{"id":"https://openalex.org/W2550342806","doi":"https://doi.org/10.1109/ialp.2016.7875952","title":"Japanese orthographical normalization does not work for statistical machine translation","display_name":"Japanese orthographical normalization does not work for statistical machine translation","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2550342806","doi":"https://doi.org/10.1109/ialp.2016.7875952","mag":"2550342806"},"language":"en","primary_location":{"id":"doi:10.1109/ialp.2016.7875952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2016.7875952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Asian Language Processing (IALP)","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/A5109500211","display_name":"Kazuhide Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]},{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhide Yamamoto","raw_affiliation_strings":["Nagaoka University of Technology, Nagaoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Nagaoka, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042574784","display_name":"Takahashi Kanji","orcid":null},"institutions":[{"id":"https://openalex.org/I119806805","display_name":"Nagaoka University","ror":"https://ror.org/02rcadd38","country_code":"JP","type":"education","lineage":["https://openalex.org/I119806805"]},{"id":"https://openalex.org/I85922643","display_name":"Nagaoka University of Technology","ror":"https://ror.org/00ys1hz88","country_code":"JP","type":"education","lineage":["https://openalex.org/I85922643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kanji Takahashi","raw_affiliation_strings":["Nagaoka University of Technology, Nagaoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagaoka University of Technology, Nagaoka, Japan","institution_ids":["https://openalex.org/I119806805","https://openalex.org/I85922643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3883,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61864764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"2004","issue":null,"first_page":"133","last_page":"136"},"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":0.9983000159263611,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9516000151634216,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/perplexity","display_name":"Perplexity","score":0.8672852516174316},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8487707376480103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7205439805984497},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6881928443908691},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6177281737327576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6156041026115417},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5334193110466003},{"id":"https://openalex.org/keywords/orthography","display_name":"Orthography","score":0.4978659152984619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4357716143131256},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.22376546263694763},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19684037566184998}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8672852516174316},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8487707376480103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7205439805984497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6881928443908691},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6177281737327576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6156041026115417},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5334193110466003},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.4978659152984619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4357716143131256},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.22376546263694763},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19684037566184998},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp.2016.7875952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2016.7875952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2134800885","https://openalex.org/W2135598948","https://openalex.org/W2145685230","https://openalex.org/W2146574666","https://openalex.org/W2153508793","https://openalex.org/W2156985047","https://openalex.org/W2250293945","https://openalex.org/W2251615219","https://openalex.org/W2341555833","https://openalex.org/W2595715041","https://openalex.org/W6679760120","https://openalex.org/W6679855610","https://openalex.org/W6682508316","https://openalex.org/W6691391470","https://openalex.org/W6691482610","https://openalex.org/W6734621010","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2376415519","https://openalex.org/W1601381279","https://openalex.org/W4294769427","https://openalex.org/W4225667838","https://openalex.org/W1895908943","https://openalex.org/W4281893144","https://openalex.org/W2374747083","https://openalex.org/W4386270999","https://openalex.org/W4399378742","https://openalex.org/W4388254351"],"abstract_inverted_index":{"We":[0,87],"have":[1,28],"investigated":[2],"the":[3,51,74,82,89],"effect":[4],"of":[5,26,76,84],"normalizing":[6],"Japanese":[7,20],"orthographical":[8,33,48],"variants":[9],"into":[10],"a":[11,37],"uniform":[12],"orthography":[13],"on":[14],"statistical":[15],"machine":[16],"translation":[17,42],"(SMT)":[18],"between":[19],"and":[21,67,81],"English.":[22],"In":[23],"Japanese,":[24],"10%":[25],"words":[27],"reportedly":[29],"more":[30],"than":[31],"one":[32],"variants,":[34],"which":[35],"is":[36,58],"promising":[38],"fact":[39],"for":[40],"improving":[41],"quality":[43],"when":[44],"we":[45],"normalize":[46],"these":[47],"variants.":[49],"However,":[50],"results":[52],"show":[53],"that":[54,61],"SMT":[55],"with":[56],"normalization":[57,63,72],"equivalent":[59],"to":[60],"without":[62],"by":[64],"both":[65],"BLEU":[66],"RIBES":[68],"measurement,":[69],"even":[70],"though":[71],"reduces":[73],"size":[75],"language":[77],"models,":[78],"its":[79],"perplexity,":[80],"number":[83],"out-of-vocabulary":[85],"words.":[86],"discuss":[88],"potential":[90],"reasons":[91],"in":[92],"this":[93],"paper.":[94]},"counts_by_year":[{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}