{"id":"https://openalex.org/W408046128","doi":null,"title":"Processing Spontaneous Orthography","display_name":"Processing Spontaneous Orthography","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W408046128","mag":"408046128"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.378.1945","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.378.1945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/N/N13/N13-1066.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060938475","display_name":"Ramy Eskander","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramy Eskander","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Y. Habash","orcid":"https://orcid.org/0000-0002-1831-3457","observed_orcids":["https://orcid.org/0000-0002-1831-3457"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["Columbia University"],"raw_orcid":"https://orcid.org/0000-0002-1831-3457","affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021314411","display_name":"Owen Rambow","orcid":"https://orcid.org/0000-0003-2054-039X","observed_orcids":["https://orcid.org/0000-0003-2054-039X"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Owen Rambow","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007428477","display_name":"Nadi Tomeh","orcid":"https://orcid.org/0000-0002-1813-3579","observed_orcids":["https://orcid.org/0000-0002-1813-3579"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nadi Tomeh","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":7.616,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.97237,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"585","last_page":"595"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.00039999998989515007,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0003000000142492354,"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/egyptian-arabic","display_name":"Egyptian Arabic","score":0.8050000071525574},{"id":"https://openalex.org/keywords/orthography","display_name":"orthography","score":0.5759999752044678},{"id":"https://openalex.org/keywords/spelling-normalization","display_name":"spelling normalization","score":0.4449999928474426},{"id":"https://openalex.org/keywords/data-sparsity","display_name":"data sparsity","score":0.6600000262260437},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.3059999942779541}],"concepts":[{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.9462753534317017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051097393035889},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7251510620117188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6408606171607971},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6148263812065125},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6049962043762207},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.507719874382019},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4746972918510437},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4670369327068329},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46352654695510864},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.4450574815273285},{"id":"https://openalex.org/C78148190","wikidata":"https://www.wikidata.org/wiki/Q8192","display_name":"Writing system","level":2,"score":0.4117540419101715},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.1486409306526184},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12472185492515564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.378.1945","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.378.1945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/N/N13/N13-1066.pdf","raw_type":"text"},{"id":"mag:408046128","doi":null,"is_oa":false,"landing_page_url":"https://www.aclweb.org/anthology/N13-1066.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420633","display_name":"North American Chapter of the Association for Computational Linguistics","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":null,"is_accepted":false,"is_published":false,"raw_source_name":"North American Chapter of the Association for Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W24746516","https://openalex.org/W201141796","https://openalex.org/W1544567521","https://openalex.org/W1550053614","https://openalex.org/W1568782772","https://openalex.org/W1577352519","https://openalex.org/W1581233860","https://openalex.org/W1586934900","https://openalex.org/W1631260214","https://openalex.org/W1987385324","https://openalex.org/W2000447173","https://openalex.org/W2010595692","https://openalex.org/W2063718015","https://openalex.org/W2078579128","https://openalex.org/W2080373976","https://openalex.org/W2100976324","https://openalex.org/W2101105183","https://openalex.org/W2105891181","https://openalex.org/W2117075678","https://openalex.org/W2124807415","https://openalex.org/W2133990480","https://openalex.org/W2147272182","https://openalex.org/W2170276118","https://openalex.org/W2250414785","https://openalex.org/W2250732891","https://openalex.org/W2404602200","https://openalex.org/W2406102681","https://openalex.org/W2436413986","https://openalex.org/W2779559028","https://openalex.org/W2950988546","https://openalex.org/W2976463404","https://openalex.org/W2993173751","https://openalex.org/W3170253630"],"related_works":["https://openalex.org/W4206850324","https://openalex.org/W7135914746","https://openalex.org/W4412393358","https://openalex.org/W137260243","https://openalex.org/W131663347","https://openalex.org/W2233440677","https://openalex.org/W3006485790","https://openalex.org/W7131814067","https://openalex.org/W2986836143","https://openalex.org/W7099717695"],"abstract_inverted_index":{"In":[0],"cases":[1],"in":[2],"which":[3,51],"there":[4],"is":[5,25],"no":[6],"standard":[7,70],"orthography":[8,50],"for":[9,27,56],"a":[10,19,48,62],"language":[11,13,29],"or":[12],"variant,":[14],"written":[15],"texts":[16],"will":[17],"display":[18],"variety":[20],"of":[21,42,76],"orthographic":[22],"choices.":[23],"This":[24],"problematic":[26],"natural":[28],"processing":[30,75],"(NLP)":[31],"because":[32],"it":[33],"creates":[34],"spurious":[35],"data":[36],"sparseness.":[37],"We":[38,59],"study":[39],"the":[40],"transformation":[41],"spontaneously":[43],"spelled":[44],"Egyptian":[45,77],"Arabic":[46,78],"into":[47],"conventionalized":[49],"we":[52],"have":[53],"previously":[54],"proposed":[55],"NLP":[57],"purposes.":[58],"show":[60],"that":[61],"two-stage":[63],"process":[64],"can":[65],"reduce":[66],"divergences":[67],"from":[68],"this":[69],"by":[71],"69%,":[72],"making":[73],"subsequent":[74],"easier.":[79],"1":[80]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":4}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}
