{"id":"https://openalex.org/W4388691689","doi":"https://doi.org/10.1162/coli_a_00497","title":"On the Role of Morphological Information for Contextual Lemmatization","display_name":"On the Role of Morphological Information for Contextual Lemmatization","publication_year":2023,"publication_date":"2023-11-15","ids":{"openalex":"https://openalex.org/W4388691689","doi":"https://doi.org/10.1162/coli_a_00497"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00497","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00497","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00497/2177318/coli_a_00497.pdf","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://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00497/2177318/coli_a_00497.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080482240","display_name":"Olia Toporkov","orcid":null},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Olia Toporkov","raw_affiliation_strings":["HiTZ Center - Ixa, University of the Basque Country UPV/EHU. olia.toporkov@ehu.eus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiTZ Center - Ixa, University of the Basque Country UPV/EHU. olia.toporkov@ehu.eus","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087067510","display_name":"Rodrigo Agerri","orcid":"https://orcid.org/0000-0002-7303-7598"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rodrigo Agerri","raw_affiliation_strings":["HiTZ Center - Ixa, University of the Basque Country UPV/EHU. rodrigo.agerri@ehu.eus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiTZ Center - Ixa, University of the Basque Country UPV/EHU. rodrigo.agerri@ehu.eus","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169108374"],"apc_list":null,"apc_paid":null,"fwci":2.3646,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.90712824,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"50","issue":"1","first_page":"157","last_page":"191"},"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9983000159263611,"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/lemmatisation","display_name":"Lemmatisation","score":0.9589239358901978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8487960696220398},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.7928556203842163},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7346816658973694},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.7054345607757568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6286714673042297},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.5205591320991516},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4974055588245392},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49458691477775574},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4421643614768982},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3982059955596924},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.13250786066055298}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9589239358901978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8487960696220398},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.7928556203842163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7346816658973694},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.7054345607757568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6286714673042297},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.5205591320991516},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4974055588245392},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49458691477775574},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4421643614768982},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3982059955596924},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.13250786066055298},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":2,"locations":[{"id":"doi:10.1162/coli_a_00497","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00497","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00497/2177318/coli_a_00497.pdf","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:1da4d552084d433a988b6814a8a8614b","is_oa":true,"landing_page_url":"https://doaj.org/article/1da4d552084d433a988b6814a8a8614b","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 50, Iss 1 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00497","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00497","pdf_url":"https://direct.mit.edu/coli/article-pdf/doi/10.1162/coli_a_00497/2177318/coli_a_00497.pdf","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/10","score":0.6299999952316284,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388691689.pdf","grobid_xml":"https://content.openalex.org/works/W4388691689.