{"id":"https://openalex.org/W2986836143","doi":"https://doi.org/10.18653/v1/d19-5518","title":"Normalising Non-standardised Orthography in Algerian Code-switched User-generated Data","display_name":"Normalising Non-standardised Orthography in Algerian Code-switched User-generated Data","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2986836143","doi":"https://doi.org/10.18653/v1/d19-5518","mag":"2986836143"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-5518","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5518","pdf_url":"https://www.aclweb.org/anthology/D19-5518.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 5th Workshop on Noisy User-generated Text (W-NUT 2019)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-5518.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008737006","display_name":"Wafia Adouane","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["CN","SE"],"is_corresponding":true,"raw_author_name":"Wafia Adouane","raw_affiliation_strings":["Department of Philosophy, Linguistics and Theory of Science (FLoV) , Centre for Linguistic Theory and Studies in Probability (CLASP) , University of Gothenburg","Department of Philosophy, Linguistics and Theory of Science (FLoV),","Centre for Linguistic Theory and Studies in Probability (CLASP), University of Gothenburg"],"affiliations":[{"raw_affiliation_string":"Department of Philosophy, Linguistics and Theory of Science (FLoV) , Centre for Linguistic Theory and Studies in Probability (CLASP) , University of Gothenburg","institution_ids":["https://openalex.org/I4210121707"]},{"raw_affiliation_string":"Department of Philosophy, Linguistics and Theory of Science (FLoV),","institution_ids":[]},{"raw_affiliation_string":"Centre for Linguistic Theory and Studies in Probability (CLASP), University of Gothenburg","institution_ids":["https://openalex.org/I881427289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070681215","display_name":"Jean-Philippe Bernardy","orcid":"https://orcid.org/0000-0002-8469-5617"},"institutions":[{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Jean-Philippe Bernardy","raw_affiliation_strings":["Department of Philosophy, Linguistics and Theory of Science (FLoV) , Centre for Linguistic Theory and Studies in Probability (CLASP) , University of Gothenburg","Centre for Linguistic Theory and Studies in Probability (CLASP), University of Gothenburg","Department of Philosophy, Linguistics and Theory of Science (FLoV),"],"affiliations":[{"raw_affiliation_string":"Department of Philosophy, Linguistics and Theory of Science (FLoV) , Centre for Linguistic Theory and Studies in Probability (CLASP) , University of Gothenburg","institution_ids":["https://openalex.org/I4210121707"]},{"raw_affiliation_string":"Centre for Linguistic Theory and Studies in Probability (CLASP), University of Gothenburg","institution_ids":["https://openalex.org/I881427289"]},{"raw_affiliation_string":"Department of Philosophy, Linguistics and Theory of Science (FLoV),","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014291440","display_name":"Simon Dobnik","orcid":"https://orcid.org/0000-0002-4019-7966"},"institutions":[{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Simon Dobnik","