{"id":"https://openalex.org/W2100976324","doi":"https://doi.org/10.3115/1219840.1219911","title":"Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop","display_name":"Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2100976324","doi":"https://doi.org/10.3115/1219840.1219911","mag":"2100976324"},"language":"en","primary_location":{"id":"doi:10.3115/1219840.1219911","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1219840.1219911","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1219911&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics  - ACL '05","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1219911&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"https://orcid.org/0000-0002-1831-3457"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["Center for Computational Learning Systems Columbia University New York, NY 10115, USA","Columbia University, New York, NY;"],"affiliations":[{"raw_affiliation_string":"Center for Computational Learning Systems Columbia University New York, NY 10115, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021314411","display_name":"Owen Rambow","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Owen Rambow","raw_affiliation_strings":["Center for Computational Learning Systems Columbia University New York, NY 10115, USA","Columbia University, New York, NY;"],"affiliations":[{"raw_affiliation_string":"Center for Computational Learning Systems Columbia University New York, NY 10115, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084517393"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":31.9686,"has_fulltext":true,"cited_by_count":441,"citation_normalized_percentile":{"value":0.99745134,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"573","last_page":"580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing 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/T10181","display_name":"Natural Language Processing 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/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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9945999979972839,"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/arabic","display_name":"Arabic","score":0.7580525875091553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7530686855316162},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.6517885327339172},{"id":"https://openalex.org/keywords/spectrum-analyzer","display_name":"Spectrum analyzer","score":0.6506805419921875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6020265817642212},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5375527739524841},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5282330513000488},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5262961387634277},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.5035416483879089},{"id":"https://openalex.org/keywords/fell","display_name":"Fell","score":0.4973287880420685},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.39572879672050476},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19759273529052734},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06897202134132385}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7580525875091553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530686855316162},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.6517885327339172},{"id":"https://openalex.org/C158007255","wikidata":"https://www.wikidata.org/wiki/Q1055222","display_name":"Spectrum analyzer","level":2,"score":0.6506805419921875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6020265817642212},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5375527739524841},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5282330513000488},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5262961387634277},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.5035416483879089},{"id":"https://openalex.org/C109167261","wikidata":"https://www.wikidata.org/wiki/Q5421955","display_name":"Fell","level":2,"score":0.4973287880420685},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.39572879672050476},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19759273529052734},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06897202134132385},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1219840.1219911","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1219840.1219911","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1219911&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics  - ACL '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.133.8511","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.133.8511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P05/P05-1071.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1219840.1219911","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1219840.1219911","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1219911&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics  - ACL '05","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2100976324.pdf","grobid_xml":"https://content.openalex.org/works/W2100976324.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1517178556","https://openalex.org/W1855497951","https://openalex.org/W2048978997","https://openalex.org/W2097341304","https://openalex.org/W2134141008","https://openalex.org/W2144810223","https://openalex.org/W2159859968","https://openalex.org/W2167301710","https://openalex.org/W2249434041"],"related_works":["https://openalex.org/W1965453504","https://openalex.org/W2283093112","https://openalex.org/W2396342956","https://openalex.org/W4200075289","https://openalex.org/W3128305375","https://openalex.org/W2626026432","https://openalex.org/W4289548496","https://openalex.org/W2251183413","https://openalex.org/W2949108231","https://openalex.org/W2147411813"],"abstract_inverted_index":{"We":[0,22,47],"present":[1],"an":[2],"approach":[3],"to":[4,37],"using":[5,34],"a":[6],"morphological":[7,27],"analyzer":[8],"for":[9,25],"tokenizing":[10],"and":[11],"morphologically":[12],"tagging":[13],"(including":[14],"partof-speech":[15],"tagging)":[16],"Arabic":[17],"words":[18],"in":[19,54],"one":[20],"process.":[21],"learn":[23],"classifiers":[24,36],"individual":[26],"features,":[28],"as":[29,31],"well":[30],"ways":[32],"of":[33,44],"these":[35],"choose":[38],"among":[39],"entries":[40],"from":[41],"the":[42,45,55],"output":[43],"analyzer.":[46],"obtain":[48],"accuracy":[49],"rates":[50],"on":[51],"all":[52],"tasks":[53],"high":[56],"nineties.":[57]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":26},{"year":2016,"cited_by_count":26},{"year":2015,"cited_by_count":27},{"year":2014,"cited_by_count":36},{"year":2013,"cited_by_count":35},{"year":2012,"cited_by_count":31}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
