{"id":"https://openalex.org/W3097288631","doi":"https://doi.org/10.13053/cys-24-3-3775","title":"Highly Language-Independent Word Lemmatization Using a Machine-Learning Classifier","display_name":"Highly Language-Independent Word Lemmatization Using a Machine-Learning Classifier","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3097288631","doi":"https://doi.org/10.13053/cys-24-3-3775","mag":"3097288631"},"language":"en","primary_location":{"id":"doi:10.13053/cys-24-3-3775","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-24-3-3775","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073124571","display_name":"Iskander Akhmetov","orcid":"https://orcid.org/0000-0002-3221-9352"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Iskander Akhmetov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020876924","display_name":"Alexandr Pak","orcid":"https://orcid.org/0000-0002-8685-9355"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandr Pak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021380909","display_name":"Irina Ualiyeva","orcid":"https://orcid.org/0000-0003-3853-8896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irina Ualiyeva","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049701126","display_name":"Alexander Gelbukh","orcid":"https://orcid.org/0000-0001-7845-9039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Gelbukh","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073124571"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7233,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.87876586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"24","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9871000051498413,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.9459999799728394,"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":0.9645752906799316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8291003704071045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7239521741867065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7224678993225098},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.4721158742904663},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4447081983089447}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9645752906799316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291003704071045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7239521741867065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7224678993225098},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.4721158742904663},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4447081983089447},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.13053/cys-24-3-3775","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-24-3-3775","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1561563106","https://openalex.org/W2116831595","https://openalex.org/W3124131622","https://openalex.org/W2970358562","https://openalex.org/W3204019825","https://openalex.org/W2513202451","https://openalex.org/W2795445283","https://openalex.org/W2285263069","https://openalex.org/W2884860922","https://openalex.org/W3190705690"],"abstract_inverted_index":{"Lemmatization":[0],"is":[1,15,47,85,131],"a":[2,12,48],"process":[3],"of":[4,11,63,76,93,98,105],"finding":[5],"the":[6,40,60,64,77,81,91,99],"base":[7],"morphological":[8],"form":[9],"(lemma)":[10],"word.":[13],"It":[14],"an":[16,34],"important":[17],"step":[18],"in":[19],"many":[20],"natural":[21],"language":[22,127],"processing,":[23],"information":[24,27],"retrieval,":[25],"and":[26,79,87,129],"extraction":[28],"tasks,":[29],"among":[30],"others.":[31],"We":[32,89],"present":[33],"open-source":[35],"language-independent":[36],"lemmatizer":[37,67,95,101],"based":[38],"on":[39,102,110,122],"Random":[41],"Forest":[42],"classification":[43],"model.":[44],"This":[45,66],"model":[46],"supervised":[49],"machine-learning":[50],"algorithm":[51],"with":[52,96],"decision":[53],"trees":[54],"that":[55,97],"are":[56],"constructed":[57],"corresponding":[58],"to":[59,134],"grammatical":[61],"features":[62],"language.":[65],"does":[68],"not":[69],"require":[70],"any":[71],"manual":[72],"work":[73,109],"for":[74,111],"hard-coding":[75],"rules,":[78],"at":[80],"same":[82],"time":[83],"it":[84,130],"simple":[86],"interpretable.":[88],"compare":[90],"performance":[92,121],"our":[94],"UDPipe":[100,113],"twenty-two":[103],"out":[104],"twenty-five":[106],"languages":[107,124],"we":[108],"which":[112],"has":[114],"models.":[115],"Our":[116],"lemmatization":[117],"method":[118],"shows":[119],"good":[120],"different":[123],"from":[125],"various":[126],"groups,":[128],"easily":[132],"extensible":[133],"other":[135],"languages.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}