{"id":"https://openalex.org/W20589053","doi":"https://doi.org/10.63317/3u3bivt7k63h","title":"Predicting Phrase Breaks in Classical and Modern Standard Arabic Text","display_name":"Predicting Phrase Breaks in Classical and Modern Standard Arabic Text","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W20589053","doi":"https://doi.org/10.63317/3u3bivt7k63h","mag":"20589053"},"language":"en","primary_location":{"id":"doi:10.63317/3u3bivt7k63h","doi":"https://doi.org/10.63317/3u3bivt7k63h","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3u3bivt7k63h","pdf_url":null,"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":null,"license_id":null,"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":"green","oa_url":"http://www.lrec-conf.org/proceedings/lrec2012/pdf/239_Paper.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051850429","display_name":"Majdi Sawalha","orcid":"https://orcid.org/0000-0003-4975-6709","observed_orcids":["https://orcid.org/0000-0003-4975-6709"]},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Majdi Sawalha","raw_affiliation_strings":["University of Jordan, Amman, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104065063","display_name":"Claire Brierley","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Claire Brierley","raw_affiliation_strings":["(University of Leeds"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074817028","display_name":"Eric Atwell","orcid":"https://orcid.org/0000-0001-9395-3764","observed_orcids":["https://orcid.org/0000-0001-9395-3764"]},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eric Atwell","raw_affiliation_strings":["(University of Leeds"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7361,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.64295895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3868","last_page":"3872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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/arabic-text-segmentation","display_name":"Arabic text segmentation","score":0.527999997138977},{"id":"https://openalex.org/keywords/prosody-features","display_name":"prosody features","score":0.5680000185966492},{"id":"https://openalex.org/keywords/minority-class-recognition","display_name":"minority class recognition","score":0.6850000023841858},{"id":"https://openalex.org/keywords/classical-arabic","display_name":"Classical Arabic","score":0.7670000195503235},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148033618927002},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7229778170585632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6616126894950867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6611086130142212},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.5937654972076416},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5167778730392456},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5156553983688354},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5084406733512878},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.4998164176940918},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.48596251010894775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46733105182647705},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46679598093032837},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.455163836479187},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4392770230770111},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.437465101480484},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42418837547302246},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.41823646426200867},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.26993560791015625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1128183901309967},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07611677050590515},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.63317/3u3bivt7k63h","doi":"https://doi.org/10.63317/3u3bivt7k63h","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3u3bivt7k63h","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:81700","doi":null,"is_oa":true,"landing_page_url":"https://eprints.whiterose.ac.uk/81700/","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2012/pdf/239_Paper.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.357.2325","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.357.2325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2012/pdf/239_Paper.pdf","raw_type":"text"},{"id":"mag:20589053","doi":null,"is_oa":false,"landing_page_url":"http://www.lrec-conf.org/proceedings/lrec2012/pdf/239_Paper.pdf","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":["cwts-core","erih-plus","jufo-3","norway-2"],"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":null,"raw_source_name":"Language Resources and Evaluation","raw_type":null}],"best_oa_location":{"id":"pmh:oai:eprints.whiterose.ac.uk:81700","doi":null,"is_oa":true,"landing_page_url":"https://eprints.whiterose.ac.uk/81700/","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2012/pdf/239_Paper.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W20589053.pdf","grobid_xml":"https://content.openalex.org/works/W20589053.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W33221268","https://openalex.org/W174611842","https://openalex.org/W1514554603","https://openalex.org/W1521626219","https://openalex.org/W1528895502","https://openalex.org/W1557533693","https://openalex.org/W1572769437","https://openalex.org/W1575919763","https://openalex.org/W1608382592","https://openalex.org/W2025617415","https://openalex.org/W2126799231","https://openalex.org/W2182917886"],"related_works":["https://openalex.org/W1828919465","https://openalex.org/W1581633842","https://openalex.org/W3047407183","https://openalex.org/W2742917097","https://openalex.org/W3162198248","https://openalex.org/W2322861043","https://openalex.org/W3103992731","https://openalex.org/W2955750298","https://openalex.org/W2098419420","https://openalex.org/W2251161416","https://openalex.org/W1551773846","https://openalex.org/W1983541059","https://openalex.org/W2191501486","https://openalex.org/W2960992944","https://openalex.org/W2144321756","https://openalex.org/W2901548275","https://openalex.org/W179203483","https://openalex.org/W1533336637","https://openalex.org/W1933993361","https://openalex.org/W2184449048"],"abstract_inverted_index":{"We":[0],"train":[1],"and":[2,18,25,50,53,59,111,144,148],"test":[3,72],"two":[4],"probabilistic":[5],"taggers":[6,52,123],"for":[7,57,146],"Arabic":[8],"phrase":[9],"break":[10],"prediction":[11],"on":[12,44,132],"a":[13,29,94,133],"purpose-built,":[14],"\u201cgold":[15],"standard\u201d,":[16],"boundary-annotated":[17],"PoS-tagged":[19],"Qur\u201fan":[20],"corpus":[21],"of":[22,75,87,117],"77430":[23],"words":[24,80],"8230":[26],"sentences.":[27],"In":[28],"related":[30],"LREC":[31],"paper":[32],"(Brierley":[33],"et":[34],"al.,":[35],"2012),":[36],"we":[37,42,101],"cover":[38],"dataset":[39],"build.":[40],"Here":[41],"report":[43],"comparative":[45],"experiments":[46],"with":[47,107,121],"off-the-shelf":[48],"N-gram":[49],"HMM":[51],"coarse-grained":[54],"feature":[55],"sets":[56,93],"syntax":[58],"prosody,":[60],"where":[61],"the":[62,90,108],"task":[63],"is":[64,129],"to":[65,137],"predict":[66],"boundary":[67,76],"locations":[68],"in":[69,89,105,114],"an":[70],"unseen":[71],"set":[73],"stripped":[74],"annotations":[77],"by":[78],"classifying":[79],"as":[81],"breaks":[82],"or":[83],"non-breaks.":[84],"The":[85],"preponderance":[86],"non-breaks":[88],"training":[91],"data":[92],"challenging":[95],"baseline":[96],"success":[97],"rate:":[98],"85.56%.":[99],"However,":[100],"achieve":[102],"significant":[103,112],"gains":[104,113],"accuracy":[106],"trigram":[109],"tagger,":[110],"performance":[115],"recognition":[116],"minority":[118],"class":[119],"instances":[120],"both":[122],"via":[124],"Balanced":[125],"Classification":[126],"Rate.":[127],"This":[128],"initial":[130],"work":[131],"long-term":[134],"research":[135],"project":[136],"produce":[138],"annotation":[139],"schemes,":[140],"language":[141],"resources,":[142],"algorithms,":[143],"applications":[145],"Classical":[147],"Modern":[149],"Standard":[150],"Arabic.":[151]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2016-06-24T00:00:00"}
