{"id":"https://openalex.org/W2575598244","doi":"https://doi.org/10.63317/59oiyegxbo3y","title":"Farasa: A New Fast and Accurate Arabic Word Segmenter","display_name":"Farasa: A New Fast and Accurate Arabic Word Segmenter","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2575598244","doi":"https://doi.org/10.63317/59oiyegxbo3y","mag":"2575598244"},"language":"en","primary_location":{"id":"doi:10.63317/59oiyegxbo3y","doi":"https://doi.org/10.63317/59oiyegxbo3y","is_oa":true,"landing_page_url":"https://doi.org/10.63317/59oiyegxbo3y","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2016/pdf/164_Paper.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/lrec2016/pdf/164_Paper.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111452036","display_name":"Kareem Mohamed Darwish","orcid":null,"observed_orcids":[]},"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":["Hamad Bin Khalifa University (HBKU) , Doha , Qatar","Qatar Computing Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamad Bin Khalifa University (HBKU) , Doha , Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102924560","display_name":"Hamdy Mubarak","orcid":"https://orcid.org/0000-0002-9051-6240","observed_orcids":["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":["Hamad Bin Khalifa University (HBKU) , Doha , Qatar","Qatar Computing Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamad Bin Khalifa University (HBKU) , Doha , Qatar","institution_ids":["https://openalex.org/I4210144839"]},{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144839"],"apc_list":null,"apc_paid":null,"fwci":3.7719,"has_fulltext":true,"cited_by_count":67,"citation_normalized_percentile":{"value":0.95430618,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1070","last_page":"1074"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00019999999494757503,"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":9.999999747378752e-05,"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/linear-kernel","display_name":"linear kernel","score":0.765999972820282},{"id":"https://openalex.org/keywords/named-entities","display_name":"named entities","score":0.7300000190734863},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.628000020980835},{"id":"https://openalex.org/keywords/java-implementation","display_name":"Java implementation","score":0.5080000162124634}],"concepts":[{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.8528543710708618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867807149887085},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6007393002510071},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.598088264465332},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5480751991271973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333347916603088},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5088348984718323},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.49494093656539917},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4294099807739258},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.4111859202384949},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.39024412631988525},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19001612067222595},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15670207142829895},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/59oiyegxbo3y","doi":"https://doi.org/10.63317/59oiyegxbo3y","is_oa":true,"landing_page_url":"https://doi.org/10.63317/59oiyegxbo3y","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2016/pdf/164_Paper.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:2575598244","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/lrec/lrec2016.html#DarwishM16","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:10.63317/59oiyegxbo3y","doi":"https://doi.org/10.63317/59oiyegxbo3y","is_oa":true,"landing_page_url":"https://doi.org/10.63317/59oiyegxbo3y","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2016/pdf/164_Paper.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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2575598244.pdf","grobid_xml":"https://content.openalex.org/works/W2575598244.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W632874098","https://openalex.org/W1563497747","https://openalex.org/W1966863499","https://openalex.org/W1970482722","https://openalex.org/W1996824467","https://openalex.org/W2033937535","https://openalex.org/W2035720976","https://openalex.org/W2097341304","https://openalex.org/W2110161737","https://openalex.org/W2144810223","https://openalex.org/W2167730892","https://openalex.org/W2250283392","https://openalex.org/W2250659129","https://openalex.org/W2250732891","https://openalex.org/W2250816155","https://openalex.org/W2556053680"],"related_works":["https://openalex.org/W2471147443","https://openalex.org/W7123362284","https://openalex.org/W2097341304","https://openalex.org/W2251053923","https://openalex.org/W2912165583","https://openalex.org/W2747566258","https://openalex.org/W2250659129","https://openalex.org/W56096989","https://openalex.org/W7098990753","https://openalex.org/W2051814063"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,37],"present":[4],"Farasa":[5,72],"(meaning":[6],"insight":[7],"in":[8,50,99,107],"Arabic),":[9],"which":[10],"is":[11,27,73,104,115],"a":[12],"fast":[13],"and":[14,46,55,58,70,82,114],"accurate":[15],"Arabic":[16,20,66],"segmenter.Segmentation":[17],"involves":[18],"breaking":[19],"words":[21,98],"into":[22],"their":[23,47],"constituent":[24],"clitics.Our":[25],"approach":[26],"based":[28],"on":[29],"SVM":[30],"rank":[31],"using":[32],"linear":[33],"kernels.The":[34],"features":[35],"that":[36],"utilized":[38],"account":[39],"for:":[40],"likelihood":[41],"of":[42,77,85],"stems,":[43],"prefixes,":[44],"suffixes,":[45],"combination;":[48],"presence":[49],"lexicons":[51],"containing":[52],"valid":[53],"stems":[54],"named":[56],"entities;":[57],"underlying":[59],"stem":[60],"templates.Farasa":[61],"outperforms":[62],"or":[63],"equalizes":[64],"state-of-the-art":[65],"segmenters,":[67],"namely":[68],"QATARA":[69,81],"MADAMIRA.Meanwhile,":[71],"nearly":[74],"one":[75,96],"order":[76],"magnitude":[78,86],"faster":[79,87],"than":[80,88,101],"two":[83],"orders":[84],"MADAMIRA.The":[89],"segmenter":[90],"should":[91],"be":[92],"able":[93],"to":[94],"process":[95],"billion":[97],"less":[100],"5":[102],"hours.Farasa":[103],"written":[105],"entirely":[106],"native":[108],"Java,":[109],"with":[110],"no":[111],"external":[112],"dependencies,":[113],"open-source.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2017-01-26T00:00:00"}
