{"id":"https://openalex.org/W2614862557","doi":"https://doi.org/10.18653/v1/w17-1306","title":"A Neural Architecture for Dialectal Arabic Segmentation","display_name":"A Neural Architecture for Dialectal Arabic Segmentation","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2614862557","doi":"https://doi.org/10.18653/v1/w17-1306","mag":"2614862557"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-1306","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1306","pdf_url":"https://www.aclweb.org/anthology/W17-1306.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 Third Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-1306.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086381528","display_name":"Younes Samih","orcid":"https://orcid.org/0000-0002-0485-7920"},"institutions":[{"id":"https://openalex.org/I75356249","display_name":"Hochschule D\u00fcsseldorf University of Applied Sciences","ror":"https://ror.org/00ftx0026","country_code":"DE","type":"education","lineage":["https://openalex.org/I75356249"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Younes Samih","raw_affiliation_strings":["Dept. of Computational Linguistics,University of Dsseldorf, Dsseldorf, Germany","Dept. of Computational Linguistics,University of D\u00fcsseldorf, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"Dept. of Computational Linguistics,University of Dsseldorf, Dsseldorf, Germany","institution_ids":["https://openalex.org/I75356249"]},{"raw_affiliation_string":"Dept. of Computational Linguistics,University of D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075586667","display_name":"Mohammed Attia","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Attia","raw_affiliation_strings":["Google Inc., New York City, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York City, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033221342","display_name":"Mohamed Eldesouki","orcid":"https://orcid.org/0009-0009-6662-5883"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mohamed Eldesouki","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047182137","display_name":"Ahmed Abdelal\u00ed","orcid":"https://orcid.org/0000-0002-4160-8181"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Abdelali","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102924560","display_name":"Hamdy Mubarak","orcid":"https://orcid.org/0000-0002-9051-6240"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Hamdy Mubarak","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004268590","display_name":"Laura Kallmeyer","orcid":"https://orcid.org/0000-0001-9691-5990"},"institutions":[{"id":"https://openalex.org/I75356249","display_name":"Hochschule D\u00fcsseldorf University of Applied Sciences","ror":"https://ror.org/00ftx0026","country_code":"DE","type":"education","lineage":["https://openalex.org/I75356249"]},{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Laura Kallmeyer","raw_affiliation_strings":["Dept. of Computational Linguistics,University of Dsseldorf, Dsseldorf, Germany","Dept. of Computational Linguistics,University of D\u00fcsseldorf, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"Dept. of Computational Linguistics,University of Dsseldorf, Dsseldorf, Germany","institution_ids":["https://openalex.org/I75356249"]},{"raw_affiliation_string":"Dept. of Computational Linguistics,University of D\u00fcsseldorf, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111452036","display_name":"Kareem Darwish","orcid":null},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Kareem Darwish","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5086381528"],"corresponding_institution_ids":["https://openalex.org/I44260953","https://openalex.org/I75356249"],"apc_list":null,"apc_paid":null,"fwci":3.1203,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.93306405,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9876999855041504,"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/computer-science","display_name":"Computer science","score":0.8208119869232178},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7010171413421631},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6979711055755615},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6894305944442749},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6842936873435974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6725291609764099},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.543098509311676},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5253802537918091},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5048004388809204},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4963424801826477},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15159061551094055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8208119869232178},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7010171413421631},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6979711055755615},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6894305944442749},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6842936873435974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6725291609764099},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.543098509311676},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5253802537918091},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5048004388809204},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4963424801826477},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15159061551094055},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-1306","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1306","pdf_url":"https://www.aclweb.org/anthology/W17-1306.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 Third Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-1306","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1306","pdf_url":"https://www.aclweb.org/anthology/W17-1306.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 Third Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2614862557.pdf","grobid_xml":"https://content.openalex.org/works/W2614862557.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W137989762","https://openalex.org/W1598796236","https://openalex.org/W1810943226","https://openalex.org/W1904365287","https://openalex.org/W1938755728","https://openalex.org/W1940872118","https://openalex.org/W2005708641","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2107878631","https://openalex.org/W2123777430","https://openalex.org/W2131774270","https://openalex.org/W2137498753","https://openalex.org/W2143612262","https://openalex.org/W2147880316","https://openalex.org/W2156554947","https://openalex.org/W2156876426","https://openalex.org/W2158899491","https://openalex.org/W2160802179","https://openalex.org/W2250414785","https://openalex.org/W2250562293","https://openalex.org/W2250659129","https://openalex.org/W2250732891","https://openalex.org/W2250783208","https://openalex.org/W2250784517","https://openalex.org/W2250816155","https://openalex.org/W2274880506","https://openalex.org/W2296283641","https://openalex.org/W2471147443","https://openalex.org/W2523233994","https://openalex.org/W2557418006","https://openalex.org/W2951559648","https://openalex.org/W2952230511","https://openalex.org/W2962784628","https://openalex.org/W2962902328","https://openalex.org/W2963682821"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W2978383222","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2058548953","https://openalex.org/W2785359773","https://openalex.org/W2362013696"],"abstract_inverted_index":{"The":[0],"automated":[1],"processing":[2,35],"of":[3,12,18,26],"Arabic":[4],"dialects":[5],"is":[6,32],"challenging":[7],"due":[8],"to":[9],"the":[10,16,81],"lack":[11],"spelling":[13],"standards":[14],"and":[15,21],"scarcity":[17],"annotated":[19,55],"data":[20],"resources":[22],"in":[23],"general.":[24],"Segmentation":[25],"words":[27],"into":[28],"their":[29],"constituent":[30],"tokens":[31],"an":[33],"important":[34],"step":[36],"for":[37],"natural":[38],"language":[39],"processing.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"show":[45,85],"how":[46],"a":[47,76],"segmenter":[48],"can":[49,90],"be":[50],"trained":[51],"on":[52,65,97],"only":[53],"350":[54],"tweets":[56],"using":[57],"neural":[58],"networks":[59],"without":[60],"any":[61],"normalization":[62],"or":[63,68],"reliance":[64],"lexical":[66],"features":[67],"linguistic":[69],"resources.":[70,99],"We":[71,84],"deal":[72],"with":[73],"segmentation":[74],"as":[75],"sequence":[77],"labeling":[78],"problem":[79],"at":[80],"character":[82],"level.":[83],"experimentally":[86],"that":[87,94],"our":[88],"model":[89],"rival":[91],"state-of-the-art":[92],"methods":[93],"heavily":[95],"depend":[96],"additional":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}