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W38462120","https://openalex.org/W1515847863","https://openalex.org/W1522301498","https://openalex.org/W1940872118","https://openalex.org/W1962622193","https://openalex.org/W2008652694","https://openalex.org/W2028863246","https://openalex.org/W2065700902","https://openalex.org/W2066201260","https://openalex.org/W2075910053","https://openalex.org/W2096369514","https://openalex.org/W2105378193","https://openalex.org/W2141457256","https://openalex.org/W2251386579","https://openalex.org/W2299976354","https://openalex.org/W2396200542","https://openalex.org/W2524643686","https://openalex.org/W2592076957","https://openalex.org/W2602331152","https://openalex.org/W2605717780","https://openalex.org/W2612690371","https://openalex.org/W2736914066","https://openalex.org/W2740646860","https://openalex.org/W2740840489","https://openalex.org/W2741095062","https://openalex.org/W2752392399","https://openalex.org/W2768663569","https://openalex.org/W2771976988","https://openalex.org/W2803622774","https://openalex.org/W2804387108","https://openalex.org/W2887428522","https://openalex.org/W2946676565","https://openalex.org/W2950825792","https://openalex.org/W2962902328","https://openalex.org/W2963376582","https://openalex.org/W2963490498","https://openalex.org/W2964204621","https://openalex.org/W2965373594","https://openalex.org/W2966234352","https://openalex.org/W2970529259","https://openalex.org/W2972688845","https://openalex.org/W2972778991","https://openalex.org/W2972874257","https://openalex.org/W2973003424","https://openalex.org/W2973071945","https://openalex.org/W2979826702","https://openalex.org/W2981875889","https://openalex.org/W3031914912","https://openalex.org/W3035390927","https://openalex.org/W3099668342","https://openalex.org/W3100160869","https://openalex.org/W3124955247","https://openalex.org/W4365799947","https://openalex.org/W4385681388","https://openalex.org/W4386576841","https://openalex.org/W4389519176","https://openalex.org/W4391156274","https://openalex.org/W6602181223","https://openalex.org/W6605036423","https://openalex.org/W6631190155","https://openalex.org/W6634757287","https://openalex.org/W6640362995","https://openalex.org/W6676719223","https://openalex.org/W6688866165","https://openalex.org/W6691351334","https://openalex.org/W6691829196","https://openalex.org/W6712286661","https://openalex.org/W6732301634","https://openalex.org/W6739901393","https://openalex.org/W6748304040","https://openalex.org/W6751793318","https://openalex.org/W6751933587","https://openalex.org/W6752788575","https://openalex.org/W6755207826","https://openalex.org/W6762374520","https://openalex.org/W6766673545","https://openalex.org/W6775301884","https://openalex.org/W6778196657","https://openalex.org/W6786586492","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W2098104139","https://openalex.org/W2187070383","https://openalex.org/W1561563106","https://openalex.org/W2116831595","https://openalex.org/W4290735204","https://openalex.org/W4319049525","https://openalex.org/W4290739335","https://openalex.org/W3215822304","https://openalex.org/W1574718645","https://openalex.org/W2610856011"],"abstract_inverted_index":{"Abstract":[0],"Lemmatization":[1,23],"is":[2,24,36,80,171],"a":[3,14,49,113],"natural":[4],"language":[5],"processing":[6],"(NLP)":[7],"task":[8],"that":[9,30,44,79,162,173,208,226],"consists":[10],"of":[11,26,37,85,102,116,132,153],"producing,":[12],"from":[13,51],"given":[15],"inflected":[16,53],"word,":[17],"its":[18,61],"canonical":[19],"form":[20],"or":[21,219],"lemma.":[22],"one":[25],"the":[27,45,81,100,129,209],"basic":[28],"tasks":[29],"facilitate":[31],"downstream":[32,86],"NLP":[33],"applications,":[34],"and":[35,124,127],"particular":[38],"importance":[39],"for":[40,177,230],"high-inflected":[41],"languages.":[42,179],"Given":[43],"process":[46],"to":[47,68,90,105,187,193,235],"obtain":[48,194],"lemma":[50],"an":[52],"word":[54,184],"can":[55],"be":[56],"explained":[57],"by":[58],"looking":[59],"at":[60],"morphosyntactic":[62,66],"category,":[63],"including":[64],"fine-grained":[65,166],"information":[67,104,192],"train":[69],"contextual":[70,107,183,196],"lemmatizers":[71,108,138,164,197,211],"has":[72],"become":[73],"common":[74,148],"practice,":[75],"without":[76,198,222],"considering":[77],"whether":[78],"optimum":[82],"in":[83,94,109,139],"terms":[84],"performance.":[87],"In":[88,180],"order":[89],"address":[91],"this":[92,95],"issue,":[93],"article":[96],"we":[97,135],"empirically":[98],"investigate":[99],"role":[101],"morphological":[103,117,167,191,202],"develop":[106],"six":[110],"languages":[111],"within":[112],"varied":[114],"spectrum":[115],"complexity:":[118],"Basque,":[119],"Turkish,":[120],"Russian,":[121],"Czech,":[122],"Spanish,":[123],"English.":[125],"Furthermore,":[126],"unlike":[128],"vast":[130],"majority":[131],"previous":[133],"work,":[134],"also":[136],"evaluate":[137],"out-of-domain":[140,212],"settings,":[141],"which":[142],"constitutes,":[143],"after":[144],"all,":[145],"their":[146],"most":[147],"application":[149],"use.":[150],"The":[151],"results":[152],"our":[154,205],"study":[155],"are":[156,213,232],"rather":[157],"surprising.":[158],"It":[159],"turns":[160],"out":[161],"providing":[163],"with":[165],"features":[168],"during":[169],"training":[170],"not":[172,175,233],"beneficial,":[174],"even":[176],"agglutinative":[178],"fact,":[181],"modern":[182],"representations":[185],"seem":[186],"implicitly":[188],"encode":[189],"enough":[190],"competitive":[195],"seeing":[199],"any":[200],"explicit":[201],"signal.":[203],"Moreover,":[204],"experiments":[206],"suggest":[207],"best":[210],"those":[214,220],"using":[215],"simple":[216],"UPOS":[217],"tags":[218],"trained":[221],"morphology":[223],"and,":[224],"lastly,":[225],"current":[227],"evaluation":[228],"practices":[229],"lemmatization":[231],"adequate":[234],"clearly":[236],"discriminate":[237],"between":[238],"models.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}