{"id":"https://openalex.org/W1986968077","doi":"https://doi.org/10.1145/1401890.1401917","title":"De-duping URLs via rewrite rules","display_name":"De-duping URLs via rewrite rules","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W1986968077","doi":"https://doi.org/10.1145/1401890.1401917","mag":"1986968077"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401917","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 ACM SIGKDD international conference on Knowledge discovery 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/A5061449196","display_name":"Anirban Dasgupta","orcid":"https://orcid.org/0000-0002-8494-3692"},"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":true,"raw_author_name":"Anirban Dasgupta","raw_affiliation_strings":["Yahoo!, Sunnyvale, CA, USA","Yahoo!, Sunnyvale, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo!, Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107809381","display_name":"Ravi Kumar","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":"Ravi Kumar","raw_affiliation_strings":["Yahoo!, Sunnyvale, CA, USA","Yahoo!, Sunnyvale, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo!, Sunnyvale, CA, USA#TAB#","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!, Sunnyvale, CA, USA","Yahoo!, Sunnyvale, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo!, Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061449196"],"corresponding_institution_ids":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":8.83,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.97285431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9979000091552734,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.995199978351593,"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":0.7212885022163391},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7031158208847046},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6566227674484253},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5937663912773132},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5198807716369629},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5147697925567627},{"id":"https://openalex.org/keywords/equivalence-class","display_name":"Equivalence class (music)","score":0.5032281279563904},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.4520735740661621},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43825218081474304},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4345332384109497},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33852332830429077},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1772957146167755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16602745652198792},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.11305767297744751},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10800275206565857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7212885022163391},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7031158208847046},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6566227674484253},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5937663912773132},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5198807716369629},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5147697925567627},{"id":"https://openalex.org/C2777044963","wikidata":"https://www.wikidata.org/wiki/Q5384707","display_name":"Equivalence class (music)","level":2,"score":0.5032281279563904},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4520735740661621},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43825218081474304},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4345332384109497},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33852332830429077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1772957146167755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16602745652198792},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.11305767297744751},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10800275206565857},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1401890.1401917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401917","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 ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1559390933","https://openalex.org/W1965415591","https://openalex.org/W2012604221","https://openalex.org/W2012767282","https://openalex.org/W2012833704","https://openalex.org/W2049955619","https://openalex.org/W2061079066","https://openalex.org/W2085922539","https://openalex.org/W2092386826","https://openalex.org/W2101069192","https://openalex.org/W2112104357","https://openalex.org/W2129598390","https://openalex.org/W2132069633","https://openalex.org/W2139532006","https://openalex.org/W2145349611","https://openalex.org/W2152565070","https://openalex.org/W2257424246","https://openalex.org/W4241558715"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W4255854114"],"abstract_inverted_index":{"A":[0],"large":[1],"fraction":[2],"of":[3,29,45,61,72,95,108],"the":[4,7,26,43,49,59,62,80,84,93,113,133],"URLs":[5,15,73,107,128],"on":[6,79],"web":[8],"contain":[9],"duplicate":[10,46],"(or":[11],"near-duplicate)":[12],"content.":[13,142],"De-duping":[14],"is":[16,67],"an":[17,109],"extremely":[18],"important":[19],"problem":[20,51,94],"for":[21,132],"search":[22,31],"engines,":[23],"since":[24],"all":[25,106],"principal":[27],"functions":[28],"a":[30,70],"engine,":[32],"including":[33],"crawling,":[34,137],"indexing,":[35],"ranking,":[36],"and":[37,57,99],"presentation,":[38],"are":[39,130],"adversely":[40],"impacted":[41],"by":[42,55],"presence":[44],"URLs.":[47],"Traditionally,":[48],"de-duping":[50],"has":[52],"been":[53],"addressed":[54],"fetching":[56,140],"examining":[58],"content":[60,81],"URL;":[63],"our":[64],"approach":[65],"here":[66],"different.":[68],"Given":[69],"set":[71,98],"partitioned":[74],"into":[75],"equivalence":[76,86,110],"classes":[77],"based":[78],"(URLs":[82],"in":[83],"same":[85,114],"class":[87,111],"have":[88],"similar":[89],"content),":[90],"we":[91],"address":[92],"mining":[96],"this":[97],"learning":[100],"URL":[101],"rewrite":[102,118],"rules":[103,119],"that":[104,129],"transform":[105],"to":[112,124],"canonical":[115],"form.":[116],"These":[117],"can":[120],"then":[121],"be":[122],"applied":[123],"eliminate":[125],"duplicates":[126],"among":[127],"encountered":[131],"first":[134],"time":[135],"during":[136],"even":[138],"without":[139],"their":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
