{"id":"https://openalex.org/W2013997717","doi":"https://doi.org/10.1145/1967293.1967295","title":"A Fast Corpus-Based Stemmer","display_name":"A Fast Corpus-Based Stemmer","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2013997717","doi":"https://doi.org/10.1145/1967293.1967295","mag":"2013997717"},"language":"en","primary_location":{"id":"doi:10.1145/1967293.1967295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1967293.1967295","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","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/A5062553068","display_name":"Jiaul H. Paik","orcid":"https://orcid.org/0000-0003-1550-3586"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jiaul H. Paik","raw_affiliation_strings":["Indian Statistical Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102911608","display_name":"Swapan K. Parui","orcid":"https://orcid.org/0000-0001-6863-5780"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swapan K. Parui","raw_affiliation_strings":["Indian Statistical Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I6498739"],"apc_list":null,"apc_paid":null,"fwci":1.7255,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.86414741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"10","issue":"2","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9990000128746033,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9970999956130981,"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":0.8217238187789917},{"id":"https://openalex.org/keywords/clef","display_name":"Clef","score":0.7854175567626953},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7715603709220886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7323954105377197},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.6525943279266357},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.6291771531105042},{"id":"https://openalex.org/keywords/marathi","display_name":"Marathi","score":0.6253788471221924},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.5765293836593628},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5756956338882446},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"Bilingual dictionary","score":0.5348460078239441},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.5314478278160095},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.52679044008255},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5125405788421631},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.44008806347846985},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.18868181109428406},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17144179344177246},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11223167181015015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8217238187789917},{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.7854175567626953},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7715603709220886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7323954105377197},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.6525943279266357},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.6291771531105042},{"id":"https://openalex.org/C2776844415","wikidata":"https://www.wikidata.org/wiki/Q1571","display_name":"Marathi","level":2,"score":0.6253788471221924},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.5765293836593628},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5756956338882446},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.5348460078239441},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.5314478278160095},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.52679044008255},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5125405788421631},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.44008806347846985},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.18868181109428406},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17144179344177246},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11223167181015015},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1967293.1967295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1967293.1967295","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W76981917","https://openalex.org/W142212369","https://openalex.org/W1483710042","https://openalex.org/W1532325895","https://openalex.org/W1654045153","https://openalex.org/W1969158886","https://openalex.org/W1971285215","https://openalex.org/W1979076595","https://openalex.org/W2008495066","https://openalex.org/W2012191724","https://openalex.org/W2029097226","https://openalex.org/W2058200372","https://openalex.org/W2064262426","https://openalex.org/W2089960290","https://openalex.org/W2101711363","https://openalex.org/W2105157020","https://openalex.org/W2138958299","https://openalex.org/W2168965629","https://openalex.org/W2503748202","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1839123017","https://openalex.org/W4232115401","https://openalex.org/W4226458220","https://openalex.org/W1592594506","https://openalex.org/W2970828463","https://openalex.org/W2084490135","https://openalex.org/W1600697429","https://openalex.org/W744849261","https://openalex.org/W4293372135","https://openalex.org/W1624239806"],"abstract_inverted_index":{"Stemming":[0],"is":[1,24,41,116],"a":[2,57,75,99],"mechanism":[3],"of":[4,63,77,125,134],"word":[5,12,84],"form":[6],"normalization":[7],"that":[8,147],"transforms":[9],"the":[10,28,32,36,82,122],"variant":[11,126],"forms":[13],"to":[14,26,43,79],"their":[15],"common":[16],"root.":[17],"In":[18],"an":[19,113,129],"Information":[20],"Retrieval":[21],"system,":[22],"it":[23],"used":[25],"increase":[27],"system\u2019s":[29],"performance,":[30],"specifically":[31],"recall":[33],"and":[34,120,142,160,172],"desirably":[35],"precision.":[37],"Although":[38],"its":[39,86],"usefulness":[40],"shown":[42],"be":[44],"mixed":[45],"in":[46,96,128],"languages":[47,54,72,91,138,159,168],"such":[48,169],"as":[49,170],"English,":[50],"because":[51],"morphologically":[52],"complex":[53],"stemming":[55],"produces":[56],"significant":[58,162],"performance":[59,163],"improvement.":[60],"A":[61,132],"number":[62],"linguistic":[64,100,154],"rule-based":[65,101,155],"stemmers":[66,156],"are":[67,93,108],"available":[68],"for":[69,89,157,165],"most":[70],"European":[71],"which":[73,92,107,115],"employ":[74],"set":[76,133],"rules":[78],"get":[80],"back":[81],"root":[83],"from":[85],"variants.":[87],"But":[88],"Indian":[90],"highly":[94],"inflectional":[95],"nature,":[97],"devising":[98],"stemmer":[102],"needs":[103],"some":[104,158],"additional":[105],"resources":[106],"not":[109],"available.":[110],"We":[111],"present":[112],"approach":[114,149],"purely":[117],"corpus":[118],"based":[119],"finds":[121],"equivalence":[123],"classes":[124],"words":[127],"unsupervised":[130],"manner.":[131],"experiments":[135],"on":[136],"four":[137],"using":[139],"FIRE,":[140],"CLEF,":[141],"TREC":[143],"test":[144],"collections":[145],"shows":[146],"our":[148],"provides":[150],"comparable":[151],"results":[152],"with":[153],"gives":[161],"improvement":[164],"resource":[166],"constrained":[167],"Bengali":[171],"Marathi.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}