{"id":"https://openalex.org/W2023457282","doi":"https://doi.org/10.1108/00220410510607480","title":"To stem or lemmatize a highly inflectional language in a probabilistic IR environment?","display_name":"To stem or lemmatize a highly inflectional language in a probabilistic IR environment?","publication_year":2005,"publication_date":"2005-08-01","ids":{"openalex":"https://openalex.org/W2023457282","doi":"https://doi.org/10.1108/00220410510607480","mag":"2023457282"},"language":"en","primary_location":{"id":"doi:10.1108/00220410510607480","is_oa":false,"landing_page_url":"https://doi.org/10.1108/00220410510607480","pdf_url":null,"source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://trepo.tuni.fi/bitstream/10024/65988/1/to_stem_or_lemmatize_2005.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014360834","display_name":"Kimmo Kettunen","orcid":"https://orcid.org/0000-0003-2747-1382"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Kimmo Kettunen","raw_affiliation_strings":["Department of Information Studies, University of Tampere, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Information Studies, University of Tampere, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062387670","display_name":"Tuomas Kunttu","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Kunttu","raw_affiliation_strings":["Department of Information Studies, University of Tampere, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Information Studies, University of Tampere, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014374477","display_name":"Kalervo J\u00e4rvelin","orcid":"https://orcid.org/0000-0001-7655-8930"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kalervo J\u00e4rvelin","raw_affiliation_strings":["Department of Information Studies, University of Tampere, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Information Studies, University of Tampere, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014360834"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":4.1137,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93762573,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"61","issue":"4","first_page":"476","last_page":"496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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":0.998199999332428,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9848347902297974},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686069011688232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6117405891418457},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6064802408218384},{"id":"https://openalex.org/keywords/originality","display_name":"Originality","score":0.5787186026573181},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5568041801452637},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.49921441078186035},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07355847954750061}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9848347902297974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686069011688232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6117405891418457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6064802408218384},{"id":"https://openalex.org/C2776950860","wikidata":"https://www.wikidata.org/wiki/Q2914681","display_name":"Originality","level":3,"score":0.5787186026573181},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5568041801452637},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.49921441078186035},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07355847954750061},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C11012388","wikidata":"https://www.wikidata.org/wiki/Q170658","display_name":"Creativity","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1108/00220410510607480","is_oa":false,"landing_page_url":"https://doi.org/10.1108/00220410510607480","pdf_url":null,"source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/65988","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/65988","pdf_url":"https://trepo.tuni.fi/bitstream/10024/65988/1/to_stem_or_lemmatize_2005.pdf","source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":null,"raw_type":"article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.610","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.info.uta.fi/tutkimus/fire/archive/kettunen_et_al_full_version_2005.pdf","raw_type":"text"},{"id":"pmh:oai:tampub.uta.fi:10024/65988","is_oa":false,"landing_page_url":"http://tampub.uta.fi/handle/10024/65988","pdf_url":null,"source":{"id":"https://openalex.org/S4306401860","display_name":"Tampere University Institutional Repository (Tampere University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150589677","host_organization_name":"Tampere University of Applied Sciences","host_organization_lineage":["https://openalex.org/I150589677"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:trepo.tuni.fi:10024/65988","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/65988","pdf_url":"https://trepo.tuni.fi/bitstream/10024/65988/1/to_stem_or_lemmatize_2005.pdf","source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2023457282.pdf","grobid_xml":"https://content.openalex.org/works/W2023457282.