{"id":"https://openalex.org/W6887884796","doi":"https://doi.org/10.18420/btw2025-130","title":"Towards Complex Table Question Answering Over Tabular Data Lakes","display_name":"Towards Complex Table Question Answering Over Tabular Data Lakes","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W6887884796","doi":"https://doi.org/10.18420/btw2025-130"},"language":"en","primary_location":{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:159397","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Risis=3ADaniela=3A=3A.html>","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":null,"raw_type":"NonPeerReviewed"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/btw2025-130","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Risis, Daniela","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Risis, Daniela","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":"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":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1935,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91535872,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"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/T11719","display_name":"Data Quality and Management","score":0.5651999711990356,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.5651999711990356,"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/T10028","display_name":"Topic Modeling","score":0.09920000284910202,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.06499999761581421,"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/table","display_name":"Table (database)","score":0.7465000152587891},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6998000144958496},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5710999965667725},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46639999747276306},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44760000705718994},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4278999865055084},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4059999883174896},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8083000183105469},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7465000152587891},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6998000144958496},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5710999965667725},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.51419997215271},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41350001096725464},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:159397","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Risis=3ADaniela=3A=3A.html>","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":null,"raw_type":"NonPeerReviewed"},{"id":"doi:10.18420/btw2025-130","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2025-130","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/btw2025-130","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2025-130","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Natural":[0],"Language":[1,79],"Interfaces":[2],"for":[3,114],"Databases":[4],"(NLIDBs)":[5],"are":[6,85,168],"an":[7,98],"interesting":[8],"alternative":[9],"to":[10,16,25,63,97,100,149,188],"SQL":[11],"since":[12,51],"they":[13,167],"empower":[14],"non-experts":[15],"query":[17],"data.":[18],"However,":[19],"NLIDB":[20,176],"approaches":[21,72,177],"require":[22],"this":[23,106,143],"data":[24,37,57,59,90,128,195],"first":[26,86,111],"be":[27],"integrated":[28],"into":[29,66],"a":[30,67,89,131],"database":[31],"schema,":[32],"which":[33],"causes":[34],"high":[35],"upfront":[36],"engineering":[38],"and":[39,92],"integration":[40],"overheads.":[41],"As":[42,130],"such,":[43],"Open":[44],"Table":[45],"Question":[46],"Answering":[47],"(OTQA)":[48],"is":[49],"promising,":[50],"it":[52,65],"allows":[53],"directly":[54],"querying":[55,173],"the":[56,102,110,155,171],"in":[58],"lakes":[60],"without":[61],"needing":[62],"incorporate":[64],"schema.":[68],"Many":[69],"recent":[70],"OTQA":[71],"combine":[73],"Retrieval-Augmented":[74],"Generation":[75],"(RAG)":[76],"with":[77,119],"Large":[78],"Models":[80],"(LLMs),":[81],"where":[82],"relevant":[83],"tables":[84],"retrieved":[87],"from":[88,170],"lake":[91],"then":[93],"used":[94],"as":[95],"input":[96],"LLM":[99],"answer":[101,123,150],"user":[103],"query.":[104],"In":[105],"paper,":[107],"we":[108,134,183],"take":[109],"systematic":[112],"step":[113],"investigating":[115],"how":[116],"LLMs":[117,146],"paired":[118],"table":[120],"retrievers":[121],"can":[122],"queries":[124,151],"over":[125,193],"private":[126],"tabular":[127,194],"lakes.":[129,196],"main":[132],"finding,":[133],"see":[135],"that":[136,152,175],"even":[137],"when":[138],"tuning":[139],"several":[140],"parameters":[141],"of":[142,158],"approach,":[144],"current":[145],"still":[147],"fail":[148],"focus":[153],"on":[154],"simple":[156],"extraction":[157],"individual":[159],"cell":[160],"values,":[161],"let":[162],"alone":[163],"aggregate":[164],"queries.":[165],"Thus,":[166],"far":[169],"rich":[172],"capabilities":[174],"offer":[178],"today.":[179],"To":[180],"solve":[181],"this,":[182],"recommend":[184],"promising":[185],"future":[186],"work":[187],"enable":[189],"complex":[190],"question":[191],"answering":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}