{"id":"https://openalex.org/W2952524414","doi":"https://doi.org/10.18653/v1/p19-1158","title":"Stochastic Tokenization with a Language Model for Neural Text Classification","display_name":"Stochastic Tokenization with a Language Model for Neural Text Classification","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952524414","doi":"https://doi.org/10.18653/v1/p19-1158","mag":"2952524414"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1158","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1158","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/p19-1158","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034042223","display_name":"Tatsuya Hiraoka","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tatsuya Hiraoka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063398043","display_name":"Hiroyuki Shindo","orcid":"https://orcid.org/0000-0003-1081-9194"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroyuki Shindo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072032804","display_name":"Y\u016bji Matsumoto","orcid":"https://orcid.org/0000-0003-4946-9574"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuji Matsumoto","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034042223"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4562,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91645653,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1620","last_page":"1629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9991999864578247,"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/lexical-analysis","display_name":"Lexical analysis","score":0.843660295009613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751078009605408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6529914140701294},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6340807676315308},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5540878176689148}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.843660295009613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751078009605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6529914140701294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6340807676315308},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5540878176689148}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/p19-1158","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1158","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:library.naist.jp:10061/13223","is_oa":false,"landing_page_url":"http://hdl.handle.net/10061/13223","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis or Dissertation"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1158","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1158","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1539673959","https://openalex.org/W1832693441","https://openalex.org/W1982498087","https://openalex.org/W2122228338","https://openalex.org/W2126377586","https://openalex.org/W2140991203","https://openalex.org/W2152775624","https://openalex.org/W2184342832","https://openalex.org/W2226734577","https://openalex.org/W2250473257","https://openalex.org/W2252215182","https://openalex.org/W2265846598","https://openalex.org/W2501941158","https://openalex.org/W2514588627","https://openalex.org/W2525332836","https://openalex.org/W2562607067","https://openalex.org/W2577986889","https://openalex.org/W2609370997","https://openalex.org/W2734062722","https://openalex.org/W2846971013","https://openalex.org/W2951672049","https://openalex.org/W2962784628","https://openalex.org/W2962904552","https://openalex.org/W2963012544","https://openalex.org/W2963250244","https://openalex.org/W2963626623","https://openalex.org/W2963979492","https://openalex.org/W2963997155","https://openalex.org/W2964121744","https://openalex.org/W2964352165"],"related_works":["https://openalex.org/W1690232763","https://openalex.org/W3107474891","https://openalex.org/W1563618553","https://openalex.org/W142374489","https://openalex.org/W2359001871","https://openalex.org/W2148757832","https://openalex.org/W2121178211","https://openalex.org/W1803932089","https://openalex.org/W61293283","https://openalex.org/W4320086032"],"abstract_inverted_index":{"For":[0],"unsegmented":[1],"languages":[2],"such":[3],"as":[4,138],"Japanese":[5],"and":[6,38,54,81,101,143],"Chinese,":[7],"tokenization":[8,80,96],"of":[9,19,129],"a":[10,13,31,75,91,98,139],"sentence":[11,120],"has":[12],"significant":[14],"impact":[15],"on":[16,135],"the":[17,59,63,67,109],"performance":[18,65,128,150],"text":[20,82,99,130,140],"classification.":[21,131],"Sentences":[22],"are":[23],"usually":[24],"segmented":[25,60],"with":[26,41],"words":[27],"or":[28,34],"subwords":[29],"by":[30],"morphological":[32],"analyzer":[33],"byte":[35],"pair":[36],"encoding":[37],"then":[39,102],"encoded":[40],"word":[42],"(or":[43],"subword)":[44],"representations":[45],"for":[46,66,94,118],"neural":[47],"networks.":[48],"However,":[49],"segmentation":[50,117],"is":[51,56],"potentially":[52],"ambiguous,":[53],"it":[55],"unclear":[57],"whether":[58],"tokens":[61],"achieve":[62],"best":[64],"target":[68],"task.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73,115],"propose":[74],"method":[76,147],"to":[77,84],"simultaneously":[78],"learn":[79],"classification":[83,141],"address":[85],"these":[86],"problems.":[87],"Our":[88],"model":[89,93,110],"incorporates":[90],"language":[92],"unsupervised":[95],"into":[97],"classifier":[100],"trains":[103],"both":[104],"models":[105],"simultaneously.":[106],"To":[107],"make":[108],"robust":[111],"against":[112],"infrequent":[113],"tokens,":[114],"sampled":[116],"each":[119],"stochastically":[121],"during":[122],"training,":[123],"which":[124],"resulted":[125],"in":[126],"improved":[127],"We":[132],"conducted":[133],"experiments":[134],"sentiment":[136],"analysis":[137],"task":[142],"show":[144],"that":[145],"our":[146],"achieves":[148],"better":[149],"than":[151],"previous":[152],"methods.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}