{"id":"https://openalex.org/W4385607102","doi":"https://doi.org/10.1145/3612919","title":"DomainNet: Homograph Detection and Understanding in Data Lake Disambiguation","display_name":"DomainNet: Homograph Detection and Understanding in Data Lake Disambiguation","publication_year":2023,"publication_date":"2023-08-05","ids":{"openalex":"https://openalex.org/W4385607102","doi":"https://doi.org/10.1145/3612919"},"language":"en","primary_location":{"id":"doi:10.1145/3612919","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3612919","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3612919","source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3612919","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061214307","display_name":"Aristotelis Leventidis","orcid":"https://orcid.org/0000-0002-7229-3936"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aristotelis Leventidis","raw_affiliation_strings":["Northeastern University, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086097686","display_name":"Laura Rocco","orcid":"https://orcid.org/0000-0002-8134-909X"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Di Rocco","raw_affiliation_strings":["Northeastern University, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086781628","display_name":"Wolfgang Gatterbauer","orcid":"https://orcid.org/0000-0002-9614-0504"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wolfgang Gatterbauer","raw_affiliation_strings":["Northeastern University, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022619313","display_name":"Ren\u00e9e J. Miller","orcid":"https://orcid.org/0000-0002-1484-4787"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ren\u00e9e J. Miller","raw_affiliation_strings":["Northeastern University, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049802784","display_name":"Mirek Riedewald","orcid":"https://orcid.org/0000-0002-6102-7472"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mirek Riedewald","raw_affiliation_strings":["Northeastern University, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061214307"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":0.7487,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74478886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"48","issue":"3","first_page":"1","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9975000023841858,"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/T10028","display_name":"Topic Modeling","score":0.9930999875068665,"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":0.8584246039390564},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.5684342980384827},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5568456053733826},{"id":"https://openalex.org/keywords/centrality","display_name":"Centrality","score":0.4674343168735504},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43968626856803894},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4276485741138458},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4197682738304138},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37250566482543945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3561505079269409},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3436296880245209},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3386807143688202},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1288222074508667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8584246039390564},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.5684342980384827},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5568456053733826},{"id":"https://openalex.org/C53811970","wikidata":"https://www.wikidata.org/wiki/Q5062194","display_name":"Centrality","level":2,"score":0.4674343168735504},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43968626856803894},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4276485741138458},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4197682738304138},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37250566482543945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3561505079269409},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3436296880245209},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3386807143688202},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1288222074508667},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3612919","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3612919","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3612919","source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3612919","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3612919","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3612919","source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1537211332","display_name":null,"funder_award_id":"IIS-1956096","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2699994585","display_name":"CAREER: Scaling Approximate Inference and Approximation-Aware Learning","funder_award_id":"1762268","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5213409069","display_name":null,"funder_award_id":"CAREER