{"id":"https://openalex.org/W2056357537","doi":"https://doi.org/10.1080/08839510490250088","title":"MACHINE LEARNING OF MORPHOSYNTACTIC STRUCTURE: LEMMATIZING UNKNOWN SLOVENE WORDS","display_name":"MACHINE LEARNING OF MORPHOSYNTACTIC STRUCTURE: LEMMATIZING UNKNOWN SLOVENE WORDS","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2056357537","doi":"https://doi.org/10.1080/08839510490250088","mag":"2056357537"},"language":"en","primary_location":{"id":"doi:10.1080/08839510490250088","is_oa":false,"landing_page_url":"https://doi.org/10.1080/08839510490250088","pdf_url":null,"source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"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/A5011635545","display_name":"Toma\u017e Erjavec","orcid":"https://orcid.org/0000-0002-1560-4099"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"TOMA\u017d ERJAVEC","raw_affiliation_strings":["Department of Intelligent Systems , Ljubljana, Slovenia"],"affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems , Ljubljana, Slovenia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064609702","display_name":"Sa\u0161o D\u017eeroski","orcid":"https://orcid.org/0000-0003-2363-712X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"SAS\u010cO D\u017dEROSKI","raw_affiliation_strings":["Department of Intelligent Systems , Ljubljana, Slovenia"],"affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems , Ljubljana, Slovenia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011635545"],"corresponding_institution_ids":[],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":7.645,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.97111413,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"1","first_page":"17","last_page":"41"},"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":0.9995999932289124,"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":0.9926000237464905,"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":0.9431707859039307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8686814904212952},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7546039819717407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7435060739517212},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6882147192955017},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.5786842107772827},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.546224057674408},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5363278388977051},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4830494523048401},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4737853705883026},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4601818323135376},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23403170704841614},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07537207007408142}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9431707859039307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8686814904212952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7546039819717407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7435060739517212},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6882147192955017},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.5786842107772827},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.546224057674408},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5363278388977051},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4830494523048401},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4737853705883026},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4601818323135376},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23403170704841614},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07537207007408142},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/08839510490250088","is_oa":false,"landing_page_url":"https://doi.org/10.1080/08839510490250088","pdf_url":null,"source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W613634021","https://openalex.org/W1502112145","https://openalex.org/W1509114999","https://openalex.org/W1512335690","https://openalex.org/W1855497951","https://openalex.org/W2005298873","https://openalex.org/W2062365585","https://openalex.org/W2099102189","https://openalex.org/W2117400858","https://openalex.org/W2134980541","https://openalex.org/W2135843243","https://openalex.org/W2136717444","https://openalex.org/W2147447918","https://openalex.org/W2147881431","https://openalex.org/W2163563414","https://openalex.org/W2930957955","https://openalex.org/W2951200021","https://openalex.org/W4231741839","https://openalex.org/W4256036167","https://openalex.org/W4285719527","https://openalex.org/W4290649644"],"related_works":["https://openalex.org/W2344644918","https://openalex.org/W2242050811","https://openalex.org/W2107817331","https://openalex.org/W1561563106","https://openalex.org/W2116831595","https://openalex.org/W2152051036","https://openalex.org/W2572912744","https://openalex.org/W2884860922","https://openalex.org/W3042025871","https://openalex.org/W2226076398"],"abstract_inverted_index":{"Automatic":[0],"lemmatization":[1,79,94],"is":[2,31,54,130,143,240],"a":[3,28,44,66,72,106,137,156,198,214],"core":[4],"application":[5],"for":[6,35,39,57,148,193],"many":[7],"language":[8],"processing":[9],"tasks.":[10],"In":[11],"inflectionally":[12],"rich":[13],"languages,":[14],"such":[15],"as":[16],"Slovene,":[17],"assigning":[18],"the":[19,77,88,116,119,122,153,167,194,206,233,236],"correct":[20,123],"lemma":[21,117],"(base":[22],"form)":[23],"to":[24,76,92,99,110,132,145],"each":[25],"word":[26,210],"in":[27,83,105],"running":[29,163],"text":[30],"not":[32],"trivial,":[33],"since":[34,60],"instance,":[36],"nouns":[37],"inflect":[38],"number":[40],"and":[41,49,108,136,177,222,238],"case,":[42],"with":[43],"complex":[45],"configuration":[46],"of":[47,80,90,103,161,197,216,235],"endings":[48],"stem":[50],"modifications.":[51],"The":[52,190],"problem":[53,89],"especially":[55],"difficult":[56],"unknown":[58,81,244],"words,":[59,173,221],"word-forms":[61],"cannot":[62],"be":[63],"matched":[64],"against":[65],"morphological":[67,112,149,199,226],"lexicon.":[68],"This":[69],"paper":[70],"discusses":[71],"machine":[73],"learning":[74,91,98,109,141],"approach":[75],"automatic":[78],"words":[82,104],"Slovene":[84,172,217,246],"texts.":[85],"We":[86,151,165,204],"decompose":[87],"perform":[93,100,111],"into":[95],"two":[96],"subproblems:":[97],"morphosyntactic":[101,124,134,188],"tagging":[102,135],"text,":[107],"analysis,":[113],"which":[114],"produces":[115],"from":[118,213],"word-form":[120],"given":[121],"tag.":[125],"A":[126],"statistics-based":[127],"trigram":[128],"tagger":[129,154,237],"used":[131,144],"learn":[133,146],"first-order":[138],"decision":[139],"list":[140],"system":[142],"rules":[147],"analysis.":[150],"train":[152,166],"on":[155,169,209,243],"manually":[157],"annotated":[158],"corpus":[159,215],"consisting":[160],"100,000":[162],"words.":[164,247],"analyzer":[168,195,239],"open-class":[170],"inflecting":[171,245],"namely":[174],"nouns,":[175],"adjectives,":[176],"main":[178],"verbs,":[179],"together":[180],"being":[181],"characterized":[182],"by":[183],"more":[184],"than":[185],"400":[186],"different":[187],"tags.":[189],"training":[191],"set":[192],"consists":[196],"lexicon":[200],"containing":[201,219],"15,000":[202],"lemmas.":[203],"evaluate":[205],"learned":[207],"model":[208],"lists":[211],"extracted":[212],"texts":[218],"500,000":[220],"show":[223],"that":[224],"our":[225],"analysis":[227],"module":[228],"achieves":[229],"98.6%":[230],"accuracy,":[231],"while":[232],"combination":[234],"92.0%":[241],"accurate":[242]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}