{"id":"https://openalex.org/W4383533102","doi":"https://doi.org/10.1162/coli_a_00489","title":"Languages Through the Looking Glass of BPE Compression","display_name":"Languages Through the Looking Glass of BPE Compression","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4383533102","doi":"https://doi.org/10.1162/coli_a_00489"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00489","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00489","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1162/coli_a_00489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004693481","display_name":"Ximena Gutierrez-Vasques","orcid":"https://orcid.org/0000-0002-1486-2774"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ximena Gutierrez-Vasques","raw_affiliation_strings":["University of Z\u00fcrich, URPP Language and Space. ximena.gutierrezvasques@uzh.ch"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Z\u00fcrich, URPP Language and Space. ximena.gutierrezvasques@uzh.ch","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059804119","display_name":"Christian Bentz","orcid":"https://orcid.org/0000-0001-6570-9326"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bentz","raw_affiliation_strings":["University of T\u00fcbingen, Department of General Linguistics. chris@christianbentz.de"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, Department of General Linguistics. chris@christianbentz.de","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017310324","display_name":"Tanja Samard\u017ci\u0107","orcid":"https://orcid.org/0000-0001-6451-3946"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I3148377317","display_name":"Department of Space","ror":"https://ror.org/000kjq947","country_code":"IN","type":"government","lineage":["https://openalex.org/I3148377317"]}],"countries":["CH","IN"],"is_corresponding":false,"raw_author_name":"Tanja Samard\u017ei\u0107","raw_affiliation_strings":["University of Z\u00fcrich, URPP Language and Space, tanja.samardzic@uzh.ch","University of Z\u00fcrich, URPP Language and Space. tanja.samardzic@uzh.ch"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Z\u00fcrich, URPP Language and Space, tanja.samardzic@uzh.ch","institution_ids":["https://openalex.org/I3148377317"]},{"raw_affiliation_string":"University of Z\u00fcrich, URPP Language and Space. tanja.samardzic@uzh.ch","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7449,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86870071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"49","issue":"4","first_page":"943","last_page":"1001"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9957000017166138,"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":0.9941999912261963,"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":0.7881753444671631},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6241979598999023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6170510053634644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5726718902587891},{"id":"https://openalex.org/keywords/typology","display_name":"Typology","score":0.5377986431121826},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.4570569694042206},{"id":"https://openalex.org/keywords/linguistic-typology","display_name":"Linguistic typology","score":0.44153544306755066},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.38411927223205566},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.14228156208992004},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.11233317852020264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7881753444671631},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6241979598999023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6170510053634644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5726718902587891},{"id":"https://openalex.org/C75795011","wikidata":"https://www.wikidata.org/wiki/Q917904","display_name":"Typology","level":2,"score":0.5377986431121826},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.4570569694042206},{"id":"https://openalex.org/C1701360","wikidata":"https://www.wikidata.org/wiki/Q192625","display_name":"Linguistic typology","level":3,"score":0.44153544306755066},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38411927223205566},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.14228156208992004},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.11233317852020264},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00489","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00489","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:98e6ed18bf46466fbede358bdb69fddf","is_oa":true,"landing_page_url":"https://doaj.org/article/98e6ed18bf46466fbede358bdb69fddf","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":"Computational Linguistics, Vol 49, Iss 4 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00489","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00489","pdf_url":null,"source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":99,"referenced_works":["https://openalex.org/W54741546","https://openalex.org/W235168920","https://openalex.org/W382421368","https://openalex.org/W609568101","https://openalex.org/W645629140","https://openalex.org/W761671411","https://openalex.org/W799336573","https://openalex.org/W1534300969","https://openalex.org/W1579728765","https://openalex.org/W1580291322","https://openalex.org/W1586700795","https://openalex.org/W1820435534","https://openalex.org/W1970975451","https://openalex.org/W1979135380","https://openalex.org/W1987971958","https://openalex.org/W1992305141","https://openalex.org/W1993859479","https://openalex.org/W2029958307","https://openalex.org/W2030202387","https://openalex.org/W2031189361","https://openalex.org/W2034339630","https://openalex.org/W2036105087","https://openalex.org/W2041432114","