{"id":"https://openalex.org/W2117202778","doi":"https://doi.org/10.3115/v1/w14-3603","title":"Building a Corpus for Palestinian Arabic: a Preliminary Study","display_name":"Building a Corpus for Palestinian Arabic: a Preliminary Study","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2117202778","doi":"https://doi.org/10.3115/v1/w14-3603","mag":"2117202778"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-3603","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3603","pdf_url":"https://aclanthology.org/W14-3603.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-3603.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050418400","display_name":"Mustafa Jarrar","orcid":"https://orcid.org/0000-0003-4351-4207"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I94800806","display_name":"Birzeit University","ror":"https://ror.org/0256kw398","country_code":"PS","type":"education","lineage":["https://openalex.org/I94800806"]}],"countries":["AE","PS"],"is_corresponding":true,"raw_author_name":"Mustafa Jarrar","raw_affiliation_strings":["New York University Abu Dhabi, United Arab Emirates","[Birzeit University]"],"affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]},{"raw_affiliation_string":"[Birzeit University]","institution_ids":["https://openalex.org/I94800806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"https://orcid.org/0000-0002-1831-3457"},"institutions":[{"id":"https://openalex.org/I94800806","display_name":"Birzeit University","ror":"https://ror.org/0256kw398","country_code":"PS","type":"education","lineage":["https://openalex.org/I94800806"]}],"countries":["PS"],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["[Birzeit University]"],"affiliations":[{"raw_affiliation_string":"[Birzeit University]","institution_ids":["https://openalex.org/I94800806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046284249","display_name":"Diyam Akra","orcid":null},"institutions":[{"id":"https://openalex.org/I94800806","display_name":"Birzeit University","ror":"https://ror.org/0256kw398","country_code":"PS","type":"education","lineage":["https://openalex.org/I94800806"]}],"countries":["PS"],"is_corresponding":false,"raw_author_name":"Diyam Akra","raw_affiliation_strings":["[Birzeit University]"],"affiliations":[{"raw_affiliation_string":"[Birzeit University]","institution_ids":["https://openalex.org/I94800806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089887413","display_name":"Nasser Zalmout","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nasser Zalmout","raw_affiliation_strings":["New York University"],"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050418400"],"corresponding_institution_ids":["https://openalex.org/I120250893","https://openalex.org/I94800806"],"apc_list":null,"apc_paid":null,"fwci":7.6114,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97290835,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"27"},"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/T10028","display_name":"Topic Modeling","score":0.9915000200271606,"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/T13629","display_name":"Text Readability and Simplification","score":0.9854000210762024,"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","display_name":"Arabic","score":0.8138218522071838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6432632207870483},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5782721042633057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40237927436828613},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25983649492263794},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.060152262449264526}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.8138218522071838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6432632207870483},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5782721042633057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40237927436828613},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25983649492263794},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.060152262449264526}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/w14-3603","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3603","pdf_url":"https://aclanthology.org/W14-3603.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.675.3022","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.3022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-3603.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-3603","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3603","pdf_url":"https://aclanthology.org/W14-3603.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2117202778.pdf","grobid_xml":"https://content.openalex.org/works/W2117202778.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W41492599","https://openalex.org/W131663347","https://openalex.org/W181901128","https://openalex.org/W201141796","https://openalex.org/W408046128","https://openalex.org/W562015464","https://openalex.org/W602480804","https://openalex.org/W1544567521","https://openalex.org/W1607053532","https://openalex.org/W1957504465","https://openalex.org/W2055147702","https://openalex.org/W2063718015","https://openalex.org/W2076768867","https://openalex.org/W2100976324","https://openalex.org/W2104463314","https://openalex.org/W2116702211","https://openalex.org/W2147272182","https://openalex.org/W2151690415","https://openalex.org/W2166660646","https://openalex.org/W2250414785","https://openalex.org/W2250732891","https://openalex.org/W2250784517","https://openalex.org/W2250816155","https://openalex.org/W2250897596","https://openalex.org/W2251657882","https://openalex.org/W2251658995","https://openalex.org/W2564673466","https://openalex.org/W2992863467","https://openalex.org/W6608206971","https://openalex.org/W6614291197","https://openalex.org/W6641252224","https://openalex.org/W6691505291","https://openalex.org/W6909269736","https://openalex.org/W6927687912"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4249048193","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W3000360420","https://openalex.org/W2530322880"],"abstract_inverted_index":{"This":[0],"paper":[1,27],"presents":[2],"preliminary":[3],"results":[4],"in":[5,43],"building":[6],"an":[7],"annotated":[8],"corpus":[9,16],"of":[10,18,45,94],"the":[11,33,38,57,63,91],"Palestinian":[12,34,96],"Arabic":[13,81,84,97],"dialect.":[14],"The":[15,26],"consists":[17],"about":[19,32],"43K":[20],"words,":[21],"stemming":[22],"from":[23],"diverse":[24],"resources.":[25],"discusses":[28],"some":[29,53],"linguistic":[30],"facts":[31],"dialect,":[35],"compared":[36],"with":[37],"Modern":[39,79],"Standard":[40,80],"Arabic,":[41],"especially":[42],"terms":[44],"morphological,":[46],"orthographic,":[47],"and":[48,51,82],"lexical":[49],"variations,":[50],"suggests":[52],"directions":[54],"to":[55,62,88],"resolve":[56],"challenges":[58],"these":[59],"differences":[60],"pose":[61],"annotation":[64,92],"goal.":[65],"Furthermore,":[66],"we":[67],"present":[68],"two":[69],"pilot":[70],"studies":[71],"that":[72],"investigate":[73],"whether":[74],"existing":[75],"tools":[76],"for":[77],"processing":[78],"Egyptian":[83],"can":[85],"be":[86],"used":[87],"speed":[89],"up":[90],"process":[93],"our":[95],"corpus.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":8}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
