{"id":"https://openalex.org/W4402969661","doi":"https://doi.org/10.1145/3677136","title":"Near-Duplicate Text Alignment with One Permutation Hashing","display_name":"Near-Duplicate Text Alignment with One Permutation Hashing","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4402969661","doi":"https://doi.org/10.1145/3677136"},"language":"en","primary_location":{"id":"doi:10.1145/3677136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677136","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-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/A5045267283","display_name":"Zhencan Peng","orcid":"https://orcid.org/0000-0003-4182-0075"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhencan Peng","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0003-4182-0075","affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005906104","display_name":"Y. T. Zhang","orcid":"https://orcid.org/0000-0002-3798-0140"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuheng Zhang","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-3798-0140","affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103237059","display_name":"Dong Deng","orcid":"https://orcid.org/0000-0002-4596-3850"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Deng","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-4596-3850","affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":0.6656,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66885639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"2","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9988999962806702,"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/T12016","display_name":"Web Data Mining and Analysis","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":0.600394070148468},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5859361886978149},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5176854133605957},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48692452907562256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37317442893981934},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11080911755561829},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09876853227615356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.600394070148468},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5859361886978149},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5176854133605957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48692452907562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37317442893981934},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11080911755561829},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09876853227615356},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677136","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W642889137","https://openalex.org/W1790180460","https://openalex.org/W1969153299","https://openalex.org/W2007842132","https://openalex.org/W2025051251","https://openalex.org/W2037450062","https://openalex.org/W2055043387","https://openalex.org/W2065259291","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2092236286","https://openalex.org/W2097776316","https://openalex.org/W2107427524","https://openalex.org/W2119455368","https://openalex.org/W2127713077","https://openalex.org/W2132069633","https://openalex.org/W2134212491","https://openalex.org/W2139660688","https://openalex.org/W2144265691","https://openalex.org/W2144322830","https://openalex.org/W2145065594","https://openalex.org/W2147717514","https://openalex.org/W2148578434","https://openalex.org/W2150916025","https://openalex.org/W2155502235","https://openalex.org/W2164634022","https://openalex.org/W2167302605","https://openalex.org/W2294518132","https://openalex.org/W2430378630","https://openalex.org/W2462305634","https://openalex.org/W2619410666","https://openalex.org/W2962733107","https://openalex.org/W3177445587","https://openalex.org/W4248428005","https://openalex.org/W4282565958","https://openalex.org/W4323651144","https://openalex.org/W4381328570","https://openalex.org/W6601894380","https://openalex.org/W6643389454"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0,54],"paper":[1],"studies":[2,76],"the":[3,9,30,39,81,94,104,108,116,140,144,157,177,182,189,195,204,231,240,243,256,265],"near-duplicate":[4],"text":[5,34,49,65,89,123,214,260],"alignment":[6,50],"problem":[7,27],"under":[8],"constraint":[10],"of":[11,18,84,103,110,184,191,233,242,264,295],"Jaccard":[12,36],"similarity.":[13],"Specifically,":[14],"given":[15,46],"a":[16,22,45,64,73,122,213,259],"collection":[17],"long":[19,153],"texts":[20],"and":[21,90,113,180,298,301],"short":[23],"query":[24,40,266,299],"text,":[25],"this":[26,71,165],"finds":[28],"all":[29,93,203,255],"subsequences":[31,62,95],"in":[32,63,87,121,131,212,222,258,293],"each":[33,88,192],"whose":[35,96],"similarities":[37],"to":[38,78,101,169,175,253,262],"are":[41,58,99],"no":[42],"smaller":[43],"than":[44],"threshold.":[47],"Near-duplicate":[48],"is":[51,55,139,148,161,198],"computationally":[52],"intensive.":[53],"because":[56],"there":[57],"O(n":[59,117,205,244],"2":[60,118,206,245],")":[61],"with":[66,124,215,273],"n":[67,125,216],"tokens.":[68],"To":[69,163],"remedy":[70],"issue,":[72,166],"few":[74],"recent":[75],"propose":[77,168],"first":[79],"generate":[80,176],"min-hash":[82,97,178],"sketch":[83,141,158,179,193],"every":[85],"subsequence":[86],"then":[91],"find":[92,254],"sketches":[98,257],"similar":[100,261],"that":[102,115,202,263],"query.":[105],"They":[106],"introduce":[107,181],"concept":[109,183],"\"compact":[111],"windows\"":[112],"show":[114,285],"k)":[119,207,246],"min-hashes":[120,208],"tokens":[126,217],"can":[127,218],"be":[128,219],"losslessly":[129,220],"compressed":[130,221],"compact":[132,186,224,235,270],"windows":[133,225,236],"using":[134,226],"O(nk)":[135,147],"space,":[136],"where":[137],"k":[138,160],"size.":[142],"However,":[143],"space":[145],"cost":[146,297],"still":[149],"too":[150],"high":[151],"for":[152],"texts,":[154],"especially":[155],"when":[156],"size":[159,190],"large.":[162],"address":[164],"we":[167,200,249],"use":[170],"One":[171],"Permutation":[172],"Hashing":[173],"(OPH)":[174],"\"OPH":[185],"windows\".":[187],"Although":[188],"remains":[194],"same,":[196],"which":[197],"O(k),":[199],"prove":[201],"generated":[209],"by":[210],"OPH":[211,223,234,269],"only":[227],"O(n+k)":[228],"space.":[229],"Note":[230],"generation":[232],"does":[237],"not":[238],"necessitate":[239],"enumeration":[241],"min-hashes.":[247],"Moreover,":[248],"develop":[250],"an":[251],"algorithm":[252],"directly":[267],"from":[268],"windows,":[271],"along":[272],"three":[274,280],"optimizations.We":[275],"conduct":[276],"extensive":[277],"experiments":[278],"on":[279],"real-world":[281],"datasets.":[282],"Empirical":[283],"results":[284],"our":[286],"proposed":[287],"algorithms":[288],"significantly":[289],"outperformed":[290],"existing":[291],"methods":[292],"terms":[294],"index":[296],"latency":[300],"scaled":[302],"well.":[303]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}