{"id":"https://openalex.org/W2756999401","doi":"https://doi.org/10.18653/v1/w17-4101","title":"Character and Subword-Based Word Representation for Neural Language Modeling Prediction","display_name":"Character and Subword-Based Word Representation for Neural Language Modeling Prediction","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2756999401","doi":"https://doi.org/10.18653/v1/w17-4101","mag":"2756999401"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-4101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4101","pdf_url":"https://www.aclweb.org/anthology/W17-4101.pdf","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 First Workshop on Subword and Character Level Models in NLP","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-4101.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055866824","display_name":"Matthieu Labeau","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Matthieu Labeau","raw_affiliation_strings":["LIMSI-CNRS / Orsay, France","LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS / Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051652099","display_name":"Alexandre Allauzen","orcid":"https://orcid.org/0000-0002-8627-1965"},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexandre Allauzen","raw_affiliation_strings":["LIMSI-CNRS / Orsay, France","LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS / Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I102197404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055866824"],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":1.6596,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88258022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9901999831199646,"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/word","display_name":"Word (group theory)","score":0.7979800701141357},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7843077182769775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7787362337112427},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7094777822494507},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6757831573486328},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6609222888946533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6070734262466431},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5926594734191895},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5189526081085205},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4530770480632782},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.4301333427429199},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4251164197921753},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2520383298397064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11692684888839722}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7979800701141357},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7843077182769775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787362337112427},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7094777822494507},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6757831573486328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6609222888946533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6070734262466431},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5926594734191895},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5189526081085205},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4530770480632782},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.4301333427429199},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4251164197921753},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2520383298397064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11692684888839722},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w17-4101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4101","pdf_url":"https://www.aclweb.org/anthology/W17-4101.pdf","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 First Workshop on Subword and Character Level Models in NLP","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02912377v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02912377","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the First Workshop on Subword and Character Level Models in NLP, Sep 2017, Copenhagen, Denmark. pp.1-13, ⟨10.18653/v1/W17-4101⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-4101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4101","pdf_url":"https://www.aclweb.org/anthology/W17-4101.pdf","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 First Workshop on Subword and Character Level Models in NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8884546066","display_name":"QT21: Quality Translation 21","funder_award_id":"645452","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2756999401.pdf","grobid_xml":"https://content.openalex.org/works/W2756999401.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W179875071","https://openalex.org/W196214544","https://openalex.org/W1483912251","https://openalex.org/W1505680913","https://openalex.org/W1522301498","https://openalex.org/W1566256432","https://openalex.org/W1589170661","https://openalex.org/W1860935423","https://openalex.org/W1899794420","https://openalex.org/W1917350224","https://openalex.org/W1938755728","https://openalex.org/W1970689298","https://openalex.org/W2032942114","https://openalex.org/W2040711288","https://openalex.org/W2056250865","https://openalex.org/W2064675550","https://openalex.org/W2100068632","https://openalex.org/W2100664567","https://openalex.org/W2101609803","https://openalex.org/W2120861206","https://openalex.org/W2131462252","https://openalex.org/W2133564696","https://openalex.org/W2138204974","https://openalex.org/W2142377809","https://openalex.org/W2143719855","https://openalex.org/W2152808281","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2159505618","https://openalex.org/W2175585630","https://openalex.org/W2250741237","https://openalex.org/W2251012068","https://openalex.org/W2251098065","https://openalex.org/W2251648400","https://openalex.org/W2251682575","https://openalex.org/W2259472270","https://openalex.org/W2463895987","https://openalex.org/W2493916176","https://openalex.org/W2507731975","https://openalex.org/W2585253991","https://openalex.org/W2611767671","https://openalex.org/W2740646860","https://openalex.org/W2949810612","https://openalex.org/W2950621961","https://openalex.org/W2951559648","https://openalex.org/W2952230511","https://openalex.org/W2962732637","https://openalex.org/W2962819663","https://openalex.org/W2962902328","https://openalex.org/W2963022149","https://openalex.org/W2963099225","https://openalex.org/W2963208801","https://openalex.org/W2963932686","https://openalex.org/W2963965928","https://openalex.org/W2964090065","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W1485297680","https://openalex.org/W2782410293","https://openalex.org/W305958151","https://openalex.org/W2724504120","https://openalex.org/W4360856886","https://openalex.org/W2614400517","https://openalex.org/W4378675964","https://openalex.org/W578757760","https://openalex.org/W1997182898","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Most":[0],"of":[1,8,48,55,116,123],"neural":[2,69],"language":[3,70],"models":[4],"use":[5],"different":[6,84],"kinds":[7],"embeddings":[9,15,110,132],"for":[10,68],"word":[11,14,21,36,106],"prediction.":[12,49],"While":[13],"can":[16,111],"be":[17],"associated":[18],"to":[19,41,64,128],"each":[20],"in":[22],"the":[23,43,46,53,92,104,114,117,121,124,130],"vocabulary":[24],"or":[25],"derived":[26],"from":[27],"characters":[28],"as":[29,31],"well":[30],"factored":[32,61],"morphological":[33,62],"decomposition,":[34],"these":[35],"representations":[37,67,107],"are":[38],"mainly":[39],"used":[40],"parametrize":[42],"input,":[44],"i.e.":[45],"context":[47],"This":[50],"work":[51],"investigates":[52],"effect":[54],"using":[56],"subword":[57],"units":[58],"(character":[59],"and":[60,86],"decomposition)":[63],"build":[65],"output":[66,87,105,125],"modeling.":[71],"We":[72],"present":[73],"a":[74,79],"case":[75],"study":[76],"on":[77],"Czech,":[78],"morphologically-rich":[80],"language,":[81],"experimenting":[82],"with":[83,91,108],"input":[85],"representations.":[88],"When":[89],"working":[90],"full":[93],"training":[94],"vocabulary,":[95],"despite":[96],"unstable":[97],"training,":[98],"our":[99],"experiments":[100],"show":[101],"that":[102],"augmenting":[103],"character-based":[109,131],"significantly":[112],"improve":[113],"performance":[115],"model.":[118],"Moreover,":[119],"reducing":[120],"size":[122],"look-up":[126],"table,":[127],"let":[129],"represent":[133],"rare":[134],"words,":[135],"brings":[136],"further":[137],"improvement.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}