{"id":"https://openalex.org/W2471147443","doi":"https://doi.org/10.18653/v1/n16-3003","title":"Farasa: A Fast and Furious Segmenter for Arabic","display_name":"Farasa: A Fast and Furious Segmenter for Arabic","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2471147443","doi":"https://doi.org/10.18653/v1/n16-3003","mag":"2471147443"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n16-3003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-3003","pdf_url":"https://www.aclweb.org/anthology/N16-3003.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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/N16-3003.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047182137","display_name":"Ahmed Abdelal\u00ed","orcid":"https://orcid.org/0000-0002-4160-8181"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Ahmed Abdelali","raw_affiliation_strings":["Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111452036","display_name":"Kareem Darwish","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Kareem Darwish","raw_affiliation_strings":["Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032689067","display_name":"Nadir Durrani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nadir Durrani","raw_affiliation_strings":["Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102924560","display_name":"Hamdy Mubarak","orcid":"https://orcid.org/0000-0002-9051-6240"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Hamdy Mubarak","raw_affiliation_strings":["Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute Hamad Bin Khalifa University Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047182137"],"corresponding_institution_ids":["https://openalex.org/I4210144839"],"apc_list":null,"apc_paid":null,"fwci":39.7549,"has_fulltext":true,"cited_by_count":366,"citation_normalized_percentile":{"value":0.99755494,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9890999794006348,"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/computer-science","display_name":"Computer science","score":0.5724371075630188},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5501223802566528},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10053485631942749},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09343251585960388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5724371075630188},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5501223802566528},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10053485631942749},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09343251585960388}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/n16-3003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-3003","pdf_url":"https://www.aclweb.org/anthology/N16-3003.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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/n16-3003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-3003","pdf_url":"https://www.aclweb.org/anthology/N16-3003.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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2471147443.pdf","grobid_xml":"https://content.openalex.org/works/W2471147443.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W11511616","https://openalex.org/W1563497747","https://openalex.org/W1628767011","https://openalex.org/W1966863499","https://openalex.org/W1970482722","https://openalex.org/W1996824467","https://openalex.org/W2035720976","https://openalex.org/W2095755718","https://openalex.org/W2101105183","https://openalex.org/W2110161737","https://openalex.org/W2116792345","https://openalex.org/W2119202242","https://openalex.org/W2124807415","https://openalex.org/W2134800885","https://openalex.org/W2136657878","https://openalex.org/W2144810223","https://openalex.org/W2148708890","https://openalex.org/W2154462503","https://openalex.org/W2155086894","https://openalex.org/W2159755860","https://openalex.org/W2161227214","https://openalex.org/W2163238067","https://openalex.org/W2167730892","https://openalex.org/W2250283392","https://openalex.org/W2250659129","https://openalex.org/W2250816155","https://openalex.org/W2251369387","https://openalex.org/W2316776689","https://openalex.org/W2416749667","https://openalex.org/W2556053680","https://openalex.org/W2595715041","https://openalex.org/W3204130541"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"Farasa,":[5],"a":[6],"fast":[7],"and":[8,32,42,58],"accurate":[9],"Arabic":[10,55],"segmenter.":[11],"Our":[12],"approach":[13],"is":[14,49],"based":[15],"on":[16],"SVM-rank":[17],"using":[18],"linear":[19],"kernels.":[20],"We":[21],"measure":[22],"the":[23,26,53],"performance":[24],"of":[25,30,66],"segmenter":[27],"in":[28,34],"terms":[29],"accuracy":[31],"efficiency,":[33],"two":[35],"NLP":[36],"tasks,":[37],"namely":[38],"Machine":[39],"Translation":[40],"(MT)":[41],"Information":[43],"Retrieval":[44],"(IR).":[45],"Farasa":[46],"outperforms":[47],"or":[48],"at":[50],"par":[51],"with":[52],"stateof-the-art":[54],"segmenters":[56],"(Stanford":[57],"MADAMIRA),":[59],"while":[60],"being":[61],"more":[62],"than":[63],"one":[64],"order":[65],"magnitude":[67],"faster.":[68]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":48},{"year":2022,"cited_by_count":46},{"year":2021,"cited_by_count":66},{"year":2020,"cited_by_count":58},{"year":2019,"cited_by_count":45},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}