{"id":"https://openalex.org/W2151234409","doi":"https://doi.org/10.1145/1989323.1989378","title":"Hybrid in-database inference for declarative information extraction","display_name":"Hybrid in-database inference for declarative information extraction","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2151234409","doi":"https://doi.org/10.1145/1989323.1989378","mag":"2151234409"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989378","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD 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/A5003464266","display_name":"Daisy Zhe Wang","orcid":"https://orcid.org/0009-0003-8234-5482"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daisy Zhe Wang","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019638","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0003-3332-8574"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Franklin","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023079617","display_name":"Minos Garofalakis","orcid":"https://orcid.org/0000-0003-0285-3907"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Minos Garofalakis","raw_affiliation_strings":["Technical University of Crete, Chania, Greece"],"affiliations":[{"raw_affiliation_string":"Technical University of Crete, Chania, Greece","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043626252","display_name":"Joseph M. Hellerstein","orcid":"https://orcid.org/0000-0002-7712-4306"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph M. Hellerstein","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058514754","display_name":"Michael Wick","orcid":null},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Wick","raw_affiliation_strings":["University of Massachusetts, Amherst, Amherst, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, Amherst, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003464266"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":6.4308,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.97398363,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"517","last_page":"528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994999766349792,"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":0.9994999766349792,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9959999918937683,"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":0.8486993312835693},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6095976829528809},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5433562397956848},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5283699035644531},{"id":"https://openalex.org/keywords/probabilistic-database","display_name":"Probabilistic database","score":0.4777328670024872},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46209755539894104},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4016300439834595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39333927631378174},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3253380060195923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3066850006580353},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.25332164764404297},{"id":"https://openalex.org/keywords/database-model","display_name":"Database model","score":0.2382771074771881}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486993312835693},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6095976829528809},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5433562397956848},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5283699035644531},{"id":"https://openalex.org/C174539288","wikidata":"https://www.wikidata.org/wiki/Q7246853","display_name":"Probabilistic database","level":4,"score":0.4777328670024872},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46209755539894104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4016300439834595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39333927631378174},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3253380060195923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3066850006580353},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.25332164764404297},{"id":"https://openalex.org/C5968703","wikidata":"https://www.wikidata.org/wiki/Q267136","display_name":"Database model","level":3,"score":0.2382771074771881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1989323.1989378","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316505","display_name":"NetApp","ror":"https://ror.org/05c4cm338"},{"id":"https://openalex.org/F4320316785","display_name":"VMware","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1488272912","https://openalex.org/W1511986666","https://openalex.org/W1599188306","https://openalex.org/W1766290689","https://openalex.org/W1962705364","https://openalex.org/W2022760666","https://openalex.org/W2035266017","https://openalex.org/W2078686663","https://openalex.org/W2092819480","https://openalex.org/W2109377779","https://openalex.org/W2110138423","https://openalex.org/W2114157818","https://openalex.org/W2114760689","https://openalex.org/W2116832440","https://openalex.org/W2120825705","https://openalex.org/W2134414349","https://openalex.org/W2142384583","https://openalex.org/W2143485006","https://openalex.org/W2144416276","https://openalex.org/W2144810465","https://openalex.org/W2147880316","https://openalex.org/W2156454791","https://openalex.org/W2163844356","https://openalex.org/W2166855749","https://openalex.org/W2166916904","https://openalex.org/W2170694982","https://openalex.org/W4248846162","https://openalex.org/W4388892785"],"related_works":["https://openalex.org/W1774414873","https://openalex.org/W2000084727","https://openalex.org/W2744606804","https://openalex.org/W2739264497","https://openalex.org/W2103934874","https://openalex.org/W2125434953","https://openalex.org/W2749065928","https://openalex.org/W4238495367","https://openalex.org/W2128160835","https://openalex.org/W4288558710"],"abstract_inverted_index":{"In":[0,87],"the":[1,24,29,65,70,92,112,115,120,129,131,134,137,154,184,189],"database":[2,42],"community,":[3],"work":[4,37],"on":[5,11,128,144],"information":[6],"extraction":[7],"(IE)":[8],"has":[9,38],"centered":[10],"two":[12,106],"themes:":[13],"how":[14,21],"to":[15,22,60,103,152,162,179,183],"effectively":[16,74],"manage":[17,23],"IE":[18,30,46,53,67,83,160],"tasks,":[19],"and":[20,55,114,133,141],"uncertainties":[25],"that":[26,48,173],"arise":[27],"in":[28,32,188],"process":[31],"a":[33,40,50,80,96,149,157],"scalable":[34],"manner.":[35],"Recent":[36],"proposed":[39,187],"probabilistic":[41,66,77,159],"(PDB)":[43],"based":[44,127],"declarative":[45,82],"system":[47,84],"supports":[49],"leading":[51],"statistical":[52],"model,":[54,130],"an":[56],"associated":[57],"inference":[58,78,100,125,165],"algorithm":[59],"answer":[61],"top-k-style":[62],"queries":[63],"over":[64],"outcome.":[68],"Still,":[69],"broader":[71],"problem":[72],"of":[73,95,99,156],"supporting":[75],"general":[76],"inside":[79],"PDB-based":[81],"remains":[85],"open.":[86],"this":[88],"paper,":[89],"we":[90,147],"explore":[91],"in-database":[93],"implementations":[94],"wide":[97],"variety":[98],"algorithms":[101,126,166],"suited":[102],"IE,":[104],"including":[105],"Markov":[107],"chain":[108],"Monte":[109],"Carlo":[110],"algorithms,":[111],"Viterbi":[113],"sum-product":[116],"algorithms.":[117],"We":[118,171],"describe":[119,148],"rules":[121],"for":[122,168],"choosing":[123],"appropriate":[124,167],"query":[132,161],"text,":[135],"considering":[136],"trade-off":[138],"between":[139],"accuracy":[140],"runtime.":[142],"Based":[143],"these":[145],"rules,":[146],"hybrid":[150],"approach":[151],"optimize":[153],"execution":[155],"single":[158],"employ":[163],"different":[164,169],"records.":[170],"show":[172],"our":[174],"techniques":[175],"can":[176],"achieve":[177],"up":[178],"10-fold":[180],"speedups":[181],"compared":[182],"non-hybrid":[185],"solutions":[186],"literature.":[190]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}