https://openalex.org/W2054658115","https://openalex.org/W2074999873","https://openalex.org/W2095694743","https://openalex.org/W2101711363","https://openalex.org/W2107745473","https://openalex.org/W2117621558","https://openalex.org/W2118232585","https://openalex.org/W2121879602","https://openalex.org/W2152561112","https://openalex.org/W2155674569","https://openalex.org/W2160654481","https://openalex.org/W2482827422","https://openalex.org/W2488733983","https://openalex.org/W2520500861","https://openalex.org/W2600999069","https://openalex.org/W2739967986","https://openalex.org/W2773533135","https://openalex.org/W2807931239","https://openalex.org/W2810095012","https://openalex.org/W2901853295","https://openalex.org/W2905510703","https://openalex.org/W2905532018","https://openalex.org/W2924135799","https://openalex.org/W2948068983","https://openalex.org/W2949303037","https://openalex.org/W2950733326","https://openalex.org/W2952638691","https://openalex.org/W2953441691","https://openalex.org/W2962784628","https://openalex.org/W2963357986","https://openalex.org/W2963560568","https://openalex.org/W2963625579","https://openalex.org/W2963826397","https://openalex.org/W2963979492","https://openalex.org/W2971081948","https://openalex.org/W3009136574","https://openalex.org/W3100135685","https://openalex.org/W3100198908","https://openalex.org/W3101140821","https://openalex.org/W3105421296","https://openalex.org/W3135427360","https://openalex.org/W3153847883","https://openalex.org/W3154046803","https://openalex.org/W3173954987","https://openalex.org/W3178228406","https://openalex.org/W3197118322","https://openalex.org/W3213934211","https://openalex.org/W3214173179","https://openalex.org/W4213351608","https://openalex.org/W4220839792","https://openalex.org/W4223508017","https://openalex.org/W4230660597","https://openalex.org/W4232169983","https://openalex.org/W4232736940","https://openalex.org/W4235752266","https://openalex.org/W4239626706","https://openalex.org/W4239919747","https://openalex.org/W4280613849","https://openalex.org/W4285169952","https://openalex.org/W4285208773","https://openalex.org/W4287889583","https://openalex.org/W4385573174","https://openalex.org/W4385574278","https://openalex.org/W4393849379","https://openalex.org/W6601894380","https://openalex.org/W6630890903","https://openalex.org/W6635035540","https://openalex.org/W6691706656","https://openalex.org/W6700915612","https://openalex.org/W6714758027","https://openalex.org/W6732047649","https://openalex.org/W6734711280","https://openalex.org/W6754280311","https://openalex.org/W6755207826","https://openalex.org/W6810728803","https://openalex.org/W6821347270"],"related_works":["https://openalex.org/W2392601317","https://openalex.org/W2184642259","https://openalex.org/W582408390","https://openalex.org/W3177021845","https://openalex.org/W4252573619","https://openalex.org/W2490207774","https://openalex.org/W3083254433","https://openalex.org/W3175960268","https://openalex.org/W2367347531","https://openalex.org/W4384433011"],"abstract_inverted_index":{"Abstract":[0],"Byte-pair":[1],"encoding":[2],"(BPE)":[3],"is":[4,103,199],"widely":[5],"used":[6],"in":[7,27,155,180],"NLP":[8],"for":[9,17,106,115],"performing":[10],"subword":[11,171],"tokenization.":[12],"It":[13],"uncovers":[14],"redundant":[15],"patterns":[16,82,129,148],"compressing":[18],"the":[19,24,33,40,45,50,78,85,111,136,175],"data,":[20],"and":[21,70,74,208,230],"hence":[22],"alleviates":[23],"sparsity":[25],"problem":[26],"downstream":[28],"applications.":[29],"Subwords":[30],"discovered":[31],"during":[32],"first":[34],"merge":[35],"operations":[36],"tend":[37],"to":[38,131,135,164,168,185,202,227],"have":[39,56,84,186],"most":[41],"substantial":[42],"impact":[43,87],"on":[44,88,110],"compression":[46,89],"of":[47,53,80,93,128,177,206],"texts.":[48],"However,":[49],"structural":[51],"underpinnings":[52],"this":[54],"effect":[55],"not":[57,143,213],"been":[58],"analyzed":[59],"cross-linguistically.":[60],"We":[61,158,222],"conduct":[62],"in-depth":[63],"analyses":[64],"across":[65,149],"47":[66],"typologically":[67],"diverse":[68],"languages":[69,97,116,150,166,207],"three":[71],"parallel":[72],"corpora,":[73],"thereby":[75],"show":[76],"that":[77,83,139,151,189],"types":[79,127],"recurrent":[81],"strongest":[86],"are":[90,123,142],"an":[91],"indicator":[92],"morphological":[94,178],"typology.":[95,157],"For":[96],"with":[98,117],"richer":[99],"inflectional":[100,119],"morphology":[101],"there":[102],"a":[104,161,203],"preference":[105],"highly":[107],"productive":[108],"subwords":[109,122,141],"early":[112],"merges,":[113],"while":[114],"less":[118],"morphology,":[120],"idiosyncratic":[121],"more":[124],"prominent.":[125],"Both":[126],"contribute":[130],"efficient":[132],"compression.":[133],"Counter":[134],"common":[137],"perception":[138],"BPE":[140,170],"linguistically":[144],"relevant,":[145],"we":[146],"find":[147],"resemble":[152],"those":[153],"described":[154],"traditional":[156],"thus":[159],"propose":[160],"novel":[162],"way":[163],"characterize":[165],"according":[167],"their":[169],"properties,":[172],"inspired":[173],"by":[174],"notion":[176],"productivity":[179],"linguistics.":[181],"This":[182],"allows":[183],"us":[184],"language":[187],"vectors":[188],"encode":[190],"typological":[191],"knowledge":[192],"induced":[193],"from":[194],"raw":[195],"text.":[196],"Our":[197],"approach":[198],"easily":[200],"applicable":[201],"wider":[204],"range":[205],"texts,":[209],"as":[210],"it":[211],"does":[212],"require":[214],"annotated":[215],"data":[216],"or":[217],"any":[218],"external":[219],"linguistic":[220],"knowledge.":[221],"discuss":[223],"its":[224],"potential":[225],"contributions":[226],"quantitative":[228],"typology":[229],"multilingual":[231],"NLP.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}