{"id":"https://openalex.org/W4381247876","doi":"https://doi.org/10.48550/arxiv.2306.09572","title":"How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese","display_name":"How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese","publication_year":2023,"publication_date":"2023-06-16","ids":{"openalex":"https://openalex.org/W4381247876","doi":"https://doi.org/10.48550/arxiv.2306.09572"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2306.09572","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.09572","pdf_url":"https://arxiv.org/pdf/2306.09572","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.09572","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107008363","display_name":"Takuro Fujii","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fujii, Takuro","raw_affiliation_strings":["Yokohama National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yokohama National University","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109628215","display_name":"Koki Shibata","orcid":"https://orcid.org/0009-0004-9955-1028","observed_orcids":["https://orcid.org/0009-0004-9955-1028"]},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shibata, Koki","raw_affiliation_strings":["University of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053723731","display_name":"Atsuki Yamaguchi","orcid":"https://orcid.org/0000-0001-8327-7598","observed_orcids":["https://orcid.org/0000-0001-8327-7598"]},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yamaguchi, Atsuki","raw_affiliation_strings":["Yokohama National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yokohama National University","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070924297","display_name":"Terufumi Morishita","orcid":"https://orcid.org/0009-0009-0753-587X","observed_orcids":["https://orcid.org/0009-0009-0753-587X"]},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Morishita, Terufumi","raw_affiliation_strings":["Hitachi, Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038587308","display_name":"Yasuhiro Sogawa","orcid":"https://orcid.org/0009-0007-0378-1614","observed_orcids":["https://orcid.org/0009-0007-0378-1614"]},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sogawa, Yasuhiro","raw_affiliation_strings":["University of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.6942999958992004,"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":0.6942999958992004,"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":0.29789999127388,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.000699999975040555,"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/tokenizers","display_name":"tokenizers","score":0.7020000219345093},{"id":"https://openalex.org/keywords/japanese","display_name":"Japanese","score":0.8899999856948853},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.8069999814033508},{"id":"https://openalex.org/keywords/subword-tokenization","display_name":"subword tokenization","score":0.9940000176429749},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.828000009059906},{"id":"https://openalex.org/keywords/downstream-task-performance","display_name":"downstream task performance","score":0.6510000228881836},{"id":"https://openalex.org/keywords/byte-pair-encoding","display_name":"byte pair encoding","score":0.6830000281333923},{"id":"https://openalex.org/keywords/wordpiece","display_name":"WordPiece","score":0.7950000166893005},{"id":"https://openalex.org/keywords/unigrams","display_name":"unigrams","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.9010002017021179},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.8366929292678833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7959145903587341},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.6878817081451416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5804128646850586},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.48234671354293823},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4604222774505615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.416654109954834},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20480266213417053},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14236319065093994},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2306.09572","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.09572","pdf_url":"https://arxiv.org/pdf/2306.09572","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2306.09572","doi":"https://doi.org/10.48550/arxiv.2306.09572","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.09572","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.09572","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.09572","pdf_url":"https://arxiv.org/pdf/2306.09572","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381247876.pdf","grobid_xml":"https://content.openalex.org/works/W4381247876.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1583765404","https://openalex.org/W4214653257","https://openalex.org/W121858127","https://openalex.org/W2775143306","https://openalex.org/W4289329995","https://openalex.org/W2373574911","https://openalex.org/W2046727832","https://openalex.org/W4247895841","https://openalex.org/W2055438207","https://openalex.org/W4381247876"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,8,79,120],"effect":[4],"of":[5,11,40,55,70,86,119,122],"tokenizers":[6],"on":[7,82],"downstream":[9,80,93],"performance":[10,81],"pretrained":[12],"language":[13],"models":[14],"(PLMs)":[15],"in":[16],"scriptio":[17],"continua":[18],"languages":[19,37],"where":[20],"no":[21],"explicit":[22],"spaces":[23],"exist":[24],"between":[25],"words,":[26],"using":[27,75],"Japanese":[28],"as":[29,114],"a":[30,41,45,52,73,83,96,115],"case":[31],"study.":[32],"The":[33],"tokenizer":[34],"for":[35],"such":[36],"often":[38],"consists":[39],"morphological":[42,99],"analyzer":[43],"and":[44,77,101],"subword":[46,116],"tokenizer,":[47,117],"requiring":[48],"us":[49],"to":[50,106],"conduct":[51],"comprehensive":[53],"study":[54],"all":[56],"possible":[57],"pairs.":[58],"However,":[59],"previous":[60],"studies":[61],"lack":[62],"this":[63],"comprehensiveness.":[64],"We":[65],"therefore":[66],"train":[67],"extensive":[68],"sets":[69],"tokenizers,":[71],"build":[72],"PLM":[74],"each,":[76],"measure":[78],"wide":[84],"range":[85],"tasks.":[87],"Our":[88],"results":[89],"demonstrate":[90],"that":[91,102],"each":[92],"task":[94],"has":[95],"different":[97],"optimal":[98],"analyzer,":[100],"it":[103],"is":[104],"better":[105],"use":[107],"Byte-Pair-Encoding":[108],"or":[109],"Unigram":[110],"rather":[111],"than":[112],"WordPiece":[113],"regardless":[118],"type":[121],"task.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}