{"id":"https://openalex.org/W2758222789","doi":"https://doi.org/10.1109/iscbi.2017.8053551","title":"TPC: An automatically generated comprehensive English-Persian parallel corpus","display_name":"TPC: An automatically generated comprehensive English-Persian parallel corpus","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2758222789","doi":"https://doi.org/10.1109/iscbi.2017.8053551","mag":"2758222789"},"language":"en","primary_location":{"id":"doi:10.1109/iscbi.2017.8053551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscbi.2017.8053551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 5th International Symposium on Computational and Business Intelligence (ISCBI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012248611","display_name":"Saeed Farzi","orcid":"https://orcid.org/0000-0003-2850-0616"},"institutions":[{"id":"https://openalex.org/I80543232","display_name":"K.N.Toosi University of Technology","ror":"https://ror.org/0433abe34","country_code":"IR","type":"education","lineage":["https://openalex.org/I80543232"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Saeed Farzi","raw_affiliation_strings":["Faculty of Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I80543232"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055598777","display_name":"Heshaam Faili","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Heshaam Faili","raw_affiliation_strings":["College of Engineering, University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"95"},"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":0.9973999857902527,"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/T10759","display_name":"Translation Studies and Practices","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8529624938964844},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.77909916639328},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7628318071365356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7161447405815125},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6844098567962646},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6137188673019409},{"id":"https://openalex.org/keywords/persian","display_name":"Persian","score":0.5919229984283447},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.5809683203697205},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5219045281410217},{"id":"https://openalex.org/keywords/lexicography","display_name":"Lexicography","score":0.44621118903160095},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.4383874237537384},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.43149739503860474},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4170588552951813},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.3115960359573364},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.17280331254005432},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14841732382774353},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1483028531074524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529624938964844},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.77909916639328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7628318071365356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7161447405815125},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6844098567962646},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6137188673019409},{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.5919229984283447},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.5809683203697205},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5219045281410217},{"id":"https://openalex.org/C80976798","wikidata":"https://www.wikidata.org/wiki/Q184524","display_name":"Lexicography","level":2,"score":0.44621118903160095},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.4383874237537384},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.43149739503860474},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4170588552951813},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.3115960359573364},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.17280331254005432},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14841732382774353},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1483028531074524},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscbi.2017.8053551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscbi.2017.8053551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 5th International Symposium on Computational and Business Intelligence (ISCBI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1973452851","https://openalex.org/W2032494091","https://openalex.org/W2101105183","https://openalex.org/W2108459463","https://openalex.org/W2124807415","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2395641992","https://openalex.org/W4280571180","https://openalex.org/W2578135827","https://openalex.org/W2753600765","https://openalex.org/W3204448004","https://openalex.org/W2099607809","https://openalex.org/W2102772020","https://openalex.org/W92588874","https://openalex.org/W2495157533","https://openalex.org/W3017195079"],"abstract_inverted_index":{"Nowadays;":[0],"Parallel":[1,44],"corpus":[2,41],"is":[3,51,141],"one":[4],"of":[5,30,49,79,152,165],"the":[6,28,54,58,71,80,111,150],"most":[7],"important":[8],"resources":[9],"which":[10,140],"can":[11],"be":[12],"employed":[13],"in":[14,163],"different":[15],"researches":[16],"such":[17],"as":[18],"machine":[19,82],"translation,":[20],"bilingual":[21],"lexicography,":[22],"and":[23,56,76,123,167],"linguistics.":[24],"This":[25],"paper":[26],"describes":[27],"process":[29],"building":[31],"a":[32,95,104,127],"large-scale":[33],"(about":[34],"400,":[35],"000":[36],"sentence":[37,118],"pairs)":[38],"English-Persian":[39],"parallel":[40,98],"called":[42],"Tehran":[43],"Corpus":[45],"(TPC).":[46],"The":[47,147],"aim":[48],"study":[50],"to":[52,93,158],"introduce":[53],"structure":[55],"explain":[57],"materials":[59],"utilized":[60],"for":[61],"constructing":[62],"TPC.":[63],"In":[64,91],"addition,":[65],"some":[66],"useful":[67],"tools":[68],"developed":[69],"within":[70],"project":[72],"have":[73,88,107],"been":[74,89,108],"introduced":[75],"three":[77,136],"sorts":[78],"statistical":[81],"translation":[83],"systems":[84,155],"trained":[85,142],"by":[86,143],"TPC":[87,144],"considered.":[90],"order":[92],"develop":[94],"high":[96],"quality":[97],"corpus,":[99],"unsure":[100],"alignments":[101],"recognized":[102],"via":[103],"MaxEnt":[105],"classifier":[106],"eliminated":[109],"from":[110],"corpus.":[112],"As":[113,132],"an":[114,133],"intrinsic":[115],"evaluation,":[116,135],"1,600":[117],"pairs":[119],"are":[120,145],"elicited":[121],"randomly":[122],"compared":[124],"manually":[125],"with":[126],"gold":[128],"standard":[129],"test":[130],"set.":[131],"extrinsic":[134],"Phrase-based":[137],"SMT":[138],"systems,":[139],"incorporated.":[146],"results":[148],"demonstrate":[149],"superiority":[151],"our":[153],"translator":[154,161],"over":[156],"English":[157],"Persian":[159],"Google":[160],"system":[162],"term":[164],"BLEU":[166],"TER":[168],"metrics.":[169]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}