{"id":"https://openalex.org/W41492599","doi":"https://doi.org/10.63317/3758yosch25d","title":"Developing and Using a Pilot Dialectal Arabic Treebank","display_name":"Developing and Using a Pilot Dialectal Arabic Treebank","publication_year":2006,"publication_date":"2006-05-01","ids":{"openalex":"https://openalex.org/W41492599","doi":"https://doi.org/10.63317/3758yosch25d","mag":"41492599"},"language":"en","primary_location":{"id":"doi:10.63317/3758yosch25d","doi":"https://doi.org/10.63317/3758yosch25d","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3758yosch25d","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2006/pdf/543_pdf.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/lrec2006/pdf/543_pdf.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053026044","display_name":"Mohamed Maamouri","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Maamouri","raw_affiliation_strings":["Linguistic Data Consortium University of Pennsylvania 3600 Market Street , Suite 810 Philadelphia , PA 19104 USA","#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania 3600 Market Street , Suite 810 Philadelphia , PA 19104 USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025999439","display_name":"Ann Bies A","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ann Bies","raw_affiliation_strings":["Linguistic Data Consortium University of Pennsylvania 3600 Market Street , Suite 810 Philadelphia , PA 19104 USA","#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania 3600 Market Street , Suite 810 Philadelphia , PA 19104 USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062893665","display_name":"Tim Buckwalter","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Buckwalter","raw_affiliation_strings":["Linguistic Data Consortium University of Pennsylvania 3600 Market Street , Suite 810 Philadelphia , PA 19104 USA","#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania 3600 Market Street , Suite 810 Philadelphia , PA 19104 USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"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":["Center for Computational Learning Systems Columbia University 475 Riverside Drive , Suite 850 , MC7717 New York , NY 10115 USA","Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Learning Systems Columbia University 475 Riverside Drive , Suite 850 , MC7717 New York , NY 10115 USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"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":["Center for Computational Learning Systems Columbia University 475 Riverside Drive , Suite 850 , MC7717 New York , NY 10115 USA","Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Learning Systems Columbia University 475 Riverside Drive , Suite 850 , MC7717 New York , NY 10115 USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","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":["Center for Computational Learning Systems Columbia University 475 Riverside Drive , Suite 850 , MC7717 New York , NY 10115 USA","Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Learning Systems Columbia University 475 Riverside Drive , Suite 850 , MC7717 New York , NY 10115 USA","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/A5014593783","display_name":"Dalila Tabessi A","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dalila Tabessi","raw_affiliation_strings":["Linguistic Data Consortium University of Pennsylvania 3600 Market Street , Suite 810 Philadelphia , PA 19104 USA","#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania 3600 Market Street , Suite 810 Philadelphia , PA 19104 USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4378,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.80150569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"443","last_page":"448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0006000000284984708,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/levantine-arabic","display_name":"Levantine Arabic","score":0.9150000214576721},{"id":"https://openalex.org/keywords/treebank-annotation","display_name":"treebank annotation","score":0.734000027179718},{"id":"https://openalex.org/keywords/morphological-annotation","display_name":"morphological annotation","score":0.8370000123977661},{"id":"https://openalex.org/keywords/syntactic-annotation","display_name":"syntactic annotation","score":0.9850000143051147},{"id":"https://openalex.org/keywords/conversational-telephone-speech","display_name":"conversational telephone speech","score":0.796999990940094},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.656000018119812},{"id":"https://openalex.org/keywords/parser-evaluation","display_name":"parser