{"id":"https://openalex.org/W2493916176","doi":"https://doi.org/10.1162/tacl_a_00051","title":"Enriching Word Vectors with Subword Information","display_name":"Enriching Word Vectors with Subword Information","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2493916176","doi":"https://doi.org/10.1162/tacl_a_00051","mag":"2493916176"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00051","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00051","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00051","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_00051","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035420035","display_name":"Piotr Bojanowski","orcid":"https://orcid.org/0000-0001-8098-5900"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Piotr Bojanowski","raw_affiliation_strings":["Facebook AI Research,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research,","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069316249","display_name":"\u00c9douard Grave","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Edouard Grave","raw_affiliation_strings":["Facebook AI Research,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research,","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107859338","display_name":"Armand Joulin","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Armand Joulin","raw_affiliation_strings":["Facebook AI Research,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research,","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020917394","display_name":"Tom\u00e1\u0161 Mikolov","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Tomas Mikolov","raw_affiliation_strings":["Facebook AI Research,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research,","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020917394","https://openalex.org/A5035420035","https://openalex.org/A5069316249","https://openalex.org/A5107859338"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":801.2543,"has_fulltext":true,"cited_by_count":9724,"citation_normalized_percentile":{"value":0.99998194,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"5","issue":null,"first_page":"135","last_page":"146"},"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":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/T13629","display_name":"Text Readability and Simplification","score":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.8645756244659424},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.8440808653831482},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7708520889282227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.694340705871582},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6456218957901001},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6269466876983643},{"id":"https://openalex.org/keywords/analogy","display_name":"Analogy","score":0.5627533793449402},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5381990075111389},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4536324441432953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32654109597206116},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20102691650390625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08098536729812622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8645756244659424},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8440808653831482},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7708520889282227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.694340705871582},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6456218957901001},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6269466876983643},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.5627533793449402},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5381990075111389},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4536324441432953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32654109597206116},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20102691650390625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08098536729812622},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00051","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00051","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00051","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:059037df735a40eabfbfe8e7f5931ad7","is_oa":false,"landing_page_url":"https://doaj.org/article/059037df735a40eabfbfe8e7f5931ad7","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_00051","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00051","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00051","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","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2493916176.pdf","grobid_xml":"https://content.openalex.org/works/W2493916176.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W196214544","https://openalex.org/W1505680913","https://openalex.org/W1572401739","https://openalex.org/W1633328346","https://openalex.org/W1662133657","https://openalex.org/W1810943226","https://openalex.org/W1860935423","https://openalex.org/W1899794420","https://openalex.org/W1938755728","https://openalex.org/W1964209958","https://openalex.org/W1974643919","https://openalex.org/W1981617416","https://openalex.org/W2040711288","https://openalex.org/W2042232391","https://openalex.org/W2067438047","https://openalex.org/W2078483536","https://openalex.org/W2101609803","https://openalex.org/W2102131037","https://openalex.org/W2117130368","https://openalex.org/W2128870637","https://openalex.org/W2129773034","https://openalex.org/W2142377809","https://openalex.org/W2147152072","https://openalex.org/W2149671658","https://openalex.org/W2153579005","https://openalex.org/W2155033295","https://openalex.org/W2167419393","https://openalex.org/W2176796957","https://openalex.org/W2250741237","https://openalex.org/W2251012068","https://openalex.org/W2251176673","https://openalex.org/W2251592786","https://openalex.org/W2252215182","https://openalex.org/W2294970769","https://openalex.org/W2295097532","https://openalex.org/W2394700483","https://openalex.org/W2408387521","https://openalex.org/W2463895987","https://openalex.org/W2501208544","https://openalex.org/W2588446908","https://openalex.org/W2882319491","https://openalex.org/W2950577311","https://openalex.org/W2951781666","https://openalex.org/W2962784628","https://openalex.org/W2963012544","https://openalex.org/W2963324947","https://openalex.org/W2964005834"],"related_works":["https://openalex.org/W2392206215","https://openalex.org/W2365201483","https://openalex.org/W2355561779","https://openalex.org/W2352407775","https://openalex.org/W108701362","https://openalex.org/W2186567693","https://openalex.org/W2469799552","https://openalex.org/W2768582344","https://openalex.org/W2803176955","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Continuous":[0],"word":[1,64,108,123,131,142],"representations,":[2,143],"trained":[3],"on":[4,58,99,125,130,152],"large":[5,43,100],"unlabeled":[6],"corpora":[7,101],"are":[8],"useful":[9],"for":[10,40,110],"many":[11,46],"natural":[12],"language":[13],"processing":[14],"tasks.":[15,135,154],"Popular":[16],"models":[17,98],"that":[18,112,146],"learn":[19],"such":[20],"representations":[21,109,124],"ignore":[22],"the":[23,59,86,117],"morphology":[24],"of":[25,70,88],"words,":[26],"by":[27],"assigning":[28],"a":[29,37,54,68],"distinct":[30],"vector":[31,74],"to":[32,78,96,106,138],"each":[33,63,79],"word.":[34],"This":[35],"is":[36,65,76,93],"limitation,":[38],"especially":[39],"languages":[41],"with":[42],"vocabularies":[44],"and":[45,103,133],"rare":[47],"words.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,144],"propose":[53],"new":[55],"approach":[56],"based":[57],"skipgram":[60],"model,":[61],"where":[62],"represented":[66,84],"as":[67,85],"bag":[69],"character":[71,80],"n-grams.":[72],"A":[73],"representation":[75],"associated":[77],"n-gram;":[81],"words":[82,111],"being":[83],"sum":[87],"these":[89,153],"representations.":[90],"Our":[91],"method":[92],"fast,":[94],"allowing":[95],"train":[97],"quickly":[102],"allows":[104],"us":[105],"compute":[107],"did":[113],"not":[114],"appear":[115],"in":[116],"training":[118],"data.":[119],"We":[120],"evaluate":[121],"our":[122,147],"nine":[126],"different":[127],"languages,":[128],"both":[129],"similarity":[132],"analogy":[134],"By":[136],"comparing":[137],"recently":[139],"proposed":[140],"morphological":[141],"show":[145],"vectors":[148],"achieve":[149],"state-of-the-art":[150],"performance":[151]},"counts_by_year":[{"year":2026,"cited_by_count":155},{"year":2025,"cited_by_count":674},{"year":2024,"cited_by_count":793},{"year":2023,"cited_by_count":1203},{"year":2022,"cited_by_count":1281},{"year":2021,"cited_by_count":1759},{"year":2020,"cited_by_count":1669},{"year":2019,"cited_by_count":1349},{"year":2018,"cited_by_count":676},{"year":2017,"cited_by_count":146},{"year":2016,"cited_by_count":17},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-13T08:25:38.343686","created_date":"2025-10-10T00:00:00"}