{"id":"https://openalex.org/W2137494357","doi":null,"title":"Arabic Named Entity Recognition: Using Features Extracted from Noisy Data","display_name":"Arabic Named Entity Recognition: Using Features Extracted from Noisy Data","publication_year":2010,"publication_date":"2010-07-11","ids":{"openalex":"https://openalex.org/W2137494357","mag":"2137494357"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.3037","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.3037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/P/P10/P10-2052.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5109466332","display_name":"Yassine Benajiba","orcid":"https://orcid.org/0009-0008-8158-4867","observed_orcids":["https://orcid.org/0009-0008-8158-4867"]},"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":"Yassine Benajiba","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108365460","display_name":"Imed Zitouni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Imed Zitouni","raw_affiliation_strings":["IBM, T.J. Watson Research Center, Yorktown Heights"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, T.J. Watson Research Center, Yorktown Heights","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436","observed_orcids":["https://orcid.org/0000-0002-7696-1436"]},"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":"Mona Diab","raw_affiliation_strings":["Columbia University"],"raw_orcid":"https://orcid.org/0000-0002-7696-1436","affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053947754","display_name":"Paolo Rosso","orcid":"https://orcid.org/0000-0002-8922-1242","observed_orcids":["https://orcid.org/0000-0002-8922-1242"]},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Paolo Rosso","raw_affiliation_strings":["Universidad politecnica de Valencia"],"raw_orcid":"https://orcid.org/0000-0002-8922-1242","affiliations":[{"raw_affiliation_string":"Universidad politecnica de Valencia","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3858,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.92405109,"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":"281","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7294999957084656,"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/T10028","display_name":"Topic Modeling","score":0.7294999957084656,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2655999958515167,"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":0.000699999975040555,"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-named-entity-recognition","display_name":"Arabic named entity recognition","score":0.9929999709129333},{"id":"https://openalex.org/keywords/noisy-features","display_name":"noisy features","score":0.7480000257492065},{"id":"https://openalex.org/keywords/bootstrap-method","display_name":"bootstrapping","score":0.7580000162124634},{"id":"https://openalex.org/keywords/feature-space","display_name":"feature space","score":0.3959999978542328},{"id":"https://openalex.org/keywords/morphological-features","display_name":"morphological features","score":0.7799999713897705},{"id":"https://openalex.org/keywords/syntactic-features","display_name":"syntactic features","score":0.9480000138282776},{"id":"https://openalex.org/keywords/lexical-features","display_name":"lexical features","score":0.9200000166893005},{"id":"https://openalex.org/keywords/morphologically-complex-languages","display_name":"morphologically complex languages","score":0.6129999756813049}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.8022760152816772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955620288848877},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7300880551338196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7099072933197021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6069947481155396},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6008676290512085},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5885303020477295},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5027503967285156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4793887138366699},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45047011971473694},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4230315685272217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3298749327659607},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12308400869369507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09080332517623901},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.3037","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.3037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology-new/P/P10/P10-2052.pdf","raw_type":"text"},{"id":"mag:2137494357","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/P10-2052.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Meeting of the Association for Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1515938884","https://openalex.org/W1550053614","https://openalex.org/W1879337757","https://openalex.org/W2020278455","https://openalex.org/W2022414723","https://openalex.org/W2024226786","https://openalex.org/W2100976324","https://openalex.org/W2108997961","https://openalex.org/W2135890475","https://openalex.org/W2139813029","https://openalex.org/W2143345705","https://openalex.org/W2145262681","https://openalex.org/W2305592425"],"related_works":["https://openalex.org/W2529562092","https://openalex.org/W2022414723","https://openalex.org/W2406146311","https://openalex.org/W7097854322","https://openalex.org/W2104912629","https://openalex.org/W2158662504","https://openalex.org/W2250988285","https://openalex.org/W156989018","https://openalex.org/W2078793151","https://openalex.org/W7098232636"],"abstract_inverted_index":{"Building":[0],"an":[1,37,51,77],"accurate":[2,40],"Named":[3],"Entity":[4],"Recognition":[5],"(NER)":[6],"system":[7],"for":[8],"languages":[9],"with":[10,59],"complex":[11],"morphology":[12],"is":[13,56],"a":[14,60],"challenging":[15],"task.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20],"present":[21],"research":[22],"that":[23,55],"explores":[24],"the":[25],"feature":[26,65],"space":[27,66],"using":[28],"both":[29],"gold":[30],"and":[31,70],"bootstrapped":[32],"noisy":[33,46],"features":[34,47],"to":[35,81],"build":[36],"improved":[38],"highly":[39],"Arabic":[41],"NER":[42,62],"system.":[43,63],"We":[44],"bootstrap":[45],"by":[48],"projection":[49],"from":[50],"Arabic-English":[52],"parallel":[53],"corpus":[54],"automatically":[57],"tagged":[58],"baseline":[61],"The":[64,73],"covers":[67],"lexical,":[68],"morphological,":[69],"syntactic":[71],"features.":[72],"proposed":[74],"approach":[75],"yields":[76],"improvement":[78],"of":[79],"up":[80],"1.64":[82],"F-measure":[83],"(absolute).":[84],"1":[85]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2016-06-24T00:00:00"}