{"id":"https://openalex.org/W180844028","doi":"https://doi.org/10.63317/2g9kidkpsdas","title":"Arabic Part of Speech Tagging","display_name":"Arabic Part of Speech Tagging","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W180844028","doi":"https://doi.org/10.63317/2g9kidkpsdas","mag":"180844028"},"language":"en","primary_location":{"id":"doi:10.63317/2g9kidkpsdas","doi":"https://doi.org/10.63317/2g9kidkpsdas","is_oa":true,"landing_page_url":"https://doi.org/10.63317/2g9kidkpsdas","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/384_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/384_Paper.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065358832","display_name":"Emad Mohamed","orcid":"https://orcid.org/0000-0002-3524-5257","observed_orcids":["https://orcid.org/0000-0002-3524-5257","https://orcid.org/1234-4564-1234-4565"]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emad Mohamed","raw_affiliation_strings":["Indiana University Department of Linguistics Memorial Hall 322 Bloomington , IN 47405 USA","\u2021Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University Department of Linguistics Memorial Hall 322 Bloomington , IN 47405 USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"raw_affiliation_string":"\u2021Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009027177","display_name":"Sandra K\u00fcbler","orcid":"https://orcid.org/0000-0003-0885-5436","observed_orcids":["https://orcid.org/0000-0003-0885-5436"]},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandra K\u00fcbler","raw_affiliation_strings":["\u2021Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Indiana University","institution_ids":["https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8444,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91577346,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic-part-of-speech-tagging","display_name":"Arabic part-of-speech tagging","score":0.949999988079071},{"id":"https://openalex.org/keywords/word-segmentation","display_name":"word segmentation","score":0.7310000061988831},{"id":"https://openalex.org/keywords/morphologically-rich-languages","display_name":"morphologically rich languages","score":0.9020000100135803},{"id":"https://openalex.org/keywords/out-of-vocabulary-words","display_name":"out-of-vocabulary words","score":0.6039999723434448}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9357227087020874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535199165344238},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.7750685214996338},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.7484849691390991},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7435760498046875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7404554486274719},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7193961143493652},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7046132683753967},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.6606813669204712},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5906475186347961},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5035108923912048},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.46282726526260376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3348587155342102},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3144046366214752},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08727994561195374},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/2g9kidkpsdas","doi":"https://doi.org/10.63317/2g9kidkpsdas","is_oa":true,"landing_page_url":"https://doi.org/10.63317/2g9kidkpsdas","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/384_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.684.7271","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.684.7271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/384_Paper.pdf","raw_type":"text"},{"id":"mag:180844028","doi":null,"is_oa":false,"landing_page_url":"http://cl.indiana.edu/~skuebler/papers/arab.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-3","norway-2","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation","raw_type":null}],"best_oa_location":{"id":"doi:10.63317/2g9kidkpsdas","doi":"https://doi.org/10.63317/2g9kidkpsdas","is_oa":true,"landing_page_url":"https://doi.org/10.63317/2g9kidkpsdas","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/384_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W180844028.pdf","grobid_xml":"https://content.openalex.org/works/W180844028.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W900993354","https://openalex.org/W1538174031","https://openalex.org/W1551773846","https://openalex.org/W2038192093","https://openalex.org/W2048978997","https://openalex.org/W2100976324","https://openalex.org/W2147169507","https://openalex.org/W2593219075"],"related_works":["https://openalex.org/W2122118939","https://openalex.org/W2130167565","https://openalex.org/W2587774662","https://openalex.org/W1828919465","https://openalex.org/W2740144049","https://openalex.org/W2910520198","https://openalex.org/W2251053923","https://openalex.org/W2756950413","https://openalex.org/W3173438327","https://openalex.org/W2948806562"],"abstract_inverted_index":{"Arabic":[0,26,44],"is":[1,64,139],"a":[2,8,67,133],"morphologically":[3],"rich":[4],"language,":[5],"which":[6,138],"presents":[7],"challenge":[9],"for":[10,22],"part":[11],"of":[12,25,30,41,86,136],"speech":[13],"tagging.In":[14],"this":[15,71],"paper,":[16],"we":[17,90],"compare":[18],"two":[19],"novel":[20],"methods":[21,130],"POS":[23,39,84,99],"tagging":[24,100,106,111],"without":[27],"the":[28,37,42,73,79,87,114,120,143],"use":[29],"gold":[31,148],"standard":[32,149],"word":[33,60,93,134],"segmentation":[34,150],"but":[35],"with":[36,83],"full":[38,53,92],"tagset":[40],"Penn":[43],"Treebank.The":[45],"first":[46,76],"approach":[47,63,122],"uses":[48],"complex":[49],"tags":[50],"that":[51],"describe":[52],"words":[54,74],"and":[55],"does":[56],"not":[57],"require":[58],"any":[59],"segmentation.The":[61],"second":[62],"segmentation-based,":[65],"using":[66,147],"machine":[68],"learning":[69],"segmenter.In":[70],"approach,":[72,89],"are":[75,81],"segmented,":[77],"then":[78],"segments":[80],"annotated":[82],"tags.Because":[85],"word-based":[88],"evaluate":[91],"accuracy":[94,135],"rather":[95],"than":[96,104],"segment":[97],"accuracy.Wordbased":[98],"yields":[101],"better":[102,124],"results":[103,116,125,131],"segment-based":[105],"(93.93%":[107],"vs.":[108],"93.41%).Word":[109],"based":[110],"also":[112],"gives":[113,123],"best":[115],"on":[117,126],"known":[118],"words,":[119],"segmentation-based":[121],"unknown":[127],"words.Combining":[128],"both":[129],"in":[132],"94.37%,":[137],"very":[140],"close":[141],"to":[142],"result":[144],"obtained":[145],"by":[146],"(94.91%).":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}