{"id":"https://openalex.org/W2251161416","doi":"https://doi.org/10.18653/v1/w15-3222","title":"Robust Part-of-speech Tagging of Arabic Text","display_name":"Robust Part-of-speech Tagging of Arabic Text","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2251161416","doi":"https://doi.org/10.18653/v1/w15-3222","mag":"2251161416"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-3222","is_oa":true,"landing_page_url":"http://doi.org/10.18653/v1/w15-3222","pdf_url":"https://www.aclweb.org/anthology/W15-3222.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Arabic Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-3222.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002602581","display_name":"Hanan Aldarmaki","orcid":"https://orcid.org/0000-0003-1706-1777"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hanan Aldarmaki","raw_affiliation_strings":["Department of Computer Science The George Washington University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science The George Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Diab","raw_affiliation_strings":["Department of Computer Science The George Washington University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science The George Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002602581"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":1.3322,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86642143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"173","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T12031","display_name":"Speech and dialogue systems","score":0.9952999949455261,"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":0.8413175344467163},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7396226525306702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6633712649345398},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6211210489273071},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5722466111183167},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5622710585594177},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5552492141723633},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5123437643051147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5061213374137878},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4772089123725891},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.46598002314567566},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4558206796646118},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4475633502006531},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11764523386955261},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06362259387969971},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.060909539461135864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413175344467163},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7396226525306702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6633712649345398},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6211210489273071},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5722466111183167},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5622710585594177},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5552492141723633},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5123437643051147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5061213374137878},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4772089123725891},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.46598002314567566},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4558206796646118},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4475633502006531},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11764523386955261},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06362259387969971},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.060909539461135864},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w15-3222","is_oa":true,"landing_page_url":"http://doi.org/10.18653/v1/w15-3222","pdf_url":"https://www.aclweb.org/anthology/W15-3222.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Arabic Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-3222","is_oa":true,"landing_page_url":"http://doi.org/10.18653/v1/w15-3222","pdf_url":"https://www.aclweb.org/anthology/W15-3222.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Arabic Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251161416.pdf","grobid_xml":"https://content.openalex.org/works/W2251161416.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W201141796","https://openalex.org/W1550053614","https://openalex.org/W1614298861","https://openalex.org/W1781547478","https://openalex.org/W1806015339","https://openalex.org/W1828919465","https://openalex.org/W2021333089","https://openalex.org/W2048978997","https://openalex.org/W2118585731","https://openalex.org/W2121227244","https://openalex.org/W2126784811","https://openalex.org/W2135161317","https://openalex.org/W2249434041","https://openalex.org/W2250816155","https://openalex.org/W6678277124"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2083794993","https://openalex.org/W352609212","https://openalex.org/W4200340037","https://openalex.org/W1511772879","https://openalex.org/W4379115841","https://openalex.org/W608917066","https://openalex.org/W4283652261","https://openalex.org/W585424826","https://openalex.org/W564602992"],"abstract_inverted_index":{"We":[0,61],"present":[1],"a":[2,15,31,40,50,88],"new":[3],"and":[4,20,58],"improved":[5],"part":[6],"of":[7,17,52,100,111],"speech":[8],"tagger":[9],"for":[10,34,73],"Arabic":[11,35],"text":[12],"that":[13,63],"incorporates":[14],"set":[16,99],"novel":[18],"features":[19,53,66],"constraints.":[21],"This":[22],"framework":[23],"is":[24,104],"presented":[25],"within":[26],"the":[27,96,107],"MADAMIRA":[28,109],"software":[29],"suite,":[30],"state-of-the-art":[32],"toolkit":[33],"language":[36],"processing.":[37],"Starting":[38],"from":[39,55],"linear":[41],"SVM":[42],"model":[43],"with":[44],"basic":[45],"lexical":[46],"features,":[47],"we":[48],"add":[49],"range":[51],"derived":[54],"morphological":[56],"analysis":[57],"clustering":[59],"methods.":[60],"show":[62],"using":[64],"these":[65],"significantly":[67],"improves":[68],"part-of-speech":[69],"tagging":[70,90],"accuracy,":[71],"especially":[72],"unseen":[74],"words,":[75],"which":[76,103],"results":[77],"in":[78,87],"better":[79],"generalization":[80],"across":[81],"genres.":[82],"The":[83],"final":[84],"model,":[85],"embedded":[86],"sequential":[89],"framework,":[91],"achieved":[92],"97.15%":[93],"accuracy":[94,110],"on":[95],"main":[97],"test":[98],"newswire":[101],"data,":[102],"higher":[105],"than":[106],"current":[108],"96.91%":[112],"while":[113],"being":[114],"30%":[115],"faster.":[116]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}