{"id":"https://openalex.org/W4403582731","doi":"https://doi.org/10.1145/3627673.3679843","title":"Enhancing Deep Entity Resolution with Integrated Blocker-Matcher Training: Balancing Consensus and Discrepancy","display_name":"Enhancing Deep Entity Resolution with Integrated Blocker-Matcher Training: Balancing Consensus and Discrepancy","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582731","doi":"https://doi.org/10.1145/3627673.3679843"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679843","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","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/A5028615006","display_name":"Wenzhou Dou","orcid":"https://orcid.org/0009-0005-5823-1965"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhou Dou","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0005-5823-1965","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015251362","display_name":"Derong Shen","orcid":"https://orcid.org/0000-0003-0310-6372"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Derong Shen","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-0310-6372","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024298278","display_name":"Xiangmin Zhou","orcid":"https://orcid.org/0000-0002-1302-818X"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiangmin Zhou","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1302-818X","affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hui Bai","orcid":"https://orcid.org/0009-0008-9582-6425"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Bai","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0008-9582-6425","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026995541","display_name":"Yue Kou","orcid":"https://orcid.org/0000-0002-5307-4893"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Kou","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-5307-4893","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102979521","display_name":"Tiezheng Nie","orcid":"https://orcid.org/0000-0002-0166-1324"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiezheng Nie","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-0166-1324","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110375654","display_name":"Hang Cui","orcid":"https://orcid.org/0000-0002-0987-3743"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Cui","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, USA"],"raw_orcid":"https://orcid.org/0000-0002-0987-3743","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072406974","display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-3171-8889","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8658,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77620369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"508","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9771999716758728,"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/T10028","display_name":"Topic Modeling","score":0.958899974822998,"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":0.6563042402267456},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5576954483985901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45421233773231506},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.42899924516677856},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07030242681503296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563042402267456},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5576954483985901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45421233773231506},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.42899924516677856},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07030242681503296},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679843","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1964786778","https://openalex.org/W1981590391","https://openalex.org/W1992930793","https://openalex.org/W2056748234","https://openalex.org/W2073471108","https://openalex.org/W2106675345","https://openalex.org/W2107966677","https://openalex.org/W2161936973","https://openalex.org/W2546672044","https://openalex.org/W2612526608","https://openalex.org/W2775696413","https://openalex.org/W2798649495","https://openalex.org/W2892181857","https://openalex.org/W2951147191","https://openalex.org/W2962781182","https://openalex.org/W2963430933","https://openalex.org/W2970641574","https://openalex.org/W2985009327","https://openalex.org/W2992897306","https://openalex.org/W3011807731","https://openalex.org/W3012733951","https://openalex.org/W3032559159","https://openalex.org/W3034756453","https://openalex.org/W3099734810","https://openalex.org/W3142849873","https://openalex.org/W3155747247","https://openalex.org/W3197468999","https://openalex.org/W4205196528","https://openalex.org/W4226341500","https://openalex.org/W4254788633","https://openalex.org/W4281721601","https://openalex.org/W4312923108","https://openalex.org/W4319975816","https://openalex.org/W4321448364","https://openalex.org/W4382239817","https://openalex.org/W4386591587","https://openalex.org/W4387841511","https://openalex.org/W4391054937","https://openalex.org/W4400909484","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Deep":[0],"entity":[1,94],"resolution":[2,95],"(ER)":[3],"identifies":[4],"matching":[5,200],"entities":[6],"across":[7],"data":[8],"sources":[9],"using":[10],"techniques":[11,146],"based":[12],"on":[13,209],"deep":[14,47,93],"learning.":[15],"It":[16],"involves":[17],"two":[18],"steps:":[19],"a":[20,33,92,118,128],"blocker":[21,78,103,126,163,169],"for":[22,35,59,124,141,179,195],"identifying":[23],"the":[24,29,38,72,77,82,86,102,108,125,142,162,168,175,184,192,205],"potential":[25],"matches":[26,39],"to":[27,55,70,159,172,182,190,203],"generate":[28],"candidate":[30,44],"pairs,":[31],"and":[32,40,61,74,79,99,104,110,127,152,164,170,199,219,228],"matcher":[34,171],"accurately":[36],"distinguishing":[37],"non-matches":[41],"among":[42],"these":[43],"pairs.":[45],"Recent":[46],"ER":[48],"approaches":[49],"utilize":[50],"pretrained":[51],"language":[52,138],"models":[53],"(PLMs)":[54],"extract":[56],"similarity":[57,193],"features":[58],"blocking":[60,198],"matching,":[62],"achieving":[63,222],"state-of-the-art":[64],"performance.":[65],"However,":[66],"they":[67],"often":[68],"fail":[69],"balance":[71],"consensus":[73,83,109],"discrepancy":[75,111],"between":[76,112],"matcher,":[80,105],"emphasizing":[81],"while":[84,186],"neglecting":[85],"discrepancy.":[87],"This":[88],"paper":[89],"proposes":[90],"MutualER,":[91],"framework":[96],"that":[97,213],"integrates":[98],"jointly":[100,160],"trains":[101],"balancing":[106],"both":[107,226],"them.":[113],"Specifically,":[114],"we":[115],"firstly":[116],"introduce":[117],"lightweight":[119],"PLM":[120,130],"in":[121,131,225],"siamese":[122],"structure":[123,133],"heavier":[129],"cross":[132],"or":[134],"an":[135],"autoregressive":[136],"large":[137],"model":[139],"(LLM)":[140],"matcher.":[143,165],"Two":[144],"optimization":[145],"named":[147],"Mutual":[148],"Sample":[149],"Selection":[150],"(MSS)":[151],"Similarity":[153],"Knowledge":[154],"Transferring":[155],"(SKT)":[156],"are":[157],"designed":[158],"train":[161],"MSS":[166],"enables":[167],"mutually":[173],"select":[174],"customized":[176],"training":[177],"samples":[178],"each":[180],"other":[181],"maintain":[183,204],"discrepancy,":[185],"SKT":[187],"allows":[188],"them":[189],"share":[191],"knowledge":[194],"improving":[196],"their":[197],"capabilities":[201],"respectively":[202],"consensus.":[206],"Extensive":[207],"experiments":[208],"five":[210],"datasets":[211],"demonstrate":[212],"MutualER":[214],"significantly":[215],"outperforms":[216],"existing":[217],"PLM-based":[218],"LLM-based":[220],"approaches,":[221],"leading":[223],"performance":[224],"effectiveness":[227],"efficiency.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}