{"id":"https://openalex.org/W2985009327","doi":"https://doi.org/10.1145/3357384.3358018","title":"Deep Sequence-to-Sequence Entity Matching for Heterogeneous Entity Resolution","display_name":"Deep Sequence-to-Sequence Entity Matching for Heterogeneous Entity Resolution","publication_year":2019,"publication_date":"2019-11-03","ids":{"openalex":"https://openalex.org/W2985009327","doi":"https://doi.org/10.1145/3357384.3358018","mag":"2985009327"},"language":"en","primary_location":{"id":"doi:10.1145/3357384.3358018","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th 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/A5066328795","display_name":"Hao Nie","orcid":"https://orcid.org/0000-0002-3031-5930"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Nie","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620300","display_name":"Xianpei Han","orcid":"https://orcid.org/0000-0002-1304-6302"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianpei Han","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109888639","display_name":"Ben He","orcid":"https://orcid.org/0000-0002-2699-9209"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ben He","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034536222","display_name":"Le Sun","orcid":"https://orcid.org/0000-0002-4221-0327"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Sun","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427262","display_name":"Bo Chen","orcid":"https://orcid.org/0000-0001-6150-3881"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Chen","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100756628","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-5556-3896"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037925740","display_name":"Suhui Wu","orcid":"https://orcid.org/0000-0003-1674-4111"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Suhui Wu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067594005","display_name":"Hao Kong","orcid":"https://orcid.org/0000-0002-1378-0056"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Kong","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5066328795"],"corresponding_institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":10.6951,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.9849965,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"629","last_page":"638"},"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/T10028","display_name":"Topic Modeling","score":0.9922999739646912,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9488000273704529,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.829829216003418},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7709447145462036},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6847220659255981},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6586917638778687},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.542367160320282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5039343237876892},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.473435640335083},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.472508043050766},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4264729917049408},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.420274019241333},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41768455505371094},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4150194823741913},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.41350096464157104},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.40988728404045105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3818868100643158},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3781405985355377},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.17363539338111877},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0969354510307312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829829216003418},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7709447145462036},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6847220659255981},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6586917638778687},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.542367160320282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5039343237876892},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.473435640335083},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.472508043050766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4264729917049408},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.420274019241333},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41768455505371094},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4150194823741913},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.41350096464157104},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40988728404045105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3818868100643158},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3781405985355377},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.17363539338111877},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0969354510307312},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3357384.3358018","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1565102206","https://openalex.org/W1742677423","https://openalex.org/W1964786778","https://openalex.org/W1981590391","https://openalex.org/W1982350890","https://openalex.org/W2015452969","https://openalex.org/W2016753842","https://openalex.org/W2041439319","https://openalex.org/W2067566391","https://openalex.org/W2079659743","https://openalex.org/W2110411158","https://openalex.org/W2111625757","https://openalex.org/W2117974736","https://openalex.org/W2139490252","https://openalex.org/W2139929608","https://openalex.org/W2140655242","https://openalex.org/W2153579005","https://openalex.org/W2154785834","https://openalex.org/W2163605009","https://openalex.org/W2164456230","https://openalex.org/W2171472464","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2261525379","https://openalex.org/W2437617937","https://openalex.org/W2493916176","https://openalex.org/W2522988508","https://openalex.org/W2542998387","https://openalex.org/W2612177096","https://openalex.org/W2767857566","https://openalex.org/W2794573079","https://openalex.org/W2798649495","https://openalex.org/W2804552794","https://openalex.org/W2966720878","https://openalex.org/W3006210356","https://openalex.org/W3099883947","https://openalex.org/W4246012463"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W3198729192","https://openalex.org/W4401821554","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W3000685722","https://openalex.org/W2520117834","https://openalex.org/W2530283981","https://openalex.org/W2792659145","https://openalex.org/W4300474194"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"(ER)":[2],"identifies":[3],"records":[4,143],"from":[5,42,51],"different":[6,52,58],"data":[7,53],"sources":[8,54],"that":[9],"refer":[10],"to":[11],"the":[12,86,114,119],"same":[13],"real-world":[14],"entity.":[15],"Conventional":[16],"ER":[17,33,46,93,130],"approaches":[18],"usually":[19],"employ":[20],"a":[21,74,95],"structure":[22,36],"matching":[23,37,78,98,126,158],"mechanism,":[24],"where":[25],"attributes":[26],"are":[27,55],"aligned,":[28],"compared":[29],"and":[30,44,60,88,124,147],"aggregated":[31],"for":[32,107,128],"decision.":[34],"The":[35],"approaches,":[38],"unfortunately,":[39],"often":[40],"suffer":[41],"heterogeneous":[43,87],"dirty":[45,89],"problems.":[47],"That":[48],"is,":[49],"entities":[50],"described":[56],"using":[57],"schemas,":[59],"attribute":[61],"values":[62],"may":[63],"be":[64],"misplaced,":[65],"missing,":[66],"or":[67],"noisy.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72,101],"propose":[73,102],"deep":[75],"sequence-to-sequence":[76,97],"entity":[77,109,142,157,168],"model,":[79],"denoted":[80],"Seq2SeqMatcher,":[81],"which":[82,111],"can":[83,112,160],"effectively":[84],"solve":[85],"problems":[90],"by":[91,140],"modeling":[92],"as":[94],"token-level":[96],"task.":[99],"Specifically,":[100],"an":[103,133,152],"align-compare-aggregate":[104],"neural":[105],"network":[106],"Seq2Seq":[108,156],"matching,":[110],"learn":[113],"representations":[115],"of":[116],"tokens,":[117,123],"capture":[118],"semantic":[120],"relevance":[121],"between":[122],"aggregate":[125],"evidence":[127],"accurate":[129],"decisions":[131],"in":[132,144,151],"end-to-end":[134,153],"manner.":[135],"Experimental":[136],"results":[137],"show":[138],"that,":[139],"comparing":[141],"token":[145],"level":[146],"learning":[148],"all":[149],"components":[150],"manner,":[154],"our":[155],"model":[159],"achieve":[161],"remarkable":[162],"performance":[163],"improvements":[164],"on":[165],"9":[166],"standard":[167],"resolution":[169],"benchmarks.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}