{"id":"https://openalex.org/W4416019959","doi":"https://doi.org/10.1561/1900000087","title":"Analytical Queries for Unstructured Data","display_name":"Analytical Queries for Unstructured Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416019959","doi":"https://doi.org/10.1561/1900000087"},"language":"en","primary_location":{"id":"doi:10.1561/1900000087","is_oa":false,"landing_page_url":"https://doi.org/10.1561/1900000087","pdf_url":null,"source":{"id":"https://openalex.org/S139685423","display_name":"Foundations and Trends in Databases","issn_l":"1931-7883","issn":["1931-7883","1931-7891"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Databases","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.03489","any_repository_has_fulltext":true},"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/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Kang","raw_affiliation_strings":["University of Illinois Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5072348548"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18370361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"2","first_page":"115","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.534500002861023,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.534500002861023,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.15199999511241913,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.046300001442432404,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/bespoke","display_name":"Bespoke","score":0.8967999815940857},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.7371000051498413},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5899999737739563},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5216000080108643},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.37770000100135803},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3224000036716461}],"concepts":[{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.8967999815940857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8705999851226807},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.7371000051498413},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5216000080108643},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4456999897956848},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.382999986410141},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1561/1900000087","is_oa":false,"landing_page_url":"https://doi.org/10.1561/1900000087","pdf_url":null,"source":{"id":"https://openalex.org/S139685423","display_name":"Foundations and Trends in Databases","issn_l":"1931-7883","issn":["1931-7883","1931-7891"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Databases","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2511.03489","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.03489","pdf_url":"https://arxiv.org/pdf/2511.03489","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.03489","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.03489","pdf_url":"https://arxiv.org/pdf/2511.03489","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416019959.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unstructured":[0],"data,":[1,97],"in":[2,38,42,76,102,113,197,251],"the":[3,68,85,156,184,198],"form":[4,157],"of":[5,87,96,155,160,170,207,245],"text,":[6],"images,":[7,39],"video,":[8],"and":[9,44,63,98,111,183,223,261],"audio,":[10],"is":[11,147],"produced":[12],"at":[13,27],"exponentially":[14],"higher":[15],"rates.":[16],"In":[17,105],"tandem,":[18],"machine":[19],"learning":[20],"(ML)":[21],"methods":[22,33,185,241],"have":[23],"become":[24],"increasingly":[25,59],"powerful":[26],"analyzing":[28],"unstructured":[29,118],"data.":[30,179],"Modern":[31],"ML":[32,88,103,130,165,181,190,252],"can":[34,143,167,192,211],"now":[35,212],"detect":[36],"objects":[37],"understand":[40,67],"actions":[41],"videos,":[43],"even":[45,137,224],"classify":[46],"complex":[47],"legal":[48,52],"texts":[49],"based":[50],"on":[51,126,234,258],"intent.":[53],"Combined,":[54],"these":[55,78,208],"trends":[56],"make":[57],"it":[58,146],"feasible":[60],"for":[61,117],"analysts":[62],"researchers":[64],"to":[65,131,151,175,186,204,248,264],"automatically":[66],"\"real":[69],"world.\"":[70],"However,":[71],"there":[72],"are":[73],"major":[74],"challenges":[75,110],"deploying":[77],"techniques:":[79],"1)":[80],"executing":[81],"queries":[82,92,133,142,214,236],"efficiently":[83],"given":[84],"expense":[86],"methods,":[89],"2)":[90],"expressing":[91],"over":[93],"bespoke":[94],"forms":[95],"3)":[99],"handling":[100],"errors":[101,250],"methods.":[104],"this":[106],"monograph,":[107],"we":[108],"discuss":[109],"advances":[112],"data":[114,119,199,265],"management":[115,200],"systems":[116],"using":[120],"ML,":[121],"with":[122,189,242,267],"a":[123,153,229],"particular":[124],"focus":[125],"video":[127],"analytics.":[128],"Using":[129],"answer":[132],"introduces":[134],"new":[135],"challenges.First,":[136],"turning":[138,162],"user":[139],"intent":[140],"into":[141],"be":[144,168,193],"challenging:":[145],"not":[148],"obvious":[149],"how":[150],"express":[152,213],"query":[154],"\"select":[158],"instances":[159],"cars":[161],"left.\"":[163],"Second,":[164],"models":[166,182,191],"orders":[169],"magnitude":[171],"more":[172],"expensive":[173,239],"compared":[174],"processing":[176],"traditional":[177],"structured":[178,221],"Third,":[180],"accelerate":[187],"analytics":[188,266],"error-prone.":[194],"Recent":[195],"work":[196,232,255],"community":[201],"has":[202,256],"aimed":[203],"address":[205],"all":[206],"challenges.":[209],"Users":[210],"via":[215],"user-defined":[216],"functions,":[217],"opaquely":[218],"through":[219],"standard":[220],"schemas,":[222],"by":[225,237],"providing":[226],"examples.":[227],"Given":[228],"query,":[230],"recent":[231,254],"focuses":[233],"optimizing":[235],"approximating":[238],"\"gold\"":[240],"varying":[243],"levels":[244],"guarantees.":[246],"Finally,":[247],"handle":[249],"models,":[253],"focused":[257],"applying":[259],"outlier":[260],"drift":[262],"detection":[263],"ML.":[268]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-28T00:00:00"}