{"id":"https://openalex.org/W2049453310","doi":"https://doi.org/10.1145/2009916.2010031","title":"A novel corpus-based stemming algorithm using co-occurrence statistics","display_name":"A novel corpus-based stemming algorithm using co-occurrence statistics","publication_year":2011,"publication_date":"2011-07-24","ids":{"openalex":"https://openalex.org/W2049453310","doi":"https://doi.org/10.1145/2009916.2010031","mag":"2049453310"},"language":"en","primary_location":{"id":"doi:10.1145/2009916.2010031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2010031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-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":true,"raw_author_name":"Jiaul H. Paik","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/A5074943851","display_name":"Dipasree Pal","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":"Dipasree Pal","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":"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, Kolkata, India"],"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062553068"],"corresponding_institution_ids":["https://openalex.org/I6498739"],"apc_list":null,"apc_paid":null,"fwci":3.8482,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.93538135,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"863","last_page":"872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/word","display_name":"Word (group theory)","score":0.7355729937553406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6802800893783569},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.6692092418670654},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6392574310302734},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5341901183128357},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.525604248046875},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5227596759796143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48899686336517334},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47628775238990784},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.452805757522583},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27688658237457275},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.23819023370742798},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22828450798988342},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21125313639640808}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7355729937553406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802800893783569},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.6692092418670654},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6392574310302734},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5341901183128357},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.525604248046875},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5227596759796143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48899686336517334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47628775238990784},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.452805757522583},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27688658237457275},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.23819023370742798},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22828450798988342},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21125313639640808},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2009916.2010031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2010031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W26591655","https://openalex.org/W1483710042","https://openalex.org/W1654045153","https://openalex.org/W1968951234","https://openalex.org/W1979076595","https://openalex.org/W1992419399","https://openalex.org/W2002306339","https://openalex.org/W2002639244","https://openalex.org/W2008495066","https://openalex.org/W2029097226","https://openalex.org/W2038114184","https://openalex.org/W2054364203","https://openalex.org/W2058200372","https://openalex.org/W2060413777","https://openalex.org/W2068143774","https://openalex.org/W2089960290","https://openalex.org/W2098162425","https://openalex.org/W2101711363","https://openalex.org/W2105157020","https://openalex.org/W2123591077","https://openalex.org/W2138958299","https://openalex.org/W2402050558","https://openalex.org/W2460754155","https://openalex.org/W6601052559"],"related_works":["https://openalex.org/W2267059662","https://openalex.org/W2392320810","https://openalex.org/W2078609410","https://openalex.org/W4388411807","https://openalex.org/W2364268683","https://openalex.org/W2387724274","https://openalex.org/W282683215","https://openalex.org/W2478803962","https://openalex.org/W3169430512","https://openalex.org/W4239643353"],"abstract_inverted_index":{"We":[0,29],"present":[1],"a":[2,31,40,47,84,105],"stemming":[3],"algorithm":[4,9,107],"for":[5,90],"text":[6],"retrieval.":[7],"The":[8],"uses":[10],"the":[11,15,23,53,61,65,78,81,93,97,100,110,120],"statistics":[12],"collected":[13],"on":[14,22,96,114],"basis":[16,79,98],"of":[17,42,80,92,99],"certain":[18,85],"corpus":[19],"analysis":[20],"based":[21,113],"co-occurrence":[24,34,82],"between":[25],"two":[26,68],"word":[27,43,62,69,111],"variants.":[28],"use":[30],"very":[32],"simple":[33],"measure":[35],"that":[36,108,118],"reflects":[37],"how":[38],"often":[39],"pair":[41],"variants":[44,63,70,112],"occurs":[45],"in":[46,52],"document":[48],"as":[49,51],"well":[50],"whole":[54],"corpus.":[55],"A":[56],"graph":[57],"is":[58,88],"formed":[59],"where":[60],"are":[64],"nodes":[66],"and":[67],"form":[71],"an":[72],"edge":[73,86,101],"if":[74],"they":[75],"co-occur.":[76],"On":[77],"measure,":[83],"strength":[87],"defined":[89],"each":[91],"edges.":[94],"Finally,":[95],"strengths,":[102],"we":[103],"propose":[104],"partition":[106],"groups":[109],"their":[115],"strongest":[116],"neighbors,":[117],"is,":[119],"neighbors":[121],"with":[122],"largest":[123],"strengths.":[124]},"counts_by_year":[{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}