{"id":"https://openalex.org/W2138958299","doi":"https://doi.org/10.1145/1281485.1281489","title":"YASS","display_name":"YASS","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2138958299","doi":"https://doi.org/10.1145/1281485.1281489","mag":"2138958299"},"language":"en","primary_location":{"id":"doi:10.1145/1281485.1281489","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281485.1281489","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","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/A5026950398","display_name":"Prasenjit Majumder","orcid":"https://orcid.org/0000-0003-0840-9313"},"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":true,"raw_author_name":"Prasenjit Majumder","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052357764","display_name":"Mandar Mitra","orcid":"https://orcid.org/0009-0007-8026-3220"},"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":"Mandar Mitra","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","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, Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029746611","display_name":"Gobinda Kole","orcid":null},"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":"Gobinda Kole","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032809289","display_name":"Pabitra Mitra","orcid":"https://orcid.org/0000-0002-1908-9813"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pabitra Mitra","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080030926","display_name":"Kalyankumar Datta","orcid":null},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kalyankumar Datta","raw_affiliation_strings":["Jadavpur University, Calcutta, India"],"affiliations":[{"raw_affiliation_string":"Jadavpur University, Calcutta, India","institution_ids":["https://openalex.org/I170979836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5026950398"],"corresponding_institution_ids":["https://openalex.org/I6498739"],"apc_list":null,"apc_paid":null,"fwci":8.7579,"has_fulltext":false,"cited_by_count":160,"citation_normalized_percentile":{"value":0.97600227,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"25","issue":"4","first_page":"18","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9973999857902527,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9973999857902527,"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/T11550","display_name":"Text and Document Classification Technologies","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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8372107148170471},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5533396005630493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5497109889984131},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5386928915977478},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5086127519607544},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5071642398834229},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5044771432876587},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.5025730133056641},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.5019159317016602},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46626123785972595},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4148152768611908},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12495717406272888}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8372107148170471},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5533396005630493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5497109889984131},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5386928915977478},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5086127519607544},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5071642398834229},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5044771432876587},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.5025730133056641},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5019159317016602},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46626123785972595},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4148152768611908},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12495717406272888},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1281485.1281489","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281485.1281489","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W26591655","https://openalex.org/W97277479","https://openalex.org/W1554385128","https://openalex.org/W1557757161","https://openalex.org/W1647671624","https://openalex.org/W1654045153","https://openalex.org/W1968951234","https://openalex.org/W1992419399","https://openalex.org/W2008495066","https://openalex.org/W2012191724","https://openalex.org/W2016004628","https://openalex.org/W2033937535","https://openalex.org/W2034163998","https://openalex.org/W2038619519","https://openalex.org/W2086790337","https://openalex.org/W2098162425","https://openalex.org/W2101711363","https://openalex.org/W2143733480","https://openalex.org/W2167301710","https://openalex.org/W2505829332","https://openalex.org/W2796677525","https://openalex.org/W6601052559","https://openalex.org/W7011679150"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W2895890526","https://openalex.org/W4298170800","https://openalex.org/W2794758919","https://openalex.org/W617692174","https://openalex.org/W4232781930","https://openalex.org/W1913642778","https://openalex.org/W4300860228","https://openalex.org/W2630858571","https://openalex.org/W2329406070"],"abstract_inverted_index":{"Stemmers":[0],"attempt":[1],"to":[2,6,20,71,86,119,151],"reduce":[3],"a":[4,29,37,50,83,109],"word":[5],"its":[7],"stem":[8],"or":[9],"root":[10,91],"form":[11],"and":[12,93,105,131,137,155,164,185],"are":[13,46,103,188],"used":[14,70],"widely":[15],"in":[16,159,180],"information":[17],"retrieval":[18,181],"tasks":[19],"increase":[21],"the":[22,54,73,106,116,135,141,165],"recall":[23],"rate.":[24],"Most":[25],"popular":[26],"stemmers":[27,42,133],"encode":[28],"large":[30],"number":[31,167],"of":[32,39,56,75,90,99,140,153,161,168],"language-specific":[33],"rules":[34,45],"built":[35],"over":[36],"length":[38],"time.":[40],"Such":[41],"with":[43,129],"comprehensive":[44],"available":[47],"only":[48],"for":[49,60,108,183],"few":[51],"languages.":[52],"In":[53,78],"absence":[55],"extensive":[57],"linguistic":[58],"resources":[59],"certain":[61],"languages,":[62],"statistical":[63],"language":[64],"processing":[65],"tools":[66],"have":[67],"been":[68],"successfully":[69],"improve":[72],"performance":[74,148,182],"IR":[76],"systems.":[77],"this":[79],"article,":[80],"we":[81],"describe":[82],"clustering-based":[84],"approach":[85,126],"discover":[87],"equivalence":[88,122],"classes":[89],"words":[92],"their":[94],"morphological":[95],"variants.":[96],"A":[97],"set":[98],"string":[100],"distance":[101,117],"measures":[102,118],"defined,":[104],"lexicon":[107],"given":[110],"text":[111],"collection":[112],"is":[113,127,149],"clustered":[114],"using":[115,144],"identify":[120],"these":[121],"classes.":[123],"The":[124,172],"proposed":[125,173],"compared":[128],"Porter's":[130,154],"Lovin's":[132,156],"on":[134],"AP":[136],"WSJ":[138],"subcollections":[139],"Tipster":[142],"dataset":[143],"200":[145],"queries.":[146],"Its":[147],"comparable":[150],"that":[152],"stemmers,":[157],"both":[158],"terms":[160],"average":[162],"precision":[163],"total":[166],"relevant":[169],"documents":[170],"retrieved.":[171],"stemming":[174],"algorithm":[175],"also":[176],"provides":[177],"consistent":[178],"improvements":[179],"French":[184],"Bengali,":[186],"which":[187],"currently":[189],"resource-poor.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":28},{"year":2012,"cited_by_count":15}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2016-06-24T00:00:00"}
