{"id":"https://openalex.org/W2972978035","doi":"https://doi.org/10.1109/access.2019.2941161","title":"Arabic\u2013Chinese Neural Machine Translation: Romanized Arabic as Subword Unit for Arabic-sourced Translation","display_name":"Arabic\u2013Chinese Neural Machine Translation: Romanized Arabic as Subword Unit for Arabic-sourced Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972978035","doi":"https://doi.org/10.1109/access.2019.2941161","mag":"2972978035"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2941161","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2941161","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835016.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835016.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033073504","display_name":"Fares Aqlan","orcid":"https://orcid.org/0000-0002-3957-8622"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fares Aqlan","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University (CSU), Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-3957-8622","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University (CSU), Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024785057","display_name":"Xiaoping Fan","orcid":"https://orcid.org/0000-0003-0172-4070"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoping Fan","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University (CSU), Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University (CSU), Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090138632","display_name":"Abdullah Alqwbani","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Abdullah Alqwbani","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University (CSU), Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University (CSU), Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057669933","display_name":"Akram Al-Mansoub","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Akram Al-Mansoub","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology (SCUT), Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology (SCUT), Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.8355,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89153841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"133122","last_page":"133135"},"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":0.9993000030517578,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8201308250427246},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7270452976226807},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7156308889389038},{"id":"https://openalex.org/keywords/romanization","display_name":"Romanization","score":0.7154442071914673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6475445032119751},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.6366615295410156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5070037841796875},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.45144954323768616},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.44509726762771606},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.44365739822387695},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.4385858178138733},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.42031192779541016},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.3187669515609741},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22131207585334778},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0863429605960846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201308250427246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7270452976226807},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7156308889389038},{"id":"https://openalex.org/C106930687","wikidata":"https://www.wikidata.org/wiki/Q976327","display_name":"Romanization","level":2,"score":0.7154442071914673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6475445032119751},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.6366615295410156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5070037841796875},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.45144954323768616},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.44509726762771606},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.44365739822387695},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.4385858178138733},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.42031192779541016},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.3187669515609741},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22131207585334778},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0863429605960846},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2941161","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2941161","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835016.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:18dcc3df450a46d08fb96d5139767fb6","is_oa":true,"landing_page_url":"https://doaj.org/article/18dcc3df450a46d08fb96d5139767fb6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 133122-133135 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2941161","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2941161","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08835016.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2876290014","display_name":null,"funder_award_id":"61876190","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7247219692","display_name":null,"funder_award_id":"61802120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972978035.pdf","grobid_xml":"https://content.openalex.org/works/W2972978035.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W11511616","https://openalex.org/W201141796","https://openalex.org/W222053410","https://openalex.org/W1560797130","https://openalex.org/W1831974383","https://openalex.org/W1905522558","https://openalex.org/W2001948479","https://openalex.org/W2006617528","https://openalex.org/W2033599040","https://openalex.org/W2113788796","https://openalex.org/W2118434577","https://openalex.org/W2123442489","https://openalex.org/W2124807415","https://openalex.org/W2133564696","https://openalex.org/W2141440284","https://openalex.org/W2153903004","https://openalex.org/W2156985047","https://openalex.org/W2164394329","https://openalex.org/W2169200297","https://openalex.org/W2197485278","https://openalex.org/W2250816155","https://openalex.org/W2251092354","https://openalex.org/W2471147443","https://openalex.org/W2527845440","https://openalex.org/W2529089661","https://openalex.org/W2572474373","https://openalex.org/W2573197213","https://openalex.org/W2577335011","https://openalex.org/W2594229957","https://openalex.org/W2605717780","https://openalex.org/W2624461416","https://openalex.org/W2773493195","https://openalex.org/W2804732445","https://openalex.org/W2805411799","https://openalex.org/W2902009742","https://openalex.org/W2910527610","https://openalex.org/W2911189325","https://openalex.org/W2944198262","https://openalex.org/W2962724530","https://openalex.org/W2962784628","https://openalex.org/W2963324947","https://openalex.org/W2963641561","https://openalex.org/W2963876447","https://openalex.org/W2963919854","https://openalex.org/W2963937700","https://openalex.org/W3099668342","https://openalex.org/W3100096019","https://openalex.org/W4289375695","https://openalex.org/W4293863842","https://openalex.org/W6600454326","https://openalex.org/W6608792757","https://openalex.org/W6638575559","https://openalex.org/W6638827026","https://openalex.org/W6639825529","https://openalex.org/W6677129709","https://openalex.org/W6679434410","https://openalex.org/W6680768788","https://openalex.org/W6684503276","https://openalex.org/W6691525129","https://openalex.org/W6691735483","https://openalex.org/W6715182511","https://openalex.org/W6731744468","https://openalex.org/W6731999184","https://openalex.org/W6732146531","https://openalex.org/W6755330623"],"related_works":["https://openalex.org/W3153459181","https://openalex.org/W4389731935","https://openalex.org/W4402657567","https://openalex.org/W4377080406","https://openalex.org/W2808928361","https://openalex.org/W2395524355","https://openalex.org/W4387031027","https://openalex.org/W922362645","https://openalex.org/W4297195154","https://openalex.org/W4386901694"],"abstract_inverted_index":{"Morphologically":[0],"rich":[1],"and":[2,25,84,111,151,183,202],"complex":[3],"languages":[4,80],"such":[5,67,87],"as":[6,59,68,88,168],"Arabic,":[7,89],"pose":[8],"a":[9,48,127,239],"major":[10],"challenge":[11],"to":[12,18,30,39,73,125,134],"neural":[13],"machine":[14],"translation":[15,104,190,206],"(NMT)":[16],"due":[17],"the":[19,26,75,90,108,113,120,139,153,193,199,205,219,235],"large":[20],"number":[21],"of":[22,28,61,116,141,238],"rare":[23,53],"words":[24,42,54],"inability":[27],"NMT":[29,44,145,174,220],"translate":[31],"them.":[32],"Unknown":[33],"word":[34],"(UNK)":[35],"symbols":[36],"are":[37],"used":[38],"represent":[40],"out-of-vocabulary":[41],"because":[43],"typically":[45],"operates":[46],"with":[47,81,155,176],"fixed":[49],"vocabulary":[50],"size.":[51],"These":[52],"can":[55,196],"be":[56],"effectively":[57,197],"encoded":[58],"sequences":[60],"subword":[62,135],"units":[63],"by":[64],"using":[65],"algorithms,":[66],"byte":[69],"pair":[70],"encoding":[71],"(BPE),":[72],"tackle":[74,198],"UNK":[76,109,200],"problem.":[77],"However,":[78],"for":[79,103,172,208,234],"highly":[82],"inflected":[83],"morphological":[85],"variations,":[86],"aforementioned":[91],"method":[92],"has":[93],"its":[94,247],"own":[95],"limitations":[96],"that":[97,130,192],"make":[98],"it":[99],"not":[100],"effective":[101],"enough":[102],"quality.":[105],"To":[106],"alleviate":[107],"problem":[110,201],"address":[112],"inconvenient":[114],"behavior":[115],"BPE":[117],"when":[118],"translating":[119],"Arabic":[121,132,160,167],"language,":[122],"we":[123,164,229],"propose":[124,231],"utilize":[126],"romanization":[128],"system":[129,221],"converts":[131],"scripts":[133],"units.":[136],"We":[137],"investigate":[138],"effect":[140],"our":[142,227],"approach":[143],"on":[144,158,188,217,222],"performance":[146],"under":[147],"various":[148],"segmentation":[149],"scenarios":[150],"compare":[152],"results":[154],"systems":[156],"trained":[157],"original":[159],"form.":[161],"In":[162],"addition,":[163],"integrate":[165],"Romanized":[166],"an":[169],"input":[170],"factor":[171],"Arabic-sourced":[173,209],"compared":[175],"well-known":[177],"factors,":[178],"namely,":[179],"lemma,":[180],"part-of-speech":[181],"tags,":[182],"morph":[184],"features.":[185],"Extensive":[186],"experiments":[187,212],"Arabic-Chinese":[189],"demonstrate":[191],"proposed":[194],"approaches":[195],"significantly":[203],"improve":[204],"quality":[207],"translation.":[210,224],"Additional":[211],"in":[213,244],"this":[214],"study":[215],"focus":[216],"developing":[218],"Chinese-Arabic":[223],"Before":[225],"implementing":[226],"experiments,":[228],"first":[230],"standard":[232],"criteria":[233],"data":[236],"filtering":[237,245],"parallel":[240],"corpus,":[241],"which":[242],"helps":[243],"out":[246],"noise.":[248]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-09-19T00:00:00"}
