{"id":"https://openalex.org/W3167997062","doi":"https://doi.org/10.1145/3447548.3467209","title":"GEM: Translation-Free Zero-Shot Global Entity Matcher for Global Catalogs","display_name":"GEM: Translation-Free Zero-Shot Global Entity Matcher for Global Catalogs","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3167997062","doi":"https://doi.org/10.1145/3447548.3467209","mag":"3167997062"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467209","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","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/A5081311040","display_name":"Karim Bouyarmane","orcid":"https://orcid.org/0000-0003-4284-0561"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karim Bouyarmane","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5081311040"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.1743,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51594149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2593","last_page":"2600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9704999923706055,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9702000021934509,"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":0.853607177734375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6555149555206299},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6422984004020691},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6111920475959778},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5568196773529053},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5561173558235168},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5322242975234985},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.521425724029541},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.499788761138916},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4808019697666168},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.4709433317184448},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.423622190952301},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4220139980316162},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4045308828353882},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30680787563323975},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12921875715255737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.853607177734375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6555149555206299},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6422984004020691},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6111920475959778},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5568196773529053},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5561173558235168},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5322242975234985},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.521425724029541},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.499788761138916},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4808019697666168},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.4709433317184448},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.423622190952301},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4220139980316162},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4045308828353882},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30680787563323975},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12921875715255737},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447548.3467209","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1495017208","https://openalex.org/W1832693441","https://openalex.org/W1899794420","https://openalex.org/W2043437843","https://openalex.org/W2073471108","https://openalex.org/W2550821151","https://openalex.org/W2798649495","https://openalex.org/W2907399266","https://openalex.org/W2946123203","https://openalex.org/W2962870495","https://openalex.org/W2963403868","https://openalex.org/W2970971581","https://openalex.org/W2989799604","https://openalex.org/W3146259567","https://openalex.org/W4234053595"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W3204726280","https://openalex.org/W4287761227","https://openalex.org/W3033862527","https://openalex.org/W3207932232","https://openalex.org/W1538473846","https://openalex.org/W3186330018","https://openalex.org/W3177381119","https://openalex.org/W3212190902","https://openalex.org/W4225789422"],"abstract_inverted_index":{"We":[0,84,110],"propose":[1],"a":[2,14,89,107,126],"modular":[3],"BiLSTM":[4],"/":[5,7],"CNN":[6],"Transformer":[8],"deep-learning":[9],"encoder":[10],"architecture,":[11],"together":[12],"with":[13],"data":[15,37,49,76],"synthesis":[16],"and":[17,34,54,64,129],"training":[18],"approach,":[19],"to":[20,77,118],"solve":[21],"the":[22,51,58,70,73,78,113,131],"problem":[23],"of":[24,57,72,106],"matching":[25,96],"catalog":[26,36,52,74],"products":[27],"across":[28],"different":[29,31,35],"languages,":[30],"local":[32,100],"catalogs,":[33],"contributors.":[38],"The":[39],"end-to-end":[40],"model":[41,91,114,132],"relies":[42],"solely":[43],"on":[44,55,88,137],"raw":[45],"natural":[46],"language":[47,81,138],"textual":[48],"in":[50,142],"entries":[53],"images":[56],"products,":[59],"without":[60],"any":[61],"feature":[62],"engineering,":[63],"is":[65],"entirely":[66],"translation-free,":[67],"not":[68,140],"requiring":[69],"translation":[71],"natural-language":[75],"same":[79],"base":[80],"for":[82],"inference.":[83],"report":[85],"experiments":[86],"results":[87],"4-languages-scope":[90],"(English,":[92],"French,":[93],"German,":[94],"Spanish)":[95],"entities":[97],"from":[98],"4":[99],"catalogs":[101],"(UK,":[102],"France,":[103],"Germany,":[104],"Spain)":[105],"retail":[108],"website.":[109],"demonstrate":[111],"that":[112,123,130],"achieves":[115,133],"performance":[116],"comparable":[117],"state-of-the-art":[119],"existing":[120],"entity":[121],"matchers":[122],"operate":[124],"within":[125],"single":[127],"language,":[128],"high-performance":[134],"zero-shot":[135],"inference":[136],"pairs":[139],"seen":[141],"training.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}