{"id":"https://openalex.org/W4406458027","doi":"https://doi.org/10.1109/bigdata62323.2024.10825234","title":"Unsupervised Domain Adaptation for Entity Blocking Leveraging Large Language Models","display_name":"Unsupervised Domain Adaptation for Entity Blocking Leveraging Large Language Models","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458027","doi":"https://doi.org/10.1109/bigdata62323.2024.10825234"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5068930286","display_name":"Yaoshu Wang","orcid":"https://orcid.org/0000-0002-5760-5145"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yaoshu Wang","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences,Fundamental Research Department,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences,Fundamental Research Department,Shenzhen,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002103818","display_name":"Mengyi Yan","orcid":"https://orcid.org/0009-0006-9991-0267"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyi Yan","raw_affiliation_strings":["Beihang University,Computer Science Department,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Computer Science Department,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068930286"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70821396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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/T11719","display_name":"Data Quality and Management","score":0.9957000017166138,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9736999869346619,"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":0.8156887292861938},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.8126475811004639},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6795793771743774},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6414596438407898},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47934967279434204},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.462439626455307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.372495174407959},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3386790156364441},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15491020679473877},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.0709812343120575},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06107094883918762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156887292861938},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.8126475811004639},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6795793771743774},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6414596438407898},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47934967279434204},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.462439626455307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.372495174407959},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3386790156364441},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15491020679473877},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0709812343120575},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06107094883918762},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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":42,"referenced_works":["https://openalex.org/W1910093137","https://openalex.org/W1964786778","https://openalex.org/W2079649893","https://openalex.org/W2111116800","https://openalex.org/W2775696413","https://openalex.org/W2798649495","https://openalex.org/W2911280950","https://openalex.org/W2951147191","https://openalex.org/W2963463240","https://openalex.org/W2970641574","https://openalex.org/W2982756875","https://openalex.org/W3011807731","https://openalex.org/W3014705052","https://openalex.org/W3123375411","https://openalex.org/W3174036215","https://openalex.org/W3197468999","https://openalex.org/W4236102654","https://openalex.org/W4295330703","https://openalex.org/W4297808394","https://openalex.org/W4312851456","https://openalex.org/W4312923108","https://openalex.org/W4366729173","https://openalex.org/W4386591587","https://openalex.org/W4387321091","https://openalex.org/W4387596482","https://openalex.org/W4387709463","https://openalex.org/W4395443438","https://openalex.org/W4396757436","https://openalex.org/W4397029689","https://openalex.org/W4401864268","https://openalex.org/W4404783811","https://openalex.org/W6632038546","https://openalex.org/W6640045804","https://openalex.org/W6750109254","https://openalex.org/W6762638821","https://openalex.org/W6775270172","https://openalex.org/W6785494106","https://openalex.org/W6790968595","https://openalex.org/W6844194202","https://openalex.org/W6857549670","https://openalex.org/W6865036302","https://openalex.org/W6929695809"],"related_works":["https://openalex.org/W4394775207","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W3203792196","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W2955455867","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"Entity":[0,86],"blocking,":[1,54],"which":[2,66],"aims":[3],"to":[4,27,113,137,154,174],"find":[5],"all":[6,55],"potentially":[7],"matched":[8],"tuple":[9],"pairs":[10],"in":[11,62],"large-scale":[12],"data,":[13],"is":[14,22,89],"an":[15,151],"important":[16],"step":[17,153],"for":[18,52,70,81,85,143],"entity":[19,53,156],"resolution.":[20],"It":[21],"non-trivial":[23],"because":[24],"it":[25,43],"needs":[26],"consider":[28],"both":[29],"of":[30,38,56,104,187],"the":[31,36,63,92,102,109,115,124,129,178,182,188,196],"effectiveness":[32],"and":[33,35,94,120,140,145,195],"efficiency,":[34],"emergence":[37],"representation":[39,49],"learning":[40,50,99,111],"has":[41,177],"made":[42],"possible.":[44],"Although":[45],"there":[46],"exist":[47],"existing":[48],"models":[51],"them":[57],"require":[58],"self-curated":[59],"training":[60,162],"instances":[61,163],"target":[64,95,121,146],"domain,":[65],"limits":[67],"their":[68],"capabilities":[69,103],"unseen":[71],"data.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76,149,170],"propose":[77,150],"UDAEB,":[78],"a":[79],"framework":[80],"Unsupervised":[82],"Domain":[83],"Adaptation":[84],"Blocking":[87],"that":[88],"fine-tuned":[90],"between":[91,118],"source":[93,119,144],"domains":[96,122],"using":[97],"contrastive":[98],"by":[100,159,166],"leveraging":[101,167],"LLMs.":[105,168],"UDAEB":[106,133,176],"first":[107],"adopts":[108],"adversarial":[110],"strategy":[112],"reduce":[114],"distribution":[116],"discrepency":[117],"as":[123],"warmup":[125],"step.":[126],"Based":[127],"on":[128],"initially":[130],"learned":[131],"representations,":[132],"involves":[134],"pre-trained":[135],"LLMs":[136],"enrich":[138],"robust":[139],"distinguishable":[141],"attributes":[142],"domains.":[147],"Furthermore,":[148],"iterative":[152],"fine-tune":[155],"blocking":[157],"model":[158],"selecting":[160],"high-quality":[161],"with":[164,185],"pseudo-labels":[165],"Finally":[169],"conduct":[171],"comprehensive":[172],"experiments":[173],"show":[175],"superior":[179],"performance":[180],"against":[181],"state-of-the-art":[183],"algorithms":[184],"aspects":[186],"pair":[189,192],"completeness":[190],"(PC),":[191],"quality":[193],"(PQ)":[194],"candidate":[197],"set":[198],"size":[199],"ratio":[200],"(CSSR).":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}