{"id":"https://openalex.org/W3135427360","doi":"https://doi.org/10.1162/tacl_a_00448","title":"<scp>Canine</scp>: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","display_name":"<scp>Canine</scp>: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3135427360","doi":"https://doi.org/10.1162/tacl_a_00448","mag":"3135427360"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00448","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00448","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00448/1985933/tacl_a_00448.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00448/1985933/tacl_a_00448.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112226713","display_name":"Jonathan H. Clark","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jonathan H. Clark","raw_affiliation_strings":["Google Research, USA. jhclark@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, USA. jhclark@google.com","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087636608","display_name":"Dan Garrette","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dan Garrette","raw_affiliation_strings":["Google Research, USA. dhgarrette@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, USA. dhgarrette@google.com","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086294822","display_name":"Iulia Turc","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Iulia Turc","raw_affiliation_strings":["Google Research, USA. iuliaturc@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, USA. iuliaturc@google.com","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002499277","display_name":"John Wieting","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Wieting","raw_affiliation_strings":["Google Research, USA. jwieting@google.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research, USA. jwieting@google.com","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002499277","https://openalex.org/A5086294822","https://openalex.org/A5087636608","https://openalex.org/A5112226713"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":13.0397,"has_fulltext":true,"cited_by_count":119,"citation_normalized_percentile":{"value":0.98995416,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"73","last_page":"91"},"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8625154495239258},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.8056914806365967},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6654927134513855},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.6146589517593384},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5586444735527039},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5431016087532043},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5248075723648071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5166871547698975},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.470463365316391},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46753451228141785},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4206567704677582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39971300959587097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8625154495239258},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.8056914806365967},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6654927134513855},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.6146589517593384},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5586444735527039},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5431016087532043},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5248075723648071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5166871547698975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.470463365316391},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46753451228141785},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4206567704677582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39971300959587097},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/tacl_a_00448","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00448","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00448/1985933/tacl_a_00448.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2103.06874","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.06874","pdf_url":"https://arxiv.org/pdf/2103.06874","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:8bb4289de652433fb4a4106ac4a592c2","is_oa":true,"landing_page_url":"https://doaj.org/article/8bb4289de652433fb4a4106ac4a592c2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 10 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00448","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00448","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00448/1985933/tacl_a_00448.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135427360.pdf","grobid_xml":"https://content.openalex.org/works/W3135427360.grobid-xml"},"referenced_works_count":124,"referenced_works":["https://openalex.org/W196214544","https://openalex.org/W588654549","https://openalex.org/W1810943226","https://openalex.org/W1938755728","https://openalex.org/W2136189984","https://openalex.org/W2144578941","https://openalex.org/W2168199177","https://openalex.org/W2170240176","https://openalex.org/W2463895987","https://openalex.org/W2493916176","https://openalex.org/W2510842514","https://openalex.org/W2525778437","https://openalex.org/W2531207078","https://openalex.org/W2606347107","https://openalex.org/W2611767671","https://openalex.org/W2727642071","https://openalex.org/W2743935014","https://openalex.org/W2751674858","https://openalex.org/W2788760202","https://openalex.org/W2804639187","https://openalex.org/W2880875857","https://openalex.org/W2883158411","https://openalex.org