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W26591655","https://openalex.org/W84158582","https://openalex.org/W103650626","https://openalex.org/W119444765","https://openalex.org/W201288405","https://openalex.org/W1501775720","https://openalex.org/W1517312174","https://openalex.org/W1518529582","https://openalex.org/W1521082019","https://openalex.org/W1571393927","https://openalex.org/W1589845329","https://openalex.org/W1601674470","https://openalex.org/W1605873790","https://openalex.org/W1660390307","https://openalex.org/W1684960071","https://openalex.org/W1867845979","https://openalex.org/W1872421927","https://openalex.org/W1949033912","https://openalex.org/W1964837950","https://openalex.org/W1969158886","https://openalex.org/W1971285215","https://openalex.org/W1979076595","https://openalex.org/W1979490177","https://openalex.org/W1987748324","https://openalex.org/W2002664886","https://openalex.org/W2006477783","https://openalex.org/W2008579625","https://openalex.org/W2040355847","https://openalex.org/W2054805201","https://openalex.org/W2064262426","https://openalex.org/W2068143774","https://openalex.org/W2071761836","https://openalex.org/W2086790337","https://openalex.org/W2098162425","https://openalex.org/W2111343008","https://openalex.org/W2154724067","https://openalex.org/W2772302643","https://openalex.org/W2796566033","https://openalex.org/W2911331535","https://openalex.org/W4233401620","https://openalex.org/W4234098973","https://openalex.org/W4237624558","https://openalex.org/W4297944350","https://openalex.org/W6601052559","https://openalex.org/W6640828583","https://openalex.org/W6758330196"],"related_works":["https://openalex.org/W3124131622","https://openalex.org/W2970358562","https://openalex.org/W2513202451","https://openalex.org/W2795445283","https://openalex.org/W2285263069","https://openalex.org/W3190705690","https://openalex.org/W2575750760","https://openalex.org/W2056380474","https://openalex.org/W3198290408","https://openalex.org/W4385574727"],"abstract_inverted_index":{"Purpose":[0],"To":[1],"show":[2,69],"that":[3,70,114],"stem":[4,38,71,92,174],"generation":[5,175],"compares":[6,79],"well":[7,80,128],"with":[8,81,182,211],"lemmatization":[9,82,95,172],"as":[10,229],"a":[11,15,23,46,55,73,84,116,134,144,200,233,253],"morphological":[12,32,77,121,171,250],"tool":[13],"for":[14,19,41,123,143,176,242,257],"highly":[16,212,234,254],"inflectional":[17,213,235],"language":[18,147,256],"IR":[20,48,86,177,202,258],"purposes":[21,178],"in":[22,45,63,83,89,104,199,247],"best\u2010match":[24,85],"retrieval":[25],"system.":[26,203],"Design/methodology/approach":[27],"Effects":[28],"of":[29,106,120,153,157,163,170,207,232,240,249,252],"three":[30],"different":[31,64],"methods":[33],"\u2013":[34,40,133,138],"lemmatization,":[35,78],"stemming":[36],"and":[37,94,98,160,173],"production":[39,93],"Finnish":[42,228],"are":[43,96,100,165,225,239],"compared":[44],"probabilistic":[47,201],"environment":[49],"(INQUERY).":[50],"Evaluation":[51],"is":[52,60,111,139,245],"done":[53],"using":[54,227],"four\u2010point":[56],"relevance":[57],"scale":[58],"which":[59],"partitioned":[61],"differently":[62],"test":[65],"settings.":[66,109],"Findings":[67],"Results":[68,224],"production,":[72],"lighter":[74],"method":[75,119,210],"than":[76],"environment.":[87],"Differences":[88],"performance":[90],"between":[91],"small":[97],"they":[99,190],"not":[101],"statistically":[102],"significant":[103],"most":[105],"the":[107,130,155,186,205,208],"tested":[108],"It":[110],"also":[112],"shown":[113],"hitherto":[115],"rather":[117],"neglected":[118],"processing":[122,248],"Finnish,":[124],"stemming,":[125],"performs":[126],"reasonably":[127],"although":[129],"stemmer":[131,136],"used":[132,209],"Porter":[135],"implementation":[137],"far":[140],"from":[141],"optimal":[142],"morphologically":[145],"complex":[146],"like":[148],"Finnish.":[149],"In":[150],"another":[151],"series":[152],"tests,":[154],"effects":[156],"compound":[158],"splitting":[159],"derivational":[161],"expansion":[162],"queries":[164],"tested.":[166],"Practical":[167],"implications":[168],"Usefulness":[169],"can":[179],"be":[180,217],"estimated":[181,218],"many":[183],"factors.":[184],"On":[185],"average":[187],"P\u2010R":[188],"level":[189],"seem":[191],"to":[192,196,216],"behave":[193],"very":[194],"close":[195],"each":[197],"other":[198,220],"Thus,":[204],"choice":[206],"languages":[214],"needs":[215],"along":[219],"dimensions":[221],"too.":[222],"Originality/value":[223],"achieved":[226],"an":[230],"example":[231],"language.":[236],"The":[237],"results":[238],"interest":[241],"anyone":[243],"who":[244],"interested":[246],"variation":[251],"inflected":[255],"purposes.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}