{"id":"https://openalex.org/W2171500543","doi":null,"title":"Using Bloom Filters to Refine Web Search Results.","display_name":"Using Bloom Filters to Refine Web Search Results.","publication_year":2005,"publication_date":"2005-06-16","ids":{"openalex":"https://openalex.org/W2171500543","mag":"2171500543"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.82.1214","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.82.1214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/dahlin/papers/webdb-167.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5110206345","display_name":"Navendu Jain","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Navendu Jain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113668705","display_name":"Michael D. Dahlin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Dahlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113704478","display_name":"Renu Tewari","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renu Tewari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0328,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.94063579,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4706999957561493,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4706999957561493,"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/T11269","display_name":"Algorithms and Data Compression","score":0.3458999991416931,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.09560000151395798,"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/bloom-filter","display_name":"Bloom filter","score":0.996999979019165},{"id":"https://openalex.org/keywords/near-duplicate-detection","display_name":"near-duplicate detection","score":0.7680000066757202},{"id":"https://openalex.org/keywords/document-similarity","display_name":"document similarity","score":0.8500000238418579},{"id":"https://openalex.org/keywords/content-defined-chunking","display_name":"content-defined chunking","score":0.9279999732971191},{"id":"https://openalex.org/keywords/search-engine-result-pages","display_name":"search engine results","score":0.3970000147819519}],"concepts":[{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.924433708190918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983255982398987},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6947112083435059},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.6946881413459778},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.644449770450592},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5192285180091858},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4871103763580322},{"id":"https://openalex.org/C2776945383","wikidata":"https://www.wikidata.org/wiki/Q7170667","display_name":"Personalized search","level":3,"score":0.4409443438053131},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4393622875213623},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.42265379428863525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3633905053138733},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.23639535903930664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17596909403800964},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08781510591506958},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0767657458782196},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.82.1214","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.82.1214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/dahlin/papers/webdb-167.pdf","raw_type":"text"},{"id":"mag:2171500543","doi":null,"is_oa":false,"landing_page_url":"https://research.microsoft.com/en-us/um/people/navendu/mypapers/webdb-167.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420358","display_name":"International Workshop on the Web and Databases","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Workshop on the Web and Databases","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1984566373","https://openalex.org/W2056980397","https://openalex.org/W2148885851","https://openalex.org/W2169189540"],"related_works":["https://openalex.org/W7098604161","https://openalex.org/W2794843716","https://openalex.org/W7098364530","https://openalex.org/W2793533000","https://openalex.org/W4200416674","https://openalex.org/W149382220","https://openalex.org/W7101069294","https://openalex.org/W7099744005","https://openalex.org/W2355561154","https://openalex.org/W2129290679"],"abstract_inverted_index":{"Search":[0],"engines":[1],"have":[2],"primarily":[3],"focused":[4],"on":[5],"presenting":[6],"the":[7,12,22,34,38,58,63],"most":[8],"relevant":[9],"pages":[10,92],"to":[11,26,37,52,62],"user":[13],"quickly.":[14],"A":[15],"less":[16],"well":[17],"explored":[18],"aspect":[19],"of":[20,102,104],"improving":[21],"search":[23,59,108,113],"experience":[24],"is":[25],"remove":[27],"or":[28,124],"group":[29],"all":[30],"near-duplicate":[31],"documents":[32,75],"in":[33,86],"results":[35,60,103],"presented":[36,61],"user.":[39,64],"In":[40],"this":[41,54],"paper,":[42],"we":[43,66,97],"apply":[44],"a":[45,100],"Bloom":[46,80],"filter":[47],"based":[48],"similarity":[49,94],"detection":[50],"technique":[51,71],"address":[53],"issue":[55],"by":[56],"refining":[57],"First,":[65],"present":[67],"and":[68,79,82,89,106,120],"analyze":[69],"our":[70],"for":[72,93],"finding":[73],"similar":[74,119],"using":[76],"contentdefined":[77],"chunking":[78],"filters,":[81],"demonstrate":[83,98],"its":[84],"effectiveness":[85],"compactly":[87],"representing":[88],"quickly":[90],"matching":[91],"testing.":[95],"Later,":[96],"how":[99],"number":[101],"popular":[105],"random":[107],"queries":[109],"retrieved":[110],"from":[111],"different":[112],"engines,":[114],"Google,":[115],"Yahoo,":[116],"MSN,":[117],"are":[118],"can":[121],"be":[122],"eliminated":[123],"re-organized.":[125],"1.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}