{"id":"https://openalex.org/W2425458534","doi":"https://doi.org/10.1145/2882903.2914838","title":"Searching Web Data using MinHash LSH","display_name":"Searching Web Data using MinHash LSH","publication_year":2016,"publication_date":"2016-06-16","ids":{"openalex":"https://openalex.org/W2425458534","doi":"https://doi.org/10.1145/2882903.2914838","mag":"2425458534"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2914838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2914838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","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/A5055784957","display_name":"B. Shanmukha Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"BiChen Rao","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013934423","display_name":"Erkang Zhu","orcid":"https://orcid.org/0009-0000-3326-1790"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Erkang Zhu","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6761,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76826619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2257","last_page":"2258"},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9911999702453613,"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":0.9850000143051147,"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/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.8361871838569641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5992833971977234},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4227992594242096},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.42010512948036194},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3906145393848419},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.2689056396484375},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25402018427848816},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.12171736359596252},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.05538180470466614}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.8361871838569641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5992833971977234},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4227992594242096},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.42010512948036194},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3906145393848419},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.2689056396484375},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25402018427848816},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.12171736359596252},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.05538180470466614}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2882903.2914838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2914838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2012833704","https://openalex.org/W2055839530","https://openalex.org/W2132069633","https://openalex.org/W2147717514","https://openalex.org/W2148781362","https://openalex.org/W2341748398","https://openalex.org/W2963174348","https://openalex.org/W6679663036","https://openalex.org/W6681272064"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W2054476758","https://openalex.org/W1976265003","https://openalex.org/W2393322642","https://openalex.org/W2393932274","https://openalex.org/W2188505374","https://openalex.org/W1558342070"],"abstract_inverted_index":{"In":[0,45],"this":[1],"extended":[2],"abstract,":[3],"we":[4,47],"explore":[5],"the":[6,17,37,53],"use":[7],"of":[8,19,31],"MinHash":[9,32],"Locality":[10],"Sensitive":[11],"Hashing":[12],"(MinHash":[13],"LSH)":[14],"to":[15],"address":[16],"problem":[18],"indexing":[20],"and":[21,34,39],"searching":[22],"Web":[23,57],"data.":[24,58],"We":[25],"discuss":[26],"a":[27],"statistical":[28],"tuning":[29],"strategy":[30],"LSH,":[33],"experimentally":[35],"evaluate":[36],"accuracy":[38],"performance,":[40],"compared":[41],"with":[42,55],"inverted":[43],"index.":[44],"addition,":[46],"describe":[48],"an":[49],"on-line":[50],"demo":[51],"for":[52],"index":[54],"real":[56]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