IIS-1762268","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6745713617","display_name":null,"funder_award_id":"1956096","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385607102.pdf","grobid_xml":"https://content.openalex.org/works/W4385607102.grobid-xml"},"referenced_works_count":102,"referenced_works":["https://openalex.org/W167809298","https://openalex.org/W632432350","https://openalex.org/W1029409534","https://openalex.org/W1527104720","https://openalex.org/W1552847225","https://openalex.org/W1568436970","https://openalex.org/W1736023725","https://openalex.org/W1866371236","https://openalex.org/W1970709149","https://openalex.org/W1971937094","https://openalex.org/W2004647285","https://openalex.org/W2022166150","https://openalex.org/W2026499502","https://openalex.org/W2032299694","https://openalex.org/W2033062623","https://openalex.org/W2033403400","https://openalex.org/W2035168844","https://openalex.org/W2041439319","https://openalex.org/W2079694211","https://openalex.org/W2091117392","https://openalex.org/W2094728533","https://openalex.org/W2108341980","https://openalex.org/W2111869785","https://openalex.org/W2112090702","https://openalex.org/W2124996875","https://openalex.org/W2129558264","https://openalex.org/W2132052677","https://openalex.org/W2133919533","https://openalex.org/W2139694940","https://openalex.org/W2148019918","https://openalex.org/W2158138755","https://openalex.org/W2158911502","https://openalex.org/W2171707538","https://openalex.org/W2243052854","https://openalex.org/W2321588627","https://openalex.org/W2340354588","https://openalex.org/W2341748398","https://openalex.org/W2374597300","https://openalex.org/W2396200542","https://openalex.org/W2397276128","https://openalex.org/W2399361902","https://openalex.org/W2418808916","https://openalex.org/W2436001372","https://openalex.org/W2460941847","https://openalex.org/W2488700629","https://openalex.org/W2518202280","https://openalex.org/W2535168187","https://openalex.org/W2584356431","https://openalex.org/W2613361247","https://openalex.org/W2751448157","https://openalex.org/W2793868694","https://openalex.org/W2798664493","https://openalex.org/W2805674303","https://openalex.org/W2885934259","https://openalex.org/W2889003264","https://openalex.org/W2889722819","https://openalex.org/W2890431379","https://openalex.org/W2897979119","https://openalex.org/W2904530076","https://openalex.org/W2922435284","https://openalex.org/W2941366772","https://openalex.org/W2948163032","https://openalex.org/W2950067395","https://openalex.org/W2950813464","https://openalex.org/W2951621897","https://openalex.org/W2962936633","https://openalex.org/W2963174348","https://openalex.org/W2963341956","https://openalex.org/W2963455014","https://openalex.org/W2963794747","https://openalex.org/W2964273740","https://openalex.org/W2965373594","https://openalex.org/W2966321063","https://openalex.org/W2970597249","https://openalex.org/W2970992672","https://openalex.org/W2971681342","https://openalex.org/W2978017171","https://openalex.org/W3010534546","https://openalex.org/W3013008430","https://openalex.org/W3014705052","https://openalex.org/W3029269967","https://openalex.org/W3032439528","https://openalex.org/W3080349078","https://openalex.org/W3082424964","https://openalex.org/W3092962901","https://openalex.org/W3095596741","https://openalex.org/W3101014329","https://openalex.org/W3103177583","https://openalex.org/W3123375411","https://openalex.org/W3138890951","https://openalex.org/W3156729426","https://openalex.org/W3174637548","https://openalex.org/W4211173878","https://openalex.org/W4235169531","https://openalex.org/W4238452917","https://openalex.org/W4239181501","https://openalex.org/W4251697274","https://openalex.org/W4287778734","https://openalex.org/W4292081303","https://openalex.org/W6637517355","https://openalex.org/W6679534712","https://openalex.org/W6777276057"],"related_works":["https://openalex.org/W4229078645","https://openalex.org/W1977345676","https://openalex.org/W2567825307","https://openalex.org/W4295762832","https://openalex.org/W1592682627","https://openalex.org/W2785998768","https://openalex.org/W2945016732","https://openalex.org/W2371352078","https://openalex.org/W2362975861","https://openalex.org/W2804963084"],"abstract_inverted_index":{"Modern":[0],"data":[1,21,29,58,61,66,75,123,178,188,217],"lakes":[2,67],"are":[3],"heterogeneous":[4],"in":[5,20,35,55,143],"the":[6,36,206,211,225],"vocabulary":[7],"that":[8,65,140,180],"is":[9,42,132,193],"used":[10,104],"to":[11,98,105,127,149,160,220],"describe":[12],"data.":[13],"We":[14,87,223],"study":[15],"a":[16,28,44,69,81,117,130,133,156,182,186,196,201,221],"problem":[17],"of":[18,74,84,166,208,210,227],"disambiguation":[19,50,73],"lakes:":[22],"How":[23],"can":[24,102],"we":[25,63,198],"determine":[26,128],"if":[27,129],"value":[30,131],"occurring":[31],"more":[32],"than":[33],"once":[34],"lake":[37,218],"has":[38],"different":[39],"meanings":[40,209],"and":[41,48,60,96,125,213,234],"therefore":[43],"homograph?":[45],"While":[46],"word":[47],"entity":[49],"have":[51,181],"been":[52],"well":[53,176],"studied":[54],"computational":[56],"linguistics,":[57],"management,":[59],"science,":[62],"show":[64,224],"provide":[68],"new":[70],"opportunity":[71],"for":[72,170,204,214],"values,":[76],"because":[77],"tables":[78],"implicitly":[79],"define":[80],"massive":[82],"network":[83],"interconnected":[85],"values.":[86],"introduce":[88],"DomainNet":[89,112,171],",":[90,172],"which":[91,173],"efficiently":[92],"represents":[93],"this":[94],"network,":[95],"investigate":[97],"what":[99],"extent":[100],"it":[101],"be":[103,147],"disambiguate":[106],"values":[107,124,179],"without":[108],"requiring":[109],"any":[110],"supervision.":[111],"leverages":[113],"network-centrality":[114],"measures":[115],"on":[116,229],"bipartite":[118],"graph":[119],"whose":[120],"nodes":[121],"represent":[122],"attributes":[126,219],"homograph.":[134],"A":[135],"thorough":[136],"experimental":[137],"evaluation":[138],"demonstrates":[139],"state-of-the-art":[141],"techniques":[142],"domain":[144,157,235],"discovery":[145,158],"cannot":[146],"re-purposed":[148],"compete":[150],"with":[151],"our":[152,190],"method.":[153],"Specifically,":[154],"using":[155],"method":[159,203],"identify":[161],"homographs":[162,175,228],"achieves":[163],"an":[164],"F1-score":[165],"0.38":[167],"versus":[168],"0.69":[169],"separates":[174],"from":[177],"unique":[183],"meaning.":[184,222],"On":[185],"real":[187],"lake,":[189],"top-100":[191],"precision":[192],"93%.":[194],"Given":[195],"homograph,":[197],"also":[199],"present":[200],"novel":[202],"determining":[205],"number":[207],"homograph":[212],"assigning":[215],"its":[216],"influence":[226],"two":[230],"downstream":[231],"tasks:":[232],"entity-matching":[233],"discovery.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}