{"id":"https://openalex.org/W4320024223","doi":"https://doi.org/10.1109/bigdata55660.2022.10021032","title":"EntityRank: Unsupervised Mining of Bilingual Named Entity Pairs from Parallel Corpora for Neural Machine Translation","display_name":"EntityRank: Unsupervised Mining of Bilingual Named Entity Pairs from Parallel Corpora for Neural Machine Translation","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024223","doi":"https://doi.org/10.1109/bigdata55660.2022.10021032"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10021032","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10021032","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5100671757","display_name":"M. Zhang","orcid":"https://orcid.org/0000-0001-8659-5727"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043581386","display_name":"Song Peng","orcid":"https://orcid.org/0000-0002-8757-0983"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Peng","raw_affiliation_strings":["Huawei Translation Services Center,Dongguan,China","Huawei Translation Services Center, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Dongguan,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Dongguan, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038736812","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0001-8861-7010"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037683279","display_name":"Yanqing Zhao","orcid":"https://orcid.org/0009-0003-4939-2519"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanqing Zhao","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065926428","display_name":"Xiaosong Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaosong Qiao","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100569705","display_name":"Junhao Zhu","orcid":"https://orcid.org/0009-0009-0768-6870"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhao Zhu","raw_affiliation_strings":["Huawei Translation Services Center,Dongguan,China","Huawei Translation Services Center, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Dongguan,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Dongguan, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006709668","display_name":"Shimin Tao","orcid":"https://orcid.org/0000-0002-2795-6921"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Tao","raw_affiliation_strings":["Huawei Translation Services Center,Beijing,China","Huawei Translation Services Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013250925","display_name":"Ying Qin","orcid":"https://orcid.org/0000-0003-4606-7174"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Qin","raw_affiliation_strings":["Huawei Translation Services Center,Dongguan,China","Huawei Translation Services Center, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Dongguan,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Dongguan, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065359060","display_name":"Yanfei Jiang","orcid":"https://orcid.org/0009-0001-2817-1018"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfei Jiang","raw_affiliation_strings":["Huawei Translation Services Center,Dongguan,China","Huawei Translation Services Center, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"Huawei Translation Services Center,Dongguan,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Translation Services Center, Dongguan, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100671757"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46288515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"3708","last_page":"3713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9728000164031982,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8678188323974609},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.81700199842453},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7006938457489014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6522431373596191},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6060907244682312},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.5017187595367432},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.45995035767555237},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.44213590025901794},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41034987568855286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8678188323974609},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.81700199842453},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7006938457489014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6522431373596191},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6060907244682312},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5017187595367432},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.45995035767555237},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.44213590025901794},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41034987568855286},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10021032","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10021032","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2100495367","https://openalex.org/W2604561121","https://openalex.org/W2620949368","https://openalex.org/W2740887992","https://openalex.org/W2781528640","https://openalex.org/W2912512851","https://openalex.org/W2914304175","https://openalex.org/W2914605928","https://openalex.org/W3035169087","https://openalex.org/W3211848854","https://openalex.org/W4205167092","https://openalex.org/W4300273322","https://openalex.org/W4320507214","https://openalex.org/W4385245566","https://openalex.org/W6638575559","https://openalex.org/W6639055396","https://openalex.org/W6655443941","https://openalex.org/W6679436768","https://openalex.org/W6679494921","https://openalex.org/W6680842446","https://openalex.org/W6682026795","https://openalex.org/W6683314313","https://openalex.org/W6732580896","https://openalex.org/W6734621010","https://openalex.org/W6736959282","https://openalex.org/W6737778391","https://openalex.org/W6750723735","https://openalex.org/W6762848077","https://openalex.org/W6772105428","https://openalex.org/W6776685237","https://openalex.org/W6787723393","https://openalex.org/W6797305597","https://openalex.org/W6809780420","https://openalex.org/W6810719880","https://openalex.org/W6826993684","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2949454572","https://openalex.org/W2952599318","https://openalex.org/W2890256614","https://openalex.org/W2883671469"],"abstract_inverted_index":{"As":[0],"Neural":[1],"Machine":[2],"Translation":[3],"(NMT)":[4],"heavily":[5],"relies":[6],"on":[7,89],"training":[8],"data,":[9,138],"finding":[10],"an":[11],"effective":[12],"method":[13,44,106],"to":[14,71],"help":[15],"NMT":[16],"make":[17],"better":[18],"use":[19],"of":[20,24,33,135,145],"limited":[21],"data":[22,76,121],"is":[23],"great":[25],"significance.":[26],"In":[27],"this":[28],"paper,":[29],"with":[30,118],"the":[31,34,66,80,86,90,104,119,124,132,142,146],"motivation":[32],"famous":[35],"Google\u2019s":[36],"PageRank":[37],"algorithm,":[38],"we":[39,73],"propose":[40],"a":[41,75],"novel":[42],"unsupervised":[43,105],"EntityRank":[45,70,107],"for":[46,79],"mining":[47],"bilingual":[48,113],"named":[49,114],"entity":[50,115],"pairs":[51,67,126],"from":[52],"parallel":[53,97],"corpora,":[54,98],"which":[55],"involves":[56],"three":[57],"critical":[58],"components":[59],"(Generator,":[60],"Scorer":[61],"and":[62,93,117],"Filter).":[63],"To":[64],"apply":[65],"mined":[68,125],"by":[69],"NMT,":[72],"design":[74],"augmentation":[77,122],"strategy":[78],"state-of-the-art":[81],"(SOTA)":[82],"model":[83],"Transformer.":[84],"From":[85],"experimental":[87],"results":[88],"CCMT20":[91],"English-Chinese":[92],"WMT14":[94],"English-German":[95],"news":[96],"it":[99],"can":[100],"be":[101],"seen":[102],"that":[103],"could":[108,127],"obtain":[109],"relatively":[110],"high":[111],"quality":[112,134,144],"pairs;":[116],"designed":[120],"strategy,":[123],"not":[128],"only":[129],"significantly":[130],"improve":[131],"translation":[133,143],"their":[136],"covered":[137],"but":[139],"also":[140],"benefit":[141],"overall":[147],"data.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
