{"id":"https://openalex.org/W6906508079","doi":"https://doi.org/10.18420/btw2023-08","title":"WannaDB: Ad-hoc SQL Queries over Text Collections","display_name":"WannaDB: Ad-hoc SQL Queries over Text Collections","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6906508079","doi":"https://doi.org/10.18420/btw2023-08"},"language":"en","primary_location":{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:138777","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/btw2023-08","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"H\u00e4ttasch, Benjamin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"H\u00e4ttasch, Benjamin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bodensohn, Jan-Micha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bodensohn, Jan-Micha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Vogel, Liane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vogel, Liane","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Urban, Matthias","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Urban, Matthias","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Binnig, Carsten","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binnig, Carsten","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8327,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.89467782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.5321000218391418,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.5321000218391418,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.21199999749660492,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.05849999934434891,"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/table","display_name":"Table (database)","score":0.6227999925613403},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5900999903678894},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.48969998955726624},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.39149999618530273},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.322299987077713},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3086000084877014}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8650000095367432},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6227999925613403},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5900999903678894},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5662000179290771},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:138777","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"},{"id":"doi:10.18420/btw2023-08","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2023-08","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/btw2023-08","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2023-08","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6727326512336731,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"n":[0],"this":[1],"paper,":[2],"we":[3,126],"propose":[4],"a":[5,31,35,81,86,111,138],"new":[6,82],"system":[7],"called":[8],"WannaDB":[9,66,129],"that":[10,128],"allows":[11],"users":[12],"to":[13,52,68,72,110,133,151],"interactively":[14,108],"perform":[15],"structured":[16,26,60,112,135],"explorations":[17],"of":[18,37,57,65,88,141],"text":[19,29,78,143],"collections":[20,79,144],"in":[21,49,145],"an":[22],"ad-hoc":[23,55,74],"manner.":[24],"Extracting":[25],"data":[27,136],"from":[28,91,137],"is":[30,67,94,130],"classical":[32],"problem":[33],"where":[34],"plenitude":[36],"approaches":[38,47],"and":[39],"even":[40],"industry-scale":[41],"systems":[42],"already":[43],"exists.":[44],"However,":[45],"these":[46],"lack":[48],"the":[50,54,92,105,118,149],"ability":[51],"support":[53,73],"exploration":[56],"texts":[58,93],"using":[59,80,96],"queries.":[61],"The":[62],"main":[63],"idea":[64],"include":[69],"user":[70,119],"interaction":[71],"SQL":[75],"queries":[76],"over":[77],"two-phased":[83],"approach.":[84],"First,":[85],"superset":[87],"information":[89],"nuggets":[90],"extracted":[95],"existing":[97],"extractors":[98],"such":[99],"as":[100,115],"named":[101],"entity":[102],"recognizers.":[103],"Then,":[104],"extractions":[106],"are":[107],"matched":[109],"table":[113],"definition":[114],"requested":[116],"by":[117],"based":[120],"on":[121],"embeddings.":[122],"In":[123],"our":[124],"evaluation,":[125],"show":[127],"thus":[131],"able":[132],"extract":[134],"broad":[139],"range":[140],"(real-world)":[142],"high":[146],"quality":[147],"without":[148],"need":[150],"design":[152],"extraction":[153],"pipelines":[154],"upfront.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}
