{"id":"https://openalex.org/W4394743136","doi":"https://doi.org/10.1162/tacl_a_00647","title":"The Impact of Word Splitting on the Semantic Content of Contextualized Word Representations","display_name":"The Impact of Word Splitting on the Semantic Content of Contextualized Word Representations","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394743136","doi":"https://doi.org/10.1162/tacl_a_00647"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00647","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/tacl_a_00647","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00647/2362190/tacl_a_00647.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":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00647/2362190/tacl_a_00647.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050718476","display_name":"Aina Gar\u00ed Soler","orcid":null},"institutions":[{"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"]},{"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"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Aina Gar\u00ed Soler","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com-Paris, Institut Polytechnique de Paris, France. aina.garisoler@telecom-paris.fr"],"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com-Paris, Institut Polytechnique de Paris, France. aina.garisoler@telecom-paris.fr","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055866824","display_name":"Matthieu Labeau","orcid":null},"institutions":[{"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"]},{"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"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Matthieu Labeau","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com-Paris, Institut Polytechnique de Paris, France. matthieu.labeau@telecom-paris.fr"],"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com-Paris, Institut Polytechnique de Paris, France. matthieu.labeau@telecom-paris.fr","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064876801","display_name":"Chlo\u00e9 Clavel","orcid":"https://orcid.org/0000-0003-4850-3398"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Chlo\u00e9 Clavel","raw_affiliation_strings":["INRIA, Paris, France. chloe.clavel@inria.fr"],"affiliations":[{"raw_affiliation_string":"INRIA, Paris, France. chloe.clavel@inria.fr","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050718476","https://openalex.org/A5055866824","https://openalex.org/A5064876801"],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1326498283","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":0.3616,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62626731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"299","last_page":"320"},"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":0.9932000041007996,"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":0.8191354274749756},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.816213846206665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7643893957138062},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7000155448913574},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.692907452583313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6464806795120239},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5767166018486023},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5387510061264038},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3390839099884033},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05689266324043274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191354274749756},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.816213846206665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7643893957138062},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7000155448913574},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.692907452583313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6464806795120239},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5767166018486023},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5387510061264038},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3390839099884033},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05689266324043274},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":3,"locations":[{"id":"doi:10.1162/tacl_a_00647","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/tacl_a_00647","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00647/2362190/tacl_a_00647.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:HAL:hal-04593480v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04593480","pdf_url":"https://hal.science/hal-04593480/document","source":{"id":"https://openalex.org/S4406922466","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":"Transactions of the Association for Computational Linguistics, 2024, 12, pp.299-320. ⟨10.1162/tacl_a_00647⟩","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:152f5891b50741d9abffe3bb682e5031","is_oa":true,"landing_page_url":"https://doaj.org/article/152f5891b50741d9abffe3bb682e5031","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 12 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00647","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/tacl_a_00647","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00647/2362190/tacl_a_00647.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G4844034504","display_name":null,"funder_award_id":"ANR-21-CE33-001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8849318481","display_name":"viRtual bEhaVioral skIlls TrAining for pubLIc SpEaking","funder_award_id":"ANR-21-CE33-0016","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334537","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4394743136.pdf"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1555805532","https://openalex.org/W1566289585","https://openalex.org/W1700952868","https://openalex.org/W1854884267","https://openalex.org/W2096819730","https://openalex.org/W2121879602","https://openalex.org/W2136480620","https://openalex.org/W2147809840","https://openalex.org/W2170682101","https://openalex.org/W2251400573","https://openalex.org/W2493916176","https://openalex.org/W2525778437","https://openalex.org/W2757041753","https://openalex.org/W2767253414","https://openalex.org/W2923014074","https://openalex.org/W2946119234","https://openalex.org/W2946817437","https://openalex.org/W2953872833","https://openalex.org/W2954699761","https://openalex.org/W2955002705","https://openalex.org/W2955083930","https://openalex.org/W2956105246","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963341956","https://openalex.org/W2963956670","https://openalex.org/W2963979492","https://openalex.org/W2964179002","https://openalex.org/W2965373594","https://openalex.org/W2971081948","https://openalex.org/W2979826702","https://openalex.org/W2998554035","https://openalex.org/W3016107616","https://openalex.org/W3021480884","https://openalex.org/W3035102548","https://openalex.org/W3035488502","https://openalex.org/W3035582413","https://openalex.org/W3037109418","https://openalex.org/W3098614164","https://openalex.org/W3099178230","https://openalex.org/W3101140821","https://openalex.org/W3103769626","https://openalex.org/W3114035504","https://openalex.org/W3115462295","https://openalex.org/W3153214054","https://openalex.org/W3154525977","https://openalex.org/W3173571438","https://openalex.org/W3173954987","https://openalex.org/W3176852325","https://openalex.org/W3176893837","https://openalex.org/W3186207066","https://openalex.org/W3188660305","https://openalex.org/W3211152275","https://openalex.org/W3213125849","https://openalex.org/W4205918858","https://openalex.org/W4212774754","https://openalex.org/W4223589941","https://openalex.org/W4235505822","https://openalex.org/W4252434862","https://openalex.org/W4285169952","https://openalex.org/W4285267582","https://openalex.org/W4288089799","https://openalex.org/W4293857795","https://openalex.org/W6601894380","https://openalex.org/W6633345489","https://openalex.org/W6684165356","https://openalex.org/W6691746754","https://openalex.org/W6761205521","https://openalex.org/W6763701032","https://openalex.org/W6766673545","https://openalex.org/W6767737316","https://openalex.org/W6767913650","https://openalex.org/W6769627184","https://openalex.org/W6771917389","https://openalex.org/W6775496526","https://openalex.org/W6778883912","https://openalex.org/W6810999548","https://openalex.org/W6851551227","https://openalex.org/W6861211568","https://openalex.org/W6968808746"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W4376653378","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2296205523","https://openalex.org/W2176214140","https://openalex.org/W2516873349","https://openalex.org/W2898077673","https://openalex.org/W4385239468","https://openalex.org/W4200476258"],"abstract_inverted_index":{"Abstract":[0],"When":[1],"deriving":[2],"contextualized":[3],"word":[4],"representations":[5,45,83],"from":[6,62],"language":[7],"models,":[8],"a":[9,39],"decision":[10],"needs":[11],"to":[12,17,34],"be":[13,108],"made":[14],"on":[15,65],"how":[16],"obtain":[18],"one":[19],"for":[20],"out-of-vocabulary":[21],"(OOV)":[22],"words":[23,37,85],"that":[24,79,86,96],"are":[25,43,87],"segmented":[26],"into":[27],"subwords.":[28],"What":[29],"is":[30,89],"the":[31,80,98],"best":[32],"way":[33],"represent":[35],"these":[36,44],"with":[38,110],"single":[40],"vector,":[41],"and":[42],"of":[46,51,60,82,84,97,100],"worse":[47,94],"quality":[48,81],"than":[49,95],"those":[50],"in-vocabulary":[52],"words?":[53],"We":[54],"carry":[55],"out":[56],"an":[57],"intrinsic":[58],"evaluation":[59],"embeddings":[61,99],"different":[63],"models":[64],"semantic":[66],"similarity":[67,104],"tasks":[68],"involving":[69],"OOV":[70],"words.":[71,102],"Our":[72],"analysis":[73],"reveals,":[74],"among":[75],"other":[76],"interesting":[77],"findings,":[78],"split":[88],"often,":[90],"but":[91],"not":[92],"always,":[93],"known":[101],"Their":[103],"values,":[105],"however,":[106],"must":[107],"interpreted":[109],"caution.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}