{"id":"https://openalex.org/W2143910127","doi":"https://doi.org/10.3115/v1/w14-3620","title":"GWU-HASP: Hybrid Arabic Spelling and Punctuation Corrector","display_name":"GWU-HASP: Hybrid Arabic Spelling and Punctuation Corrector","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2143910127","doi":"https://doi.org/10.3115/v1/w14-3620","mag":"2143910127"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-3620","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/w14-3620","pdf_url":"https://doi.org/10.3115/v1/w14-3620","source":null,"license":null,"license_id":null,"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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/w14-3620","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075586667","display_name":"Mohammed Attia","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Attia","raw_affiliation_strings":["george Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"george Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073237528","display_name":"Mohamed Al-Badrashiny","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Al-Badrashiny","raw_affiliation_strings":["george Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"george Washington University","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Diab","raw_affiliation_strings":["george Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"george Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9993000030517578,"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":0.9958000183105469,"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/punctuation","display_name":"Punctuation","score":0.943506121635437},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6944277286529541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5859584212303162},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5664989352226257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41718778014183044},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1722082495689392},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.057492733001708984}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.943506121635437},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6944277286529541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5859584212303162},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5664989352226257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41718778014183044},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1722082495689392},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.057492733001708984}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-3620","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/w14-3620","pdf_url":"https://doi.org/10.3115/v1/w14-3620","source":null,"license":null,"license_id":null,"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:10.1.1.675.5903","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.675.5903","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/W14-3620.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.722.4073","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.722.4073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.attiaspace.com/Publications/2014_HASP_W14-36.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-3620","is_oa":true,"landing_page_url":"http://doi.org/10.3115/v1/w14-3620","pdf_url":"https://doi.org/10.3115/v1/w14-3620","source":null,"license":null,"license_id":null,"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","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W126222424","https://openalex.org/W1516896190","https://openalex.org/W1553646478","https://openalex.org/W1581233860","https://openalex.org/W1632767318","https://openalex.org/W1647671624","https://openalex.org/W1648417313","https://openalex.org/W1935410517","https://openalex.org/W1987385324","https://openalex.org/W2010595692","https://openalex.org/W2014611589","https://openalex.org/W2018616927","https://openalex.org/W2042777049","https://openalex.org/W2057900969","https://openalex.org/W2066792529","https://openalex.org/W2111739706","https://openalex.org/W2121227244","https://openalex.org/W2126784811","https://openalex.org/W2127610924","https://openalex.org/W2140608987","https://openalex.org/W2146867136","https://openalex.org/W2147272182","https://openalex.org/W2147880316","https://openalex.org/W2153013403","https://openalex.org/W2156985047","https://openalex.org/W2159781504","https://openalex.org/W2159859968","https://openalex.org/W2167730892","https://openalex.org/W2170276118","https://openalex.org/W2250268234","https://openalex.org/W2250816155","https://openalex.org/W2250854801","https://openalex.org/W2251851155","https://openalex.org/W2251944986","https://openalex.org/W2406102681","https://openalex.org/W2436413986","https://openalex.org/W2917881729"],"related_works":["https://openalex.org/W3133627921","https://openalex.org/W2890155603","https://openalex.org/W4292714663","https://openalex.org/W4205116992","https://openalex.org/W4362595941","https://openalex.org/W1569864752","https://openalex.org/W2611234994","https://openalex.org/W1517880244","https://openalex.org/W4385506872","https://openalex.org/W3198369135"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"describe":[4],"our":[5],"Hybrid":[6],"Ar-abic":[7],"Spelling":[8],"and":[9,51,53,65,78,80,100],"Punctuation":[10],"Corrector":[11],"(HASP).":[12],"HASP":[13],"was":[14],"one":[15],"of":[16,68],"the":[17,21,62,97],"systems":[18],"participating":[19],"in":[20],"QALB-2014":[22],"Shared":[23],"Task":[24],"on":[25],"Arabic":[26,85],"Error":[27],"Correction.":[28],"The":[29],"system":[30],"uses":[31],"a":[32,66],"CRF":[33],"(Conditional":[34],"Random":[35],"Fields)":[36],"classifier":[37],"for":[38,48,60,71,93],"correcting":[39],"punctua-tion":[40],"errors,":[41],"an":[42,56],"open-source":[43],"dictionary":[44],"(or":[45],"word":[46,91],"list)":[47],"detecting":[49],"errors":[50],"gener-ating":[52],"filtering":[54],"candidates,":[55,64],"n-gram":[57],"language":[58],"model":[59],"selecting":[61],"best":[63],"set":[67],"deterministic":[69],"rules":[70],"text":[72],"normalization":[73],"(such":[74],"as":[75],"re-moving":[76],"diacritics":[77],"kashida":[79],"con-verting":[81],"Hindi":[82],"numbers":[83],"into":[84],"nu-merals).":[86],"We":[87],"also":[88],"experiment":[89],"with":[90],"alignment":[92],"spelling":[94],"correction":[95],"at":[96],"character":[98],"level":[99],"report":[101],"some":[102],"prelimi-nary":[103],"results.":[104],"1":[105]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
