{"id":"https://openalex.org/W2063809066","doi":"https://doi.org/10.1145/1921656.1921657","title":"An accuracy-enhanced light stemmer for arabic text","display_name":"An accuracy-enhanced light stemmer for arabic text","publication_year":2010,"publication_date":"2010-02-24","ids":{"openalex":"https://openalex.org/W2063809066","doi":"https://doi.org/10.1145/1921656.1921657","mag":"2063809066"},"language":"en","primary_location":{"id":"doi:10.1145/1921656.1921657","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1921656.1921657","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"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 Speech and Language 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/A5086805519","display_name":"Samhaa R. El-Beltagy","orcid":"https://orcid.org/0000-0002-5769-8054"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Samhaa R. El-Beltagy","raw_affiliation_strings":["Cairo University, Giza, Egypt","Cairo Univ., Giza, Egypt#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]},{"raw_affiliation_string":"Cairo Univ., Giza, Egypt#TAB#","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058725522","display_name":"Ahmed Rafea","orcid":"https://orcid.org/0000-0001-8109-1845"},"institutions":[{"id":"https://openalex.org/I80693520","display_name":"American University in Cairo","ror":"https://ror.org/0176yqn58","country_code":"EG","type":"education","lineage":["https://openalex.org/I80693520"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ahmed Rafea","raw_affiliation_strings":["The American University in Cairo","The American university in Cairo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The American University in Cairo","institution_ids":["https://openalex.org/I80693520"]},{"raw_affiliation_string":"The American university in Cairo","institution_ids":["https://openalex.org/I80693520"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6736,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.93163095,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"7","issue":"2","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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":0.9728999733924866,"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/T10028","display_name":"Topic Modeling","score":0.9639999866485596,"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":0.8917917013168335},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7426144480705261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7340862154960632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6522446870803833},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6210059523582458},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.610794723033905},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6076877117156982},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6031123399734497},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5385464429855347},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4712051749229431},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.47002649307250977},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4530196189880371},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06543439626693726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8917917013168335},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7426144480705261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7340862154960632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6522446870803833},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6210059523582458},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.610794723033905},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6076877117156982},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6031123399734497},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5385464429855347},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4712051749229431},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.47002649307250977},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4530196189880371},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06543439626693726},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1921656.1921657","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1921656.1921657","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"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 Speech and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.47999998927116394,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W30790492","https://openalex.org/W84280981","https://openalex.org/W88705112","https://openalex.org/W198023826","https://openalex.org/W1519890653","https://openalex.org/W1532325895","https://openalex.org/W1594622829","https://openalex.org/W1970482722","https://openalex.org/W1972156112","https://openalex.org/W1977830583","https://openalex.org/W1996824467","https://openalex.org/W2008495066","https://openalex.org/W2008598865","https://openalex.org/W2026868490","https://openalex.org/W2027740070","https://openalex.org/W2033937535","https://openalex.org/W2048978997","https://openalex.org/W2054997212","https://openalex.org/W2062233052","https://openalex.org/W2064652252","https://openalex.org/W2065764268","https://openalex.org/W2074344664","https://openalex.org/W2097341304","https://openalex.org/W2099490002","https://openalex.org/W2126815469","https://openalex.org/W2143733480","https://openalex.org/W2144810223","https://openalex.org/W2167301710","https://openalex.org/W2169104544","https://openalex.org/W2281080695","https://openalex.org/W2900549721","https://openalex.org/W2913614304","https://openalex.org/W2930957955","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W2251519152","https://openalex.org/W4380994516"],"abstract_inverted_index":{"Stemming":[0],"is":[1,31,106,118],"a":[2,24,29,32,80],"key":[3],"step":[4],"in":[5,40,110],"most":[6],"text":[7,66],"mining":[8,67],"and":[9,88,148],"information":[10,51],"retrieval":[11],"applications.":[12,68],"Information":[13],"extraction,":[14],"semantic":[15],"annotation,":[16],"as":[17,19,145],"well":[18],"ontology":[20],"learning":[21],"are":[22],"but":[23],"few":[25],"examples":[26],"where":[27],"using":[28],"stemmer":[30],"must.":[33],"While":[34],"the":[35,48,61,74,126],"use":[36],"of":[37,50,55,59,82,95,104,115,125],"light":[38,77],"stemmers":[39,56,78],"Arabic":[41,111],"texts":[42],"has":[43],"proven":[44],"highly":[45],"effective":[46],"for":[47],"task":[49],"retrieval,":[52],"this":[53,102,116],"class":[54,103],"falls":[57],"short":[58],"providing":[60],"accuracy":[62],"required":[63],"by":[64,139],"many":[65],"This":[69],"can":[70,151],"be":[71,153],"attributed":[72],"to":[73,119],"fact":[75],"that":[76,84,89,129,138],"employ":[79],"set":[81],"rules":[83],"they":[85,90],"apply":[86],"indiscriminately":[87],"do":[91],"not":[92],"address":[93],"stemming":[94,133,141],"broken":[96],"plurals":[97,105],"at":[98],"all,":[99],"even":[100],"though":[101],"very":[107],"commonly":[108],"used":[109],"texts.":[112],"The":[113,123],"goal":[114],"work":[117,127],"overcome":[120],"these":[121],"limitations.":[122],"evaluation":[124],"shows":[128,137],"it":[130],"significantly":[131,154],"improves":[132],"accuracy.":[134],"It":[135],"also":[136,152],"improving":[140],"accuracy,":[142],"tasks":[143],"such":[144],"automatic":[146],"annotation":[147],"keyphrase":[149],"extraction":[150],"improved.":[155]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
