize":[106],"reduces":[112],"resource":[114],"footprint":[115],"be":[117],"usable":[118],"at":[119],"web-scale.":[120],"The":[121],"extraction":[123],"robust":[126],"against":[127],"web-site":[128],"specific":[129],"conventions.":[131],"compare":[133],"precision":[135],"scalability":[137],"our":[139,153],"approach":[140,154],"with":[141,162],"recent":[142,171],"efforts":[143],"de-duplication.":[148],"Experimental":[149],"results":[150],"demonstrate":[151],"that":[152],"achieves":[155],"2":[156],"times":[157],"more":[158],"reduction":[159],"duplicates":[161],"only":[163],"half":[164],"compared":[167],"most":[170],"previous":[172],"approach.":[173],"Scalability":[174],"framework":[177],"demonstrated":[179],"by":[180],"performing":[181],"scale":[184],"evaluation":[185],"on":[186],"3":[190],"Billion":[191],"URLs,":[192],"implemented":[193],"MapReduce":[196],"framework.":[197]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
