{"id":"https://openalex.org/W2104554525","doi":"https://doi.org/10.5539/cis.v8n1p119","title":"Augmenting Performance of SMT Models by Deploying Fine Tokenization of the Text and Part-of-Speech Tag","display_name":"Augmenting Performance of SMT Models by Deploying Fine Tokenization of the Text and Part-of-Speech Tag","publication_year":2015,"publication_date":"2015-01-28","ids":{"openalex":"https://openalex.org/W2104554525","doi":"https://doi.org/10.5539/cis.v8n1p119","mag":"2104554525"},"language":"en","primary_location":{"id":"doi:10.5539/cis.v8n1p119","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v8n1p119","pdf_url":"http://www.ccsenet.org/journal/index.php/cis/article/download/44745/24372","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.ccsenet.org/journal/index.php/cis/article/download/44745/24372","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079342172","display_name":"Abraham Tesso Nedjo","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Abraham Tesso Nedjo","raw_affiliation_strings":["School of Computer Science and Technology, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, Liaoning Province, 116024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, Liaoning Province, 116024, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046871248","display_name":"Degen Huang","orcid":"https://orcid.org/0000-0002-8860-7805"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang Degen","raw_affiliation_strings":["School of Computer Science and Technology, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, Liaoning Province, 116024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, Liaoning Province, 116024, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05307545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"1","first_page":null,"last_page":null},"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":0.9990000128746033,"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/T13629","display_name":"Text Readability and Simplification","score":0.9656999707221985,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9138321876525879},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7925838828086853},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.749273955821991},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6889233589172363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6708675622940063},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6458710432052612},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.643796980381012},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.541670024394989},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.530296802520752},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4902058243751526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43355634808540344},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09949555993080139},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09177109599113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9138321876525879},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7925838828086853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.749273955821991},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6889233589172363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6708675622940063},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6458710432052612},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.643796980381012},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.541670024394989},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.530296802520752},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4902058243751526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43355634808540344},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09949555993080139},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09177109599113464},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5539/cis.v8n1p119","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v8n1p119","pdf_url":"http://www.ccsenet.org/journal/index.php/cis/article/download/44745/24372","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.669.1075","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.669.1075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ccsenet.org/journal/index.php/cis/article/download/44745/24372/","raw_type":"text"}],"best_oa_location":{"id":"doi:10.5539/cis.v8n1p119","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v8n1p119","pdf_url":"http://www.ccsenet.org/journal/index.php/cis/article/download/44745/24372","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1267140333","display_name":"\u8de8\u8bed\u8a00\u4fe1\u606f\u68c0\u7d22\u4e2d\u7684\u673a\u5668\u7ffb\u8bd1\u7814\u7a76","funder_award_id":"61173100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6183852862","display_name":"\u57fa\u4e8e\u7ffb\u8bd1\u5b66\u4e60\u548c\u6838\u65b9\u6cd5\u7684\u4e2d\u6587\u6a21\u7cca\u9650\u5236\u4fe1\u606f\u68c0\u6d4b\u7814\u7a76","funder_award_id":"61272375","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G873187850","display_name":"\u878d\u5408\u6307\u4ee3\u6d88\u89e3\u548c\u8fc1\u79fb\u5b66\u4e60\u7684\u86cb\u767d\u8d28\u4ea4\u4e92\u5173\u7cfb\u62bd\u53d6\u7684\u7814\u7a76","funder_award_id":"61173101","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2104554525.pdf","grobid_xml":"https://content.openalex.org/works/W2104554525.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W16967297","https://openalex.org/W589407005","https://openalex.org/W1916559533","https://openalex.org/W1970072068","https://openalex.org/W2006969979","https://openalex.org/W2017802499","https://openalex.org/W2032175749","https://openalex.org/W2119168550","https://openalex.org/W2124807415","https://openalex.org/W2132248251","https://openalex.org/W2139770225","https://openalex.org/W2144385980","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2161792612","https://openalex.org/W2164394329","https://openalex.org/W2170464899","https://openalex.org/W2184326353","https://openalex.org/W2314530273","https://openalex.org/W2407892396","https://openalex.org/W2595715041","https://openalex.org/W4242105955"],"related_works":["https://openalex.org/W2151197196","https://openalex.org/W2384400852","https://openalex.org/W2963259630","https://openalex.org/W2070920720","https://openalex.org/W2398549619","https://openalex.org/W1542743110","https://openalex.org/W2883671469","https://openalex.org/W4287760117","https://openalex.org/W3045818198","https://openalex.org/W3034697300"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3,171],"study":[4],"of":[5,42,56,80,107,112,143,156,178],"exploiting":[6],"the":[7,32,40,121,154,157,185],"languages\u2019":[8],"word":[9],"class":[10],"information":[11],"augmented":[12],"with":[13],"some":[14],"rule-based":[15],"processing":[16],"for":[17,31,83,148,184],"phrase-based":[18],"Statistical":[19],"Machine":[20],"Translation":[21],"(SMT).":[22],"In":[23,72,98],"statistical":[24],"machine":[25,130],"translation,":[26],"estimating":[27],"word-to-word":[28],"alignment":[29],"probabilities":[30],"translation":[33,131,162],"model":[34],"can":[35,68],"be":[36,69],"difficult":[37],"due":[38],"to":[39,119,182],"problem":[41,67],"sparse":[43],"data:":[44],"most":[45,53],"words":[46,108,113],"in":[47,88,161],"a":[48,54,59,138,175],"given":[49],"corpus":[50,142,159],"occur":[51],"at":[52],"handful":[55],"times.":[57],"With":[58],"highly":[60],"inflected":[61],"language":[62,90],"such":[63],"as":[64,180],"Oromo,":[65],"this":[66,99],"particularly":[70],"severe.":[71],"addition,":[73],"there":[74],"is":[75],"variant":[76],"nature":[77],"or":[78],"use":[79],"different":[81],"symbols":[82],"\u2018hudhaa\u2019":[84],"(the":[85],"diacritical":[86],"marker)":[87],"Oromo":[89,122],"which":[91],"intrudes":[92],"another":[93],"severe":[94],"data":[95,144],"sparsity":[96],"problem.":[97],"work,":[100],"we":[101],"show":[102],"that":[103],"using":[104],"fine":[105],"tokenization":[106],"considering":[109],"intra-word":[110],"behavior":[111],"consisting":[114],"hudhaa,":[115],"and":[116,124,152,163],"POS":[117],"tag":[118],"modify":[120],"input":[123],"see":[125],"how":[126],"it":[127],"improves":[128],"Oromo-English":[129],"system.":[132,187],"The":[133],"models":[134],"were":[135,166],"trained":[136],"on":[137],"very":[139],"small":[140],"parallel":[141,158],"set":[145],"(usually":[146],"unacceptable":[147],"normal":[149],"SMT":[150],"system)":[151],"also":[153],"quality":[155],"both":[160],"spelling":[164],"errors":[165],"not":[167],"so":[168],"good.":[169],"Yet,":[170],"final":[172],"system":[173],"achieves":[174],"BLEU":[176],"score":[177],"2.88,":[179],"compared":[181],"2.56":[183],"baseline":[186]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}