{"id":"https://openalex.org/W7155384489","doi":"https://doi.org/10.31449/inf.v50i11.13673","title":"LC-ATSR: A Transformer-Based Approach for Semantic Retrieval in Lakehouse Data Platforms","display_name":"LC-ATSR: A Transformer-Based Approach for Semantic Retrieval in Lakehouse Data Platforms","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155384489","doi":"https://doi.org/10.31449/inf.v50i11.13673"},"language":null,"primary_location":{"id":"doi:10.31449/inf.v50i11.13673","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i11.13673","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/13673/6663","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.informatica.si/index.php/informatica/article/download/13673/6663","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134432626","display_name":"Youfang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117818","display_name":"Hexi University","ror":"https://ror.org/02axfzt86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210117818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Youfang Xu","raw_affiliation_strings":["School of Information Technology and media, Hexi University, Zhangye Gansu, 734000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology and media, Hexi University, Zhangye Gansu, 734000, China","institution_ids":["https://openalex.org/I4210117818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5134432626"],"corresponding_institution_ids":["https://openalex.org/I4210117818"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52537225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.15209999680519104,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.15209999680519104,"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/T11719","display_name":"Data Quality and Management","score":0.12890000641345978,"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":0.10260000079870224,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.5788000226020813},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.40450000762939453},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.40130001306533813},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.391400009393692},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3808000087738037},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.367000013589859},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.36579999327659607},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.3422999978065491}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514999747276306},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5128999948501587},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.367000013589859},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36169999837875366},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.29170000553131104},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31449/inf.v50i11.13673","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i11.13673","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/13673/6663","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.31449/inf.v50i11.13673","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v50i11.13673","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/13673/6663","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4085230827331543}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155384489.pdf","grobid_xml":"https://content.openalex.org/works/W7155384489.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3,24,32,39,59,78,96,101,125,185,190,200],"Lakehouse":[4,25,102],"Collaborative":[5],"Adaptive":[6],"Transformer":[7],"Semantic":[8],"Representation":[9],"Algorithm":[10],"(LC-ATSR)":[11],"to":[12,49,72,74,92],"address":[13],"the":[14,110,121,151,162,166,206,218],"core":[15,56],"challenge":[16],"of":[17,20,43,128,134,192,203,209,221],"semantic":[18,80,98,104],"retrieval":[19,177],"unstructured":[21,222],"data":[22,27,47,174,211],"in":[23,172],"integrated":[26,52],"platform.":[28],"The":[29,55,116,146,176],"algorithm":[30,123,183],"uses":[31],"transformer":[33],"as":[34,141],"its":[35],"backbone":[36],"and":[37,46,82,100,130,144,165,199,213],"incorporates":[38],"dual-dimensional":[40],"adaptive":[41],"mechanism":[42,63,106],"storage":[44,60,67,76],"attributes":[45],"types":[48],"construct":[50],"an":[51,131],"\"preprocessing-representation-retrieval\"":[53],"framework.":[54],"designs":[57],"include":[58],"attribute-enhanced":[61],"attention":[62],"that":[64,86,107,120],"integrates":[65],"Lake":[66],"tags":[68],"into":[69],"self-attention":[70],"computation":[71],"adapt":[73],"heterogeneous":[75,173],"characteristics;":[77],"lightweight":[79],"compression":[81],"multi-modal":[83],"alignment":[84],"module":[85],"reduces":[87],"vector":[88],"dimensions":[89],"(from":[90],"768":[91],"256)":[93],"while":[94],"constructing":[95],"unified":[97],"space;":[99],"incremental":[103,152],"indexing":[105],"dynamically":[108],"updates":[109],"index":[111,153],"based":[112,180],"on":[113,181],"LSH":[114],"hashing.":[115],"experimental":[117],"results":[118],"show":[119],"LC-ATSR":[122],"achieves":[124,184],"P@10":[126],"score":[127,133],"89.7%":[129],"F1":[132],"88.2%,":[135],"significantly":[136],"outperforming":[137],"mainstream":[138],"algorithms":[139],"such":[140],"BERT,":[142],"DPR,":[143],"RoBERTa.":[145],"single-retrieval":[147],"latency":[148],"was":[149,156,169],"18.3ms,":[150],"construction":[154],"time":[155,202],"reduced":[157],"by":[158],"68.4%":[159],"compared":[160],"with":[161,195],"full-data":[163],"approach,":[164],"accuracy":[167],"fluctuation":[168],"only":[170],"3.2%":[171],"scenarios.":[175],"system":[178],"built":[179],"this":[182],"99.8%":[186],"functional":[187],"pass":[188],"rate,":[189],"throughput":[191],"286":[193],"QPS":[194],"500":[196],"concurrent":[197],"connections,":[198],"response":[201],"21.3ms,":[204],"meeting":[205],"engineering":[207],"requirements":[208],"enterprise":[210],"platforms":[212],"providing":[214],"technical":[215],"support":[216],"for":[217],"value":[219],"mining":[220],"data.":[223]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-04-24T00:00:00"}