{"id":"https://openalex.org/W68059783","doi":"https://doi.org/10.63317/47zx42oawm7v","title":"Improving NER in Arabic Using a Morphological Tagger","display_name":"Improving NER in Arabic Using a Morphological Tagger","publication_year":2008,"publication_date":"2008-05-01","ids":{"openalex":"https://openalex.org/W68059783","doi":"https://doi.org/10.63317/47zx42oawm7v","mag":"68059783"},"language":"en","primary_location":{"id":"doi:10.63317/47zx42oawm7v","doi":"https://doi.org/10.63317/47zx42oawm7v","is_oa":true,"landing_page_url":"https://doi.org/10.63317/47zx42oawm7v","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2008/pdf/625_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/lrec2008/pdf/625_paper.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043056624","display_name":"Benjamin Farber","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I75028090","display_name":"Fair Isaac Corporation (United States)","ror":"https://ror.org/0354agh42","country_code":"US","type":"company","lineage":["https://openalex.org/I75028090"]},{"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":"Benjamin Farber","raw_affiliation_strings":["\u2021Center for Computational Learning Systems , Columbia University","Fair Isaac Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Center for Computational Learning Systems , Columbia University","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Fair Isaac Corporation","institution_ids":["https://openalex.org/I75028090"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080437721","display_name":"Dayne Freitag","orcid":"https://orcid.org/0009-0001-0016-5097","observed_orcids":["https://orcid.org/0009-0001-0016-5097"]},"institutions":[{"id":"https://openalex.org/I75028090","display_name":"Fair Isaac Corporation (United States)","ror":"https://ror.org/0354agh42","country_code":"US","type":"company","lineage":["https://openalex.org/I75028090"]},{"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":"Dayne Freitag","raw_affiliation_strings":["\u2021Center for Computational Learning Systems , Columbia University","Fair Isaac Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Center for Computational Learning Systems , Columbia University","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Fair Isaac Corporation","institution_ids":["https://openalex.org/I75028090"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Y. Habash","orcid":"https://orcid.org/0000-0002-1831-3457","observed_orcids":["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":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["\u2021Center for Computational Learning Systems , Columbia University","Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Center for Computational Learning Systems , Columbia University","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021314411","display_name":"Owen Rambow","orcid":"https://orcid.org/0000-0003-2054-039X","observed_orcids":["https://orcid.org/0000-0003-2054-039X"]},"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":["\u2021Center for Computational Learning Systems , Columbia University","Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2021Center for Computational Learning Systems , Columbia University","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4768,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.89480429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2509","last_page":"2514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6586999893188477,"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":0.6586999893188477,"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":0.3337000012397766,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0012000000569969416,"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/named-entity-recognition","display_name":"named entity recognition","score":0.906000018119812},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic language","score":0.6079999804496765},{"id":"https://openalex.org/keywords/morphological-tagging","display_name":"morphological tagging","score":0.9120000004768372},{"id":"https://openalex.org/keywords/mada","display_name":"MADA","score":0.6959999799728394},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.8370000123977661},{"id":"https://openalex.org/keywords/out-of-vocabulary-words","display_name":"out-of-vocabulary words","score":0.8569999933242798},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.675000011920929},{"id":"https://openalex.org/keywords/precision-recall-trade-off","display_name":"precision-recall trade-off","score":0.9369999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159684538841248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6884405612945557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6319109201431274},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5568283796310425},{"id":"https://openalex.org/C158007255","wikidata":"https://www.wikidata.org/wiki/Q1055222","display_name":"Spectrum analyzer","level":2,"score":0.5034324526786804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44154953956604004},{"id":"https://openalex.org/C143025027","wikidata":"https://www.wikidata.org/wiki/Q900581","display_name":"Gloss (optics)","level":3,"score":0.43678414821624756},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4325394630432129},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12652140855789185},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2781448156","wikidata":"https://www.wikidata.org/wiki/Q1570182","display_name":"Coating","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/47zx42oawm7v","doi":"https://doi.org/10.63317/47zx42oawm7v","is_oa":true,"landing_page_url":"https://doi.org/10.63317/47zx42oawm7v","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2008/pdf/625_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:10.1.1.161.1206","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.1206","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/lrec2008/pdf/625_paper.pdf","raw_type":"text"},{"id":"mag:68059783","doi":null,"is_oa":false,"landing_page_url":"http://www.lrec-conf.org/proceedings/lrec2008/pdf/625_paper.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:10.63317/47zx42oawm7v","doi":"https://doi.org/10.63317/47zx42oawm7v","is_oa":true,"landing_page_url":"https://doi.org/10.63317/47zx42oawm7v","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2008/pdf/625_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":[{"id":"https://openalex.org/G2515541506","display_name":null,"funder_award_id":"HR0011","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G3190074090","display_name":null,"funder_award_id":"HR0011-06-C-0023","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W68059783.pdf","grobid_xml":"https://content.openalex.org/works/W68059783.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W77787017","https://openalex.org/W130850236","https://openalex.org/W201141796","https://openalex.org/W1505083828","https://openalex.org/W1550053614","https://openalex.org/W1967350923","https://openalex.org/W1983279103","https://openalex.org/W2008652694","https://openalex.org/W2100976324","https://openalex.org/W2249434041"],"related_works":["https://openalex.org/W2137494357","https://openalex.org/W2406146311","https://openalex.org/W784649594","https://openalex.org/W7088483413","https://openalex.org/W7095367551","https://openalex.org/W1520131719","https://openalex.org/W7096997499","https://openalex.org/W2073676589","https://openalex.org/W2345474875","https://openalex.org/W2100976324"],"abstract_inverted_index":{"We":[0],"discuss":[1],"a":[2,19,25,52,68,74,78,87],"named":[3],"entity":[4],"recognition":[5],"system":[6,70],"for":[7],"Arabic,":[8],"and":[9,43,96,101],"show":[10,102],"how":[11],"we":[12,111],"incorporated":[13],"the":[14,28,33,36,41,44,58,63,84,99,106,115],"information":[15],"provided":[16],"by":[17,40,104],"MADA,":[18],"full":[20],"morphological":[21,26,59,75],"tagger":[22,64],"which":[23,71],"uses":[24,73],"analyzer.Surprisingly,":[27],"relevant":[29],"features":[30],"used":[31],"are":[32],"capitalization":[34],"of":[35,62,94],"English":[37],"gloss":[38],"chosen":[39],"tagger,":[42],"fact":[45],"that":[46,103],"an":[47],"analysis":[48,90],"is":[49,54],"returned":[50],"(that":[51],"word":[53],"not":[55],"OOV":[56],"to":[57,91],"analyzer).The":[60],"use":[61],"also":[65],"improves":[66],"over":[67,83],"third":[69],"just":[72],"analyzer,":[76],"yielding":[77],"14%":[79],"reduction":[80],"in":[81,108],"error":[82,89],"baseline.We":[85],"conduct":[86],"thorough":[88],"identify":[92],"sources":[93],"success":[95],"failure":[97],"among":[98],"variations,":[100],"combining":[105],"systems":[107],"simple":[109],"ways":[110],"can":[112],"significantly":[113],"influence":[114],"precision-recall":[116],"trade-off.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}