{"id":"https://openalex.org/W2034943479","doi":"https://doi.org/10.1145/2247596.2247638","title":"Searching by corpus with fingerprints","display_name":"Searching by corpus with fingerprints","publication_year":2012,"publication_date":"2012-03-27","ids":{"openalex":"https://openalex.org/W2034943479","doi":"https://doi.org/10.1145/2247596.2247638","mag":"2034943479"},"language":"en","primary_location":{"id":"doi:10.1145/2247596.2247638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","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/A5028089542","display_name":"Char\u0173 C. Aggarwal","orcid":"https://orcid.org/0000-0003-2579-7581"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charu C. Aggarwal","raw_affiliation_strings":["IBM T. J. Watson Research Center, Hawthorne, NY","IBM T.J. Watson Research Center, Hawthorne, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Hawthorne, NY","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM T.J. Watson Research Center, Hawthorne, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100829230","display_name":"Wangqun Lin","orcid":"https://orcid.org/0009-0001-5624-2864"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangqun Lin","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, IL","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3048,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83380573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"348","last_page":"359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9850000143051147,"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":0.6538349986076355},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5240193605422974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5086320638656616},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.45033979415893555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538349986076355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5240193605422974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5086320638656616},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.45033979415893555}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2247596.2247638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.297.6737","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.6737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://charuaggarwal.net/text-indexing.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G153416028","display_name":null,"funder_award_id":"IIS-0905215DBI-0960443CNS-1115234IIS-0914934OISE-1129076OIA-0963278","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G2075106381","display_name":null,"funder_award_id":"IIS-0905215DBI-0960443CNS-1115234IIS-0914934OISE-1129076OIA-0963278","funder_id":"https://openalex.org/F4320337398","funder_display_name":"Division of Biological Infrastructure"},{"id":"https://openalex.org/G2459280394","display_name":null,"funder_award_id":"6.09E+15","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4754481392","display_name":null,"funder_award_id":"IIS-0905215DBI-0960443CNS-1115234IIS-0914934OISE-1129076OIA-0963278","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G5499289178","display_name":null,"funder_award_id":"2010AA012505","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G6312937207","display_name":null,"funder_award_id":"IIS-0905215DBI-0960443CNS-1115234IIS-0914934OISE-1129076OIA-0963278","funder_id":"https://openalex.org/F4320337378","funder_display_name":"Office of Integrative Activities"},{"id":"https://openalex.org/G6584410789","display_name":null,"funder_award_id":"IIS-0905215DBI-0960443CNS-1115234IIS-0914934OISE-1129076OIA-0963278","funder_id":"https://openalex.org/F4320337370","funder_display_name":"Office of International Science and Engineering"},{"id":"https://openalex.org/G948678646","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320337370","display_name":"Office of International Science and Engineering","ror":"https://ror.org/01k638r21"},{"id":"https://openalex.org/F4320337378","display_name":"Office of Integrative Activities","ror":"https://ror.org/04k9mqs78"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"},{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W191231183","https://openalex.org/W1500117362","https://openalex.org/W1956559956","https://openalex.org/W1976535830","https://openalex.org/W1978394996","https://openalex.org/W1981663733","https://openalex.org/W1990061958","https://openalex.org/W2030839740","https://openalex.org/W2055375607","https://openalex.org/W2056707490","https://openalex.org/W2060772621","https://openalex.org/W2084367148","https://openalex.org/W2111593814","https://openalex.org/W2114909134","https://openalex.org/W2125203709","https://openalex.org/W2145766604","https://openalex.org/W2157328170","https://openalex.org/W2160484851","https://openalex.org/W2163652601","https://openalex.org/W4230511558","https://openalex.org/W6640862754"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,211,273],"growing":[1],"sizes":[2],"of":[3,26,39,58,82,105,125,145,150,172,187,220,251,297],"text":[4,22,28,52,85,180],"repositories":[5],"on":[6,55,182,305],"the":[7,27,37,51,56,76,80,91,113,146,165,173,179,205,226,233,247,267,291,295,302],"world":[8],"wide":[9],"web":[10],"has":[11],"created":[12],"a":[13,45,69,72,103,110,184,197],"need":[14,70,154],"for":[15,21,36,71,90,225,237,270,290],"efficient":[16,216,222,259,282],"indexing":[17,31,167],"and":[18,30,50,140,168],"retrieval":[19,29,92],"methods":[20,32],"collections.":[23,255,272,311],"Almost":[24],"all":[25,126],"have":[33],"been":[34],"designed":[35],"case":[38,98],"simple":[40],"keyword":[41],"search,":[42,77],"in":[43,64,101,240,253,308],"which":[44,102,153,202,241,262,285],"few":[46],"keywords":[47,188],"are":[48,132,141],"specified,":[49],"is":[53,68,99,107,120,243,263,280,301],"retrieved":[54],"basis":[57],"matches":[59],"to":[60,112,122,134,137,155,235,245,265,277],"these":[61],"keywords.":[62],"However,":[63],"many":[65],"applications":[66],"there":[67],"greater":[73],"specificity":[74],"during":[75],"such":[78,117],"as":[79,109,135],"use":[81],"phrases,":[83],"sentences,":[84],"fragments,":[86],"or":[87,189],"even":[88,95],"documents":[89,106,252],"process.":[93,115,228,293],"An":[94],"more":[96,207],"general":[97,208],"one":[100],"collection":[104],"available":[108,166,175],"query":[111],"search":[114,218,227,260,268,292,307],"In":[116,192],"cases,":[118],"it":[119,242],"desirable":[121,244],"return":[123],"sets":[124],"pairwise":[127],"similar":[128,249],"documents.":[129],"Such":[130,158],"queries":[131],"referred":[133],"corpus":[136,138],"queries,":[139,239],"computationally":[142],"intensive":[143],"because":[144,219],"very":[147,215],"large":[148,271],"number":[149,186],"document":[151,310],"pairs":[152,250],"be":[156,161,287],"compared.":[157],"cases":[159],"cannot":[160],"efficiently":[162],"processed":[163],"by":[164],"searching":[169],"methods.":[170],"Most":[171],"currently":[174],"techniques":[176],"can":[177,203,213,286],"index":[178,201],"based":[181],"only":[183],"small":[185],"representative":[190],"phrases.":[191],"this":[193,279,300],"paper,":[194],"we":[195],"design":[196,257],"compressed":[198],"finger":[199],"print":[200],"support":[204],"following":[206],"queries:":[209],"(a)":[210],"method":[212,234],"process":[214],"document-to-corpus":[217],"their":[221],"bit-wise":[223],"operations":[224],"(b)":[229],"We":[230,256],"further":[231],"extend":[232],"work":[236,304],"corpus-to-corpus":[238],"determine":[246],"most":[248],"two":[254],"an":[258,281],"technique":[261,275],"able":[264],"reduce":[266],"time":[269],"key":[274],"used":[276,288],"enable":[278],"fingerprint":[283],"representation,":[284],"effectively":[289],"To":[294],"best":[296],"our":[298],"knowledge,":[299],"first":[303],"corpus-based":[306],"massive":[309]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}