evaluation","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9812330007553101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314898014068604},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7279903292655945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7162017226219177},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6042812466621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5991606116294861},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.588718056678772},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5707608461380005},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.47407665848731995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46868541836738586},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":"doi:10.63317/3758yosch25d","doi":"https://doi.org/10.63317/3758yosch25d","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3758yosch25d","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2006/pdf/543_pdf.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":"mag:41492599","doi":null,"is_oa":false,"landing_page_url":"https://www.ldc.upenn.edu/sites/www.ldc.upenn.edu/files/lrec2006-developing-using-dialectal-arabic-treebank.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:10.63317/3758yosch25d","doi":"https://doi.org/10.63317/3758yosch25d","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3758yosch25d","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2006/pdf/543_pdf.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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W41492599.pdf","grobid_xml":"https://content.openalex.org/works/W41492599.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W146914567","https://openalex.org/W592217130","https://openalex.org/W1607278777","https://openalex.org/W1957504465","https://openalex.org/W1970523617","https://openalex.org/W2039087642","https://openalex.org/W2048978997","https://openalex.org/W2073827186","https://openalex.org/W2076768867","https://openalex.org/W2100976324","https://openalex.org/W2305592425","https://openalex.org/W2481582840"],"related_works":["https://openalex.org/W6977809669","https://openalex.org/W7223250638","https://openalex.org/W7166566408","https://openalex.org/W2577201715","https://openalex.org/W2250784517","https://openalex.org/W7216829323","https://openalex.org/W2251573242","https://openalex.org/W7095436249","https://openalex.org/W2805974756","https://openalex.org/W2039087642"],"abstract_inverted_index":{"In":[0],"this":[1,123,159,168],"paper,":[2,160],"we":[3,161],"describe":[4,162],"the":[5,13,23,32,73,95,138,148,155,163,175,183,191],"methodological":[6],"procedures":[7],"and":[8,28,40,53,100,113,125,134,142,181,190],"issues":[9],"that":[10],"emerged":[11],"from":[12],"development":[14,141],"of":[15,51,56,60,137,144,165],"a":[16],"pilot":[17],"Levantine":[18,61,88,104],"Arabic":[19,46,62,84],"Treebank":[20],"(LATB)":[21],"at":[22,31],"Linguistic":[24],"Data":[25],"Consortium":[26],"(LDC)":[27],"its":[29],"use":[30,136],"Johns":[33],"Hopkins":[34],"University":[35],"(JHU)":[36],"Center":[37],"for":[38,103,122,140,167],"Language":[39],"Speech":[41],"Processing":[42],"workshop":[43],"on":[44,77,110,174],"Parsing":[45],"Dialects":[47],"(PAD).This":[48],"pilot,":[49],"consisting":[50],"morphological":[52],"syntactic":[54,130,145],"annotation":[55],"approximately":[57],"26,000":[58],"words":[59],"conversational":[63],"telephone":[64],"speech,":[65],"was":[66,92],"developed":[67,120],"under":[68],"severe":[69],"time":[70],"constraints;":[71],"hence":[72],"LDC":[74,156],"team":[75,97,150],"drew":[76],"their":[78],"experience":[79],"in":[80],"treebanking":[81],"Modern":[82],"Standard":[83],"(MSA)":[85],"text.The":[86],"resulting":[87],"dialect":[89,105],"treebanked":[90],"corpus":[91,176],"used":[93],"by":[94],"PAD":[96,149],"to":[98,151,154,177],"develop":[99],"evaluate":[101],"parsers":[102,107,146],"texts.The":[106],"were":[108],"trained":[109],"MSA":[111,133,188],"resources":[112,118,166,189],"adapted":[114],"using":[115],"dialect-MSA":[116],"lexical":[117],"(some":[119],"especially":[121],"task)":[124],"existing":[126],"linguistic":[127],"knowledge":[128],"about":[129],"differences":[131],"between":[132,185],"dialect.The":[135],"LATB":[139],"evaluation":[143],"allowed":[147],"provide":[152],"feedback":[153],"treebank":[157],"developers.In":[158],"creation":[164],"corpus,":[169],"as":[170,172],"well":[171],"transformations":[173],"eliminate":[178],"speech":[179],"effects":[180],"lessen":[182],"gap":[184],"our":[186],"preexisting":[187],"new":[192],"dialectal":[193],"corpus.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}