/W2889191148","https://openalex.org/W2889474778","https://openalex.org/W2889775767","https://openalex.org/W2890887452","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2915429162","https://openalex.org/W2945785363","https://openalex.org/W2946417913","https://openalex.org/W2947415936","https://openalex.org/W2951559648","https://openalex.org/W2951815953","https://openalex.org/W2952087486","https://openalex.org/W2952125979","https://openalex.org/W2952487930","https://openalex.org/W2952638691","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2962943936","https://openalex.org/W2963012544","https://openalex.org/W2963022149","https://openalex.org/W2963088785","https://openalex.org/W2963099225","https://openalex.org/W2963208801","https://openalex.org/W2963250244","https://openalex.org/W2963324947","https://openalex.org/W2963341956","https://openalex.org/W2963357986","https://openalex.org/W2963403868","https://openalex.org/W2963421945","https://openalex.org/W2963735467","https://openalex.org/W2963831883","https://openalex.org/W2963899393","https://openalex.org/W2963979492","https://openalex.org/W2970049541","https://openalex.org/W2970458645","https://openalex.org/W2970748231","https://openalex.org/W2972369460","https://openalex.org/W2995435108","https://openalex.org/W2999168658","https://openalex.org/W3011279327","https://openalex.org/W3016697633","https://openalex.org/W3023911605","https://openalex.org/W3030045039","https://openalex.org/W3033188311","https://openalex.org/W3034469191","https://openalex.org/W3035207248","https://openalex.org/W3035390927","https://openalex.org/W3045462440","https://openalex.org/W3045733172","https://openalex.org/W3081031588","https://openalex.org/W3082274269","https://openalex.org/W3091156754","https://openalex.org/W3093517588","https://openalex.org/W3094306499","https://openalex.org/W3098466758","https://openalex.org/W3098903812","https://openalex.org/W3101140821","https://openalex.org/W3101278968","https://openalex.org/W3102892879","https://openalex.org/W3103699753","https://openalex.org/W3105190698","https://openalex.org/W3105238007","https://openalex.org/W3115462295","https://openalex.org/W3123615524","https://openalex.org/W3139100866","https://openalex.org/W3166790124","https://openalex.org/W3169483174","https://openalex.org/W3177365697","https://openalex.org/W3207937903","https://openalex.org/W4210462185","https://openalex.org/W4287633380","https://openalex.org/W4287704453","https://openalex.org/W4287775202","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4299548129","https://openalex.org/W4309793872","https://openalex.org/W4385245566","https://openalex.org/W6607974698","https://openalex.org/W6617363653","https://openalex.org/W6638273328","https://openalex.org/W6684702499","https://openalex.org/W6685053522","https://openalex.org/W6725939724","https://openalex.org/W6736923733","https://openalex.org/W6739901393","https://openalex.org/W6742672929","https://openalex.org/W6744166606","https://openalex.org/W6752788575","https://openalex.org/W6755207826","https://openalex.org/W6759455113","https://openalex.org/W6762287338","https://openalex.org/W6767155645","https://openalex.org/W6769627184","https://openalex.org/W6774862694","https://openalex.org/W6778280760","https://openalex.org/W6778883912","https://openalex.org/W6779089016","https://openalex.org/W6781533629","https://openalex.org/W6783944145","https://openalex.org/W6789317445"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W4378498597","https://openalex.org/W3101140821","https://openalex.org/W4287816966","https://openalex.org/W3015650676","https://openalex.org/W4389520445","https://openalex.org/W4387800341","https://openalex.org/W4388347706","https://openalex.org/W3213130020"],"abstract_inverted_index":{"Abstract":[0],"Pipelined":[1],"NLP":[2],"systems":[3],"have":[4],"largely":[5],"been":[6],"superseded":[7],"by":[8,131],"end-to-end":[9],"neural":[10,70],"modeling,":[11],"yet":[12],"nearly":[13],"all":[14,47],"commonly":[15],"used":[16],"models":[17],"still":[18],"require":[19],"an":[20],"explicit":[21,78],"tokenization":[22,26,79],"step.":[23],"While":[24],"recent":[25],"approaches":[27],"based":[28],"on":[29,75,89,134],"data-derived":[30],"subword":[31],"lexicons":[32],"are":[33,42],"less":[34],"brittle":[35],"than":[36],"manually":[37],"engineered":[38],"tokenizers,":[39],"these":[40],"techniques":[41],"not":[43],"equally":[44],"suited":[45],"to":[46,61],"languages,":[48],"and":[49,106],"the":[50,113],"use":[51,101],"of":[52],"any":[53],"fixed":[54],"vocabulary":[55],"may":[56],"limit":[57],"a":[58,69,82,96,118,127,137],"model\u2019s":[59],"ability":[60],"adapt.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"present":[67],"Canine,":[68],"encoder":[71],"that":[72,85],"operates":[73,86],"directly":[74,88],"character":[76],"sequences\u2014without":[77],"or":[80,91],"vocabulary\u2014and":[81],"pre-training":[83],"strategy":[84],"either":[87],"characters":[90],"optionally":[92],"uses":[93],"subwords":[94],"as":[95],"soft":[97],"inductive":[98],"bias.":[99],"To":[100],"its":[102],"finer-grained":[103],"input":[104,114],"effectively":[105],"efficiently,":[107],"Canine":[108,125],"combines":[109],"downsampling,":[110],"which":[111,122],"reduces":[112],"sequence":[115],"length,":[116],"with":[117],"deep":[119],"transformer":[120],"stack,":[121],"encodes":[123],"context.":[124],"outperforms":[126],"comparable":[128],"mBert":[129],"model":[130,144],"5.7":[132],"F1":[133],"TyDi":[135],"QA,":[136],"challenging":[138],"multilingual":[139],"benchmark,":[140],"despite":[141],"having":[142],"fewer":[143],"parameters.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":21}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2021-03-15T00:00:00"}