{"id":"https://openalex.org/W1553623403","doi":null,"title":"Determining Case in Arabic: Learning Complex Linguistic Behavior Requires Complex Linguistic Features","display_name":"Determining Case in Arabic: Learning Complex Linguistic Behavior Requires Complex Linguistic Features","publication_year":2007,"publication_date":"2007-06-01","ids":{"openalex":"https://openalex.org/W1553623403","mag":"1553623403"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.1082","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.1082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/D/D07/D07-1116.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/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":["Columbia University"],"raw_orcid":"https://orcid.org/0000-0002-1831-3457","affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102936432","display_name":"Ryan Gabbard","orcid":"https://orcid.org/0000-0002-2122-9678","observed_orcids":["https://orcid.org/0000-0002-2122-9678"]},"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":"Ryan Gabbard","raw_affiliation_strings":["#N#               * University of Pennsylvania"],"raw_orcid":"https://orcid.org/0000-0002-2122-9678","affiliations":[{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"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":["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/A5090150146","display_name":"Seth Kulick A","orcid":"https://orcid.org/0000-0002-1376-4902","observed_orcids":["https://orcid.org/0000-0002-1376-4902"]},"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":"Seth Kulick","raw_affiliation_strings":["#N#               * University of Pennsylvania"],"raw_orcid":"https://orcid.org/0000-0002-1376-4902","affiliations":[{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112418817","display_name":"Mitch Marcus 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":"Mitch Marcus","raw_affiliation_strings":["#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"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":4.7289,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94422259,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1084","last_page":"1092"},"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.0010000000474974513,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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-diacritization","display_name":"Arabic diacritization","score":0.9319999814033508},{"id":"https://openalex.org/keywords/arabic-morphology","display_name":"Arabic morphology","score":0.46799999475479126},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.753000020980835},{"id":"https://openalex.org/keywords/classifiers","display_name":"machine learning classifiers","score":0.6159999966621399},{"id":"https://openalex.org/keywords/syntax-trees","display_name":"syntax trees","score":0.5440000295639038},{"id":"https://openalex.org/keywords/linguistic-features","display_name":"linguistic features","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800114095211029},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.701815664768219},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7008984088897705},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6906024813652039},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.6701558232307434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6530370116233826},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6442736387252808},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5694806575775146},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.5170043706893921},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4106695055961609},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.309073805809021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08818021416664124},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07023254036903381},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.1082","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.1082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/D/D07/D07-1116.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.8660","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.8660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/~gabbard/arabic_case.pdf","raw_type":"text"},{"id":"mag:1553623403","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/D/D07/D07-1116.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Empirical Methods in Natural Language Processing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W201141796","https://openalex.org/W369747275","https://openalex.org/W1550053614","https://openalex.org/W1986543644","https://openalex.org/W2020079054","https://openalex.org/W2041349462","https://openalex.org/W2063718015","https://openalex.org/W2109613320","https://openalex.org/W2153186553"],"related_works":["https://openalex.org/W2250509225","https://openalex.org/W7100876296","https://openalex.org/W2740272870","https://openalex.org/W2136534344","https://openalex.org/W6903825032","https://openalex.org/W3199361379","https://openalex.org/W7100572075","https://openalex.org/W2149709850","https://openalex.org/W6976522769","https://openalex.org/W7100743205"],"abstract_inverted_index":{"This":[0,9],"paper":[1],"discusses":[2],"automatic":[3],"determination":[4],"of":[5,15,20,33],"case":[6],"in":[7,17,60],"Arabic.":[8,21],"task":[10],"is":[11],"a":[12,24,37,43],"major":[13],"source":[14],"errors":[16,59],"full":[18],"diacritization":[19],"We":[22],"use":[23],"gold-standard":[25],"syntactic":[26],"tree,":[27],"and":[28],"obtain":[29],"an":[30],"error":[31,50,65],"rate":[32,66],"about":[34],"4.2%,":[35],"with":[36,70],"machine":[38,76],"learning":[39],"based":[40],"system":[41,44],"outperforming":[42,74],"using":[45],"hand-written":[46,72],"rules.":[47],"A":[48],"careful":[49],"analysis":[51],"suggests":[52],"that":[53],"when":[54],"we":[55],"account":[56],"for":[57],"annotation":[58],"the":[61,64,71,75],"gold":[62],"standard,":[63],"drops":[67],"to":[68],"0.8%,":[69],"rules":[73],"learning-based":[77],"system.":[78]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}
