{"id":"https://openalex.org/W2169104544","doi":"https://doi.org/10.1145/1390749.1390767","title":"A novel Arabic lemmatization algorithm","display_name":"A novel Arabic lemmatization algorithm","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2169104544","doi":"https://doi.org/10.1145/1390749.1390767","mag":"2169104544"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390767","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","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/A5001821815","display_name":"Eiman Tamah Al-Shammari","orcid":"https://orcid.org/0000-0002-0382-8319"},"institutions":[{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":true,"raw_author_name":"Eiman Al-Shammari","raw_affiliation_strings":["Kuwait University, Fairfax, VA"],"affiliations":[{"raw_affiliation_string":"Kuwait University, Fairfax, VA","institution_ids":["https://openalex.org/I36721946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101558875","display_name":"Jessica Lin","orcid":"https://orcid.org/0000-0002-4887-0692"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jessica Lin","raw_affiliation_strings":["George Mason University, Fairfax, VA"],"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, VA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001821815"],"corresponding_institution_ids":["https://openalex.org/I36721946"],"apc_list":null,"apc_paid":null,"fwci":4.1061,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.94052758,"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":"113","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.991100013256073,"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":0.991100013256073,"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":0.9872999787330627,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8542889952659607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7048428654670715},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6834572553634644},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45456746220588684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45009124279022217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39888837933540344},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11961749196052551}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.8542889952659607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7048428654670715},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6834572553634644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45456746220588684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45009124279022217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39888837933540344},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11961749196052551},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1390749.1390767","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.386.8273","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.8273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.gmu.edu/~jessica/publications/arabic_and08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W78961616","https://openalex.org/W84280981","https://openalex.org/W96445060","https://openalex.org/W151024599","https://openalex.org/W1515618414","https://openalex.org/W1516314344","https://openalex.org/W1651093245","https://openalex.org/W1971784203","https://openalex.org/W1984972187","https://openalex.org/W1987680958","https://openalex.org/W2011586660","https://openalex.org/W2033937535","https://openalex.org/W2064926261","https://openalex.org/W2077679384","https://openalex.org/W2302382203","https://openalex.org/W2319660501","https://openalex.org/W2911331535","https://openalex.org/W3139328003","https://openalex.org/W6603439621","https://openalex.org/W6603877830","https://openalex.org/W6630772770","https://openalex.org/W6637231022"],"related_works":["https://openalex.org/W3124131622","https://openalex.org/W2970358562","https://openalex.org/W3204019825","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"],"abstract_inverted_index":{"Tokenization":[0,21],"is":[1,22],"a":[2,23],"fundamental":[3],"step":[4],"in":[5],"processing":[6],"textual":[7],"data":[8],"preceding":[9],"the":[10],"tasks":[11],"of":[12],"information":[13],"retrieval,":[14],"text":[15],"mining,":[16],"and":[17,32],"natural":[18],"language":[19],"processing.":[20],"language-dependent":[24],"approach,":[25],"including":[26],"normalization,":[27],"stop":[28],"words":[29],"removal,":[30],"lemmatization":[31],"stemming.":[33]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}