{"id":"https://openalex.org/W4408226290","doi":"https://doi.org/10.1142/s1793351x25420024","title":"Comparative Analysis of Indexing Techniques for Table Search in Data Lakes","display_name":"Comparative Analysis of Indexing Techniques for Table Search in Data Lakes","publication_year":2025,"publication_date":"2025-03-07","ids":{"openalex":"https://openalex.org/W4408226290","doi":"https://doi.org/10.1142/s1793351x25420024"},"language":"en","primary_location":{"id":"doi:10.1142/s1793351x25420024","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x25420024","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-7108","issn":["1793-7108","1793-351X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/5b18a553-1be0-4342-9dd5-9268ae1bbc7b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104262686","display_name":"Ibraheem Taha","orcid":"https://orcid.org/0009-0002-2956-7281"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK","GR"],"is_corresponding":false,"raw_author_name":"Ibraheem Taha","raw_affiliation_strings":["National Kapodistrian University of Athens, Athena Research Center, Aalborg University, Athens, Greece","Aalborg University, The Technical Faculty of IT and Design, DK"],"raw_orcid":"https://orcid.org/0009-0002-2956-7281","affiliations":[{"raw_affiliation_string":"National Kapodistrian University of Athens, Athena Research Center, Aalborg University, Athens, Greece","institution_ids":["https://openalex.org/I200777214","https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084898176","display_name":"Matteo Lissandrini","orcid":"https://orcid.org/0000-0001-7922-5998"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK","IT"],"is_corresponding":false,"raw_author_name":"Matteo Lissandrini","raw_affiliation_strings":["University of Verona, Verona, Italy","Aalborg University, The Technical Faculty of IT and Design, DK"],"raw_orcid":"https://orcid.org/0000-0001-7922-5998","affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]},{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072082268","display_name":"Alkis Simitsis","orcid":"https://orcid.org/0009-0006-6078-5323"},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Alkis Simitsis","raw_affiliation_strings":["Athena Research Center, Athens, Greece"],"raw_orcid":"https://orcid.org/0009-0006-6078-5323","affiliations":[{"raw_affiliation_string":"Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084870386","display_name":"Yannis Ioannidis","orcid":"https://orcid.org/0000-0002-1705-8247"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Ioannidis","raw_affiliation_strings":["National Kapodistrian University of Athens, Athena Research Center, Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0002-1705-8247","affiliations":[{"raw_affiliation_string":"National Kapodistrian University of Athens, Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I200777214","https://openalex.org/I4210156054"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1401,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76648207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"19","issue":"02","first_page":"173","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.984000027179718,"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":0.984000027179718,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9760000109672546,"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":0.9747999906539917,"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":0.8278031349182129},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.776138961315155},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6848828196525574},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6174558401107788},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43951615691185},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38104817271232605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278031349182129},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.776138961315155},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6848828196525574},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6174558401107788},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43951615691185},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38104817271232605}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s1793351x25420024","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x25420024","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-7108","issn":["1793-7108","1793-351X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/5b18a553-1be0-4342-9dd5-9268ae1bbc7b","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/5b18a553-1be0-4342-9dd5-9268ae1bbc7b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Taha, I, Lissandrini, M, Simitsis, A & Ioannidis, Y 2025, 'Comparative Analysis of Indexing Techniques for Table Search in Data Lakes', International Journal of Semantic Computing, vol. 19, no. 02, pp. 173-196. https://doi.org/10.1142/S1793351X25420024","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/5b18a553-1be0-4342-9dd5-9268ae1bbc7b","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/5b18a553-1be0-4342-9dd5-9268ae1bbc7b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Taha, I, Lissandrini, M, Simitsis, A & Ioannidis, Y 2025, 'Comparative Analysis of Indexing Techniques for Table Search in Data Lakes', International Journal of Semantic Computing, vol. 19, no. 02, pp. 173-196. https://doi.org/10.1142/S1793351X25420024","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.7200000286102295,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1970709149","https://openalex.org/W2121350579","https://openalex.org/W2123194427","https://openalex.org/W2124509324","https://openalex.org/W2140116426","https://openalex.org/W2147717514","https://openalex.org/W2169624745","https://openalex.org/W2341748398","https://openalex.org/W2795089200","https://openalex.org/W2798664493","https://openalex.org/W2926805670","https://openalex.org/W2948163032","https://openalex.org/W2951621897","https://openalex.org/W2963174348","https://openalex.org/W2963469388","https://openalex.org/W2963626623","https://openalex.org/W3014616325","https://openalex.org/W3032215537","https://openalex.org/W3082424964","https://openalex.org/W3196481040","https://openalex.org/W4205922070","https://openalex.org/W4283383705","https://openalex.org/W4375928372","https://openalex.org/W4380433117","https://openalex.org/W4385653220","https://openalex.org/W4393066124"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W2130160813","https://openalex.org/W2054476758","https://openalex.org/W2350613701","https://openalex.org/W2188505374","https://openalex.org/W1558342070"],"abstract_inverted_index":{"Data":[0],"lakes":[1],"store":[2],"vast":[3],"amount":[4],"of":[5,7,66,82,104,142,150,170,181,200],"datasets":[6,180],"various":[8,12,182],"forms":[9],"collected":[10],"from":[11],"sources.":[13],"In":[14,113],"this":[15,114,122],"context,":[16],"efficient":[17],"table":[18,46,132],"search":[19,85,133],"is":[20,110],"essential":[21],"for":[22,40,55,131],"identifying":[23],"and":[24,31,74,102,153,163,184,198,202],"integrating":[25],"data":[26,135],"to":[27,190,204],"support":[28],"business":[29],"intelligence":[30],"machine":[32],"learning":[33,50],"pipelines.":[34],"This":[35,186],"paper":[36],"explores":[37],"effective":[38],"methods":[39],"finding":[41],"related":[42],"tables":[43,56],"using":[44],"advanced":[45,67,128],"representation":[47],"learning.":[48],"Representation":[49],"generates":[51],"dense":[52],"vector":[53,87],"representations":[54],"at":[57,118],"different":[58],"levels":[59],"(row,":[60],"column,":[61],"cell),":[62],"enabling":[63],"the":[64,79,151,168,196],"use":[65],"indexing":[68,92,155,192],"techniques":[69,93,130],"such":[70],"as":[71],"LSH,":[72],"HNSW,":[73],"DiskANN,":[75],"which":[76],"speed":[77],"up":[78],"core":[80],"operation":[81],"approximate":[83],"k-NN":[84],"within":[86],"spaces.":[88],"However,":[89],"while":[90],"several":[91],"have":[94],"been":[95],"proposed":[96],"so":[97],"far,":[98],"a":[99,139,148],"thorough":[100],"study":[101,187],"comparison":[103,149],"their":[105,158],"effectiveness":[106],"versus":[107],"performance":[108],"trade-offs":[109],"still":[111],"missing.":[112],"paper,":[115],"we":[116,146,166],"aim":[117],"shedding":[119],"light":[120],"on":[121,173],"gap.":[123],"We":[124],"begin":[125],"by":[126,138],"reviewing":[127],"vector-search":[129],"in":[134],"lakes,":[136],"followed":[137],"detailed":[140],"analysis":[141],"k-ANN":[143],"indexes.":[144],"Next,":[145],"present":[147],"HNSW":[152],"DiskANN":[154],"techniques,":[156],"comparing":[157],"internal":[159],"structure,":[160],"effectiveness,":[161],"efficiency,":[162],"scalability.":[164],"Additionally,":[165],"explore":[167,191],"impact":[169],"model":[171],"accuracy":[172],"index":[174],"performance.":[175],"Our":[176],"experiments":[177],"include":[178],"four":[179],"sizes":[183],"complexity.":[185],"allows":[188],"us":[189],"design":[193],"options,":[194],"revealing":[195],"strengths":[197],"weaknesses":[199],"each,":[201],"also":[203],"identify":[205],"potentially":[206],"interesting":[207],"future":[208],"research":[209],"directions.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}