{"id":"https://openalex.org/W4390548040","doi":"https://doi.org/10.1145/3632410.3632414","title":"Semantic Annotation of Relational Schemas Using a Probabilistic Generative Model","display_name":"Semantic Annotation of Relational Schemas Using a Probabilistic Generative Model","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390548040","doi":"https://doi.org/10.1145/3632410.3632414"},"language":"en","primary_location":{"id":"doi:10.1145/3632410.3632414","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","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/A5044893500","display_name":"Debayan Mukherjee","orcid":"https://orcid.org/0009-0007-3078-7587"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Debayan Mukherjee","raw_affiliation_strings":["TCS Research, India"],"raw_orcid":"https://orcid.org/0009-0007-3078-7587","affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026667471","display_name":"Atreya Bandyopadhyay","orcid":"https://orcid.org/0009-0008-5725-1712"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Atreya Bandyopadhyay","raw_affiliation_strings":["TCS Research, India"],"raw_orcid":"https://orcid.org/0009-0008-5725-1712","affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000710398","display_name":"Soham Datta","orcid":"https://orcid.org/0009-0000-7151-8470"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soham Datta","raw_affiliation_strings":["TCS Research, India"],"raw_orcid":"https://orcid.org/0009-0000-7151-8470","affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101727281","display_name":"Indrajit Bhattacharya","orcid":"https://orcid.org/0009-0004-4279-538X"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Indrajit Bhattacharya","raw_affiliation_strings":["TCS Research, India"],"raw_orcid":"https://orcid.org/0009-0004-4279-538X","affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044893500"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00225619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.784088134765625},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6425658464431763},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5641249418258667},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5472065210342407},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5114840269088745},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4745422303676605},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.4615931510925293},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4356107711791992},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43199270963668823},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42966213822364807},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3645060360431671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3547423481941223},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3058199882507324},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2975788116455078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784088134765625},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6425658464431763},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5641249418258667},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5472065210342407},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5114840269088745},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4745422303676605},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4615931510925293},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4356107711791992},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43199270963668823},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42966213822364807},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3645060360431671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3547423481941223},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3058199882507324},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2975788116455078},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3632410.3632414","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632414","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W92812941","https://openalex.org/W2067292826","https://openalex.org/W2092364718","https://openalex.org/W2110686900","https://openalex.org/W2111869785","https://openalex.org/W2122678284","https://openalex.org/W2150365753","https://openalex.org/W2178725228","https://openalex.org/W2233823309","https://openalex.org/W2406114359","https://openalex.org/W2521543926","https://openalex.org/W2898796029","https://openalex.org/W2904530076","https://openalex.org/W2913854033","https://openalex.org/W3035231859","https://openalex.org/W3042602466","https://openalex.org/W3045464143","https://openalex.org/W3105538385","https://openalex.org/W3155695283","https://openalex.org/W4385567171","https://openalex.org/W4389520779"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495","https://openalex.org/W4387506531"],"abstract_inverted_index":{"Data":[0],"in":[1,95,130,155],"enterprises":[2],"resides":[3],"largely":[4],"under":[5],"relational":[6,71,128],"schemas.":[7],"Annotating":[8],"such":[9,113],"schemas":[10,72],"with":[11,88,119,127],"a":[12,65,96,148],"knowledge":[13,18,97,153],"graph":[14],"(KG)":[15],"that":[16,68,160],"represents":[17],"of":[19,27,76],"the":[20,28,122,131,161],"domain":[21,152],"is":[22],"useful":[23],"for":[24],"semantic":[25],"understanding":[26],"data":[29],"as":[30,32,114],"well":[31],"downstream":[33],"processing":[34],"by":[35,91],"machines":[36],"and":[37,47,50,59,85,117,121,151],"humans.":[38],"Existing":[39],"approaches":[40,167],"annotate":[41],"only":[42],"individual":[43],"tables":[44,77,84,89,116],"using":[45,145],"small":[46],"simple":[48],"KGs,":[49],"also":[51,135],"fail":[52],"to":[53,55,137,157],"generalize":[54],"unseen":[56,138],"KG":[57],"entities":[58],"relationships":[60],"during":[61],"test.":[62],"We":[63,143],"propose":[64],"probabilistic":[66],"model":[67,108],"generates":[69],"complex":[70],"\u2014":[73,90],"tables,":[74],"grouping":[75],"into":[78],"neighborhoods,":[79],"foreign":[80],"key":[81],"connections":[82],"between":[83,124],"fields":[86],"associated":[87],"traversing":[92],"over":[93],"paths":[94,129,139],"graph.":[98],"An":[99],"efficient":[100],"two-pass":[101],"inference":[102],"algorithm":[103,134],"based":[104],"on":[105,147],"inverting":[106],"this":[107],"jointly":[109],"annotates":[110],"schema":[111,125,150],"elements":[112,126],"fields,":[115],"neighborhoods":[118],"entities,":[120],"associations":[123],"KG.":[132],"The":[133],"generalizes":[136],"at":[140],"test":[141],"time.":[142],"show":[144],"experiments":[146],"real-world":[149],"graph,":[154],"addition":[156],"benchmark":[158],"datasets,":[159],"proposed":[162],"approach":[163],"significantly":[164],"out-performs":[165],"existing":[166],"while":[168],"demonstrating":[169],"better":[170],"scalability.":[171]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}