{"id":"https://openalex.org/W2531207078","doi":"https://doi.org/10.1162/tacl_a_00067","title":"Fully Character-Level Neural Machine Translation without Explicit Segmentation","display_name":"Fully Character-Level Neural Machine Translation without Explicit Segmentation","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2531207078","doi":"https://doi.org/10.1162/tacl_a_00067","mag":"2531207078"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00067","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00067","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00067","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":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00067","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059740024","display_name":"Jason D. Lee","orcid":"https://orcid.org/0000-0003-0064-7800"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["CH","US"],"is_corresponding":true,"raw_author_name":"Jason Lee","raw_affiliation_strings":["ETH Z\u00fcrich,","New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich,","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030087918","display_name":"Kyunghyun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyunghyun Cho","raw_affiliation_strings":["New York University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045413165","display_name":"Thomas Hofmann","orcid":"https://orcid.org/0000-0003-4057-7165"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Thomas Hofmann","raw_affiliation_strings":["ETH Z\u00fcrich,","New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich,","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059740024"],"corresponding_institution_ids":["https://openalex.org/I35440088","https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":55.9975,"has_fulltext":true,"cited_by_count":415,"citation_normalized_percentile":{"value":0.99871767,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"5","issue":null,"first_page":"365","last_page":"378"},"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":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9850999712944031,"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":0.8806465864181519},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8198803663253784},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.811267614364624},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7620366811752319},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6705589890480042},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.624133825302124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6202696561813354},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5527205467224121},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5505446195602417},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5194168090820312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5012383460998535},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49292659759521484},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48762646317481995},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45147600769996643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8806465864181519},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8198803663253784},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.811267614364624},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7620366811752319},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6705589890480042},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.624133825302124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6202696561813354},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5527205467224121},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5505446195602417},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5194168090820312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5012383460998535},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49292659759521484},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48762646317481995},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45147600769996643},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00067","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00067","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00067","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:doaj.org/article:4a7d3b43748549729b197a4f4a7e0c93","is_oa":false,"landing_page_url":"https://doaj.org/article/4a7d3b43748549729b197a4f4a7e0c93","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 5 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00067","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00067","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00067","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320315121","display_name":"Samsung Advanced Institute of Technology","ror":null},{"id":"https://openalex.org/F4320319918","display_name":"York University","ror":"https://ror.org/05fq50484"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2531207078.pdf","grobid_xml":"https://content.openalex.org/works/W2531207078.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1026270304","https://openalex.org/W1815076433","https://openalex.org/W1902237438","https://openalex.org/W1938755728","https://openalex.org/W2064675550","https://openalex.org/W2100664567","https://openalex.org/W2130942839","https://openalex.org/W2143539737","https://openalex.org/W2157331557","https://openalex.org/W2252335727","https://openalex.org/W2260677151","https://openalex.org/W2294699749","https://openalex.org/W2351252181","https://openalex.org/W2525778437","https://openalex.org/W2962732637","https://openalex.org/W2962784628","https://openalex.org/W2962801832","https://openalex.org/W2963012544","https://openalex.org/W2963208801","https://openalex.org/W2963247703","https://openalex.org/W2963251942","https://openalex.org/W2963324947","https://openalex.org/W2964007535","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W3103989898","https://openalex.org/W4287804464","https://openalex.org/W2728761353","https://openalex.org/W2883671469","https://openalex.org/W2794347674"],"abstract_inverted_index":{"Most":[0],"existing":[1],"machine":[2,22],"translation":[3,23,123,156],"systems":[4],"operate":[5],"at":[6,48,64],"the":[7,49,53,59,129,134,139,150,153,159,172],"level":[8],"of":[9,55,152,171],"words,":[10],"relying":[11],"on":[12,87,96,120,137,145,163],"explicit":[13],"segmentation":[14],"to":[15,32,51,61,68,107],"extract":[16],"tokens.":[17],"We":[18,40,100,142],"introduce":[19],"a":[20,28,33,42,65,79,84,109,118,121],"neural":[21],"(NMT)":[24],"model":[25,60,77,119],"that":[26,103,144,164],"maps":[27],"source":[29,56],"character":[30,35],"sequence":[31,36],"target":[34],"without":[37],"any":[38],"segmentation.":[39],"employ":[41],"character-level":[43,111,130,155],"convolutional":[44],"network":[45],"with":[46,83],"max-pooling":[47],"encoder":[50,86,112,131,136],"reduce":[52],"length":[54],"representation,":[57],"allowing":[58],"be":[62],"trained":[63,162],"speed":[66],"comparable":[67,94],"subword-level":[69,85,135],"models":[70,160],"while":[71],"capturing":[72],"local":[73],"regularities.":[74],"Our":[75],"character-to-character":[76],"outperforms":[78,133],"recently":[80],"proposed":[81],"baseline":[82],"WMT\u201915":[88],"DE-EN":[89],"and":[90,92,98,148,175],"CS-EN,":[91,146],"gives":[93],"performance":[95],"FI-EN":[97,147],"RU-EN.":[99],"then":[101],"demonstrate":[102],"it":[104],"is":[105],"possible":[106],"share":[108],"single":[110],"across":[113],"multiple":[114],"languages":[115],"by":[116],"training":[117],"many-to-one":[122],"task.":[124],"In":[125],"this":[126],"multilingual":[127,154],"setting,":[128],"significantly":[132],"all":[138],"language":[140,165],"pairs.":[141],"observe":[143],"RU-EN,":[149],"quality":[151],"even":[157],"surpasses":[158],"specifically":[161],"pair":[166],"alone,":[167],"both":[168],"in":[169],"terms":[170],"BLEU":[173],"score":[174],"human":[176],"judgment.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":56},{"year":2020,"cited_by_count":72},{"year":2019,"cited_by_count":67},{"year":2018,"cited_by_count":84},{"year":2017,"cited_by_count":46},{"year":2016,"cited_by_count":5}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}