{"id":"https://openalex.org/W4281739679","doi":"https://doi.org/10.1145/3514221.3517897","title":"TASTI: Semantic Indexes for Machine Learning-based Queries over Unstructured Data","display_name":"TASTI: Semantic Indexes for Machine Learning-based Queries over Unstructured Data","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281739679","doi":"https://doi.org/10.1145/3514221.3517897"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517897","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517897","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 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/A5072348548","display_name":"Daniel Kang","orcid":"https://orcid.org/0000-0001-9860-9938"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Kang","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030319720","display_name":"John Guibas","orcid":"https://orcid.org/0009-0004-8237-2154"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Guibas","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002538469","display_name":"Peter Bailis","orcid":"https://orcid.org/0000-0003-1166-7823"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter D. Bailis","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015518638","display_name":"Tatsunori Hashimoto","orcid":"https://orcid.org/0000-0003-0521-5855"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tatsunori Hashimoto","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072348548"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.4516,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91690363,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1934","last_page":"1947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9850999712944031,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9000997543334961},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.6252419352531433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4701179265975952},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4315067529678345},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41827428340911865},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41443198919296265},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41193562746047974},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.344970166683197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9000997543334961},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.6252419352531433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4701179265975952},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4315067529678345},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41827428340911865},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41443198919296265},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41193562746047974},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.344970166683197}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514221.3517897","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517897","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 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":26,"referenced_works":["https://openalex.org/W204268067","https://openalex.org/W1499049447","https://openalex.org/W1566022212","https://openalex.org/W1913628733","https://openalex.org/W1994655805","https://openalex.org/W2045964207","https://openalex.org/W2106053110","https://openalex.org/W2118269922","https://openalex.org/W2144679084","https://openalex.org/W2161694911","https://openalex.org/W2493916176","https://openalex.org/W2752236330","https://openalex.org/W2786278116","https://openalex.org/W2887117815","https://openalex.org/W2903557836","https://openalex.org/W2912374867","https://openalex.org/W2912981821","https://openalex.org/W2998752879","https://openalex.org/W3000318171","https://openalex.org/W3028942915","https://openalex.org/W3086715908","https://openalex.org/W3094550259","https://openalex.org/W3103272053","https://openalex.org/W3147178137","https://openalex.org/W6633872374","https://openalex.org/W6633912359"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2028495302","https://openalex.org/W2037549926","https://openalex.org/W4396872084","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W4249498729","https://openalex.org/W2849310602","https://openalex.org/W2002261065","https://openalex.org/W3006008237"],"abstract_inverted_index":{"Unstructured":[0],"data":[1],"(e.g.,":[2,37,180],"video":[3],"or":[4,17,59],"text)":[5],"is":[6,115],"now":[7],"commonly":[8],"queried":[9],"by":[10,126,243],"using":[11],"computationally":[12],"expensive":[13,56,230],"deep":[14],"neural":[15,57],"networks":[16,58],"human":[18,60],"labelers":[19,53],"to":[20,48,80,118,164,231,245],"produce":[21],"structured":[22],"information,":[23],"e.g.,":[24],"object":[25],"types":[26],"and":[27,85,114,189,214,217,240],"positions":[28],"in":[29,71,132,174],"video.":[30],"To":[31],"accelerate":[32,241],"queries,":[33],"many":[34],"recent":[35],"systems":[36],"BlazeIt,":[38],"NoScope,":[39],"Tahoma,":[40],"SUPG,":[41],"etc.)":[42],"train":[43,165],"a":[44,50,133,166,192,202],"query-specific":[45],"proxy":[46,65,76,158],"model":[47],"approximate":[49],"large":[51,87],"target":[52,93,151],"(i.e.,":[54],"these":[55],"labelers).":[61],"These":[62,169],"models":[63,77],"return":[64],"scores":[66,159,170],"that":[67,106,144,191,223],"are":[68],"then":[69,155],"used":[70,173],"query":[72,84,177,199,219],"processing":[73,178],"algorithms.":[74],"Unfortunately,":[75],"usually":[78],"have":[79,149],"be":[81,172,227],"trained":[82],"per":[83],"require":[86],"amounts":[88],"of":[89,205],"annotations":[90,235],"from":[91],"the":[92,109],"labelers.":[94],"In":[95],"this":[96,125],"work,":[97],"we":[98],"develop":[99],"an":[100],"index":[101],"(trainable":[102],"semantic":[103,128],"index,":[104],"TASTI)":[105],"simultaneously":[107],"removes":[108],"need":[110],"for":[111,140,181,201,236],"per-query":[112,167],"proxies":[113],"more":[116],"efficient":[117],"construct":[119,232],"than":[120,233],"prior":[121],"indexes.":[122],"TASTI":[123,154,188,209],"accomplishes":[124],"leveraging":[127],"similarity":[129],"across":[130],"records":[131,145],"given":[134],"dataset.":[135],"Specifically,":[136],"it":[137],"produces":[138],"embeddings":[139,148,161],"each":[141],"record":[142],"such":[143],"with":[146],"close":[147],"similar":[150],"labeler":[152],"outputs.":[153],"generates":[156],"high-quality":[157],"via":[160],"without":[162],"needing":[163],"proxy.":[168],"can":[171,226],"existing":[175],"proxy-based":[176,238],"algorithms":[179],"aggregation,":[182],"selection,":[183],"etc.).":[184],"We":[185,207,221],"theoretically":[186],"analyze":[187],"show":[190,222],"low":[193],"embedding":[194],"training":[195],"error":[196],"guarantees":[197],"downstream":[198],"accuracy":[200],"natural":[203],"class":[204],"queries.":[206],"evaluate":[208],"on":[210],"five":[211],"video,":[212],"text,":[213],"speech":[215],"datasets,":[216],"three":[218],"types.":[220],"TASTI's":[224],"indexes":[225],"10x":[228],"less":[229],"generating":[234],"current":[237],"methods,":[239],"queries":[242],"up":[244],"24x.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}