{"id":"https://openalex.org/W7162407310","doi":"https://doi.org/10.1145/3788853.3801605","title":"Intent-aware Join Discovery using Natural Language","display_name":"Intent-aware Join Discovery using Natural Language","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162407310","doi":"https://doi.org/10.1145/3788853.3801605"},"language":null,"primary_location":{"id":"doi:10.1145/3788853.3801605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788853.3801605","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3788853.3801605","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058592820","display_name":"Mir Mahathir Mohammad","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mir Mahathir Mohammad","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA"],"raw_orcid":"https://orcid.org/0009-0005-9314-7793","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004937696","display_name":"El Kindi Rezig","orcid":"https://orcid.org/0000-0002-5187-3499"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"El Kindi Rezig","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA"],"raw_orcid":"https://orcid.org/0000-0002-5187-3499","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86237406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"106","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.06350000202655792,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.06350000202655792,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.05990000069141388,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.05730000138282776,"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/join","display_name":"Join (topology)","score":0.8215000033378601},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.582099974155426},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5085999965667725},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.36230000853538513},{"id":"https://openalex.org/keywords/natural-language-user-interface","display_name":"Natural language user interface","score":0.31540000438690186},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.30809998512268066},{"id":"https://openalex.org/keywords/data-manipulation-language","display_name":"Data manipulation language","score":0.2928999960422516}],"concepts":[{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.8215000033378601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777000069618225},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.582099974155426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4377000033855438},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32510000467300415},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3068000078201294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2522999942302704},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788853.3801605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788853.3801605","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3788853.3801605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788853.3801605","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2890431379","https://openalex.org/W2963469388","https://openalex.org/W3197661828","https://openalex.org/W4385653220","https://openalex.org/W4399208200","https://openalex.org/W4402043038","https://openalex.org/W7151331477"],"related_works":[],"abstract_inverted_index":{"We":[0,70],"present":[1],"NLDisc,":[2],"a":[3],"system":[4],"for":[5,36],"intent-aware":[6],"join":[7,34,52],"discovery":[8,20,64],"over":[9],"data":[10,19,63,77],"lakes":[11],"using":[12],"natural":[13,48],"language":[14],"(NL)":[15],"queries.":[16],"Unlike":[17],"existing":[18],"systems":[21],"that":[22],"rely":[23],"on":[24],"structured":[25],"inputs":[26],"(e.g.,":[27],"example":[28],"tables)":[29],"or":[30],"fail":[31],"to":[32,42],"support":[33],"operations":[35],"NL":[37],"queries,":[38],"NLDisc":[39,57],"enables":[40],"users":[41],"describe":[43],"their":[44],"desired":[45],"datasets":[46],"in":[47,61],"language\u2014automatically":[49],"discovering":[50],"relevant":[51],"paths":[53],"across":[54,74],"multiple":[55],"tables,":[56],"addresses":[58],"key":[59],"challenges":[60],"NL-based":[62],"by":[65],"supporting":[66],"interactive":[67],"intent":[68],"disambiguation.":[69],"demonstrate":[71],"NLDisc's":[72],"capabilities":[73],"diverse":[75],"real-world":[76],"lakes,":[78],"including":[79],"benchmarks":[80],"and":[81],"public":[82],"datasets.":[83]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-27T00:00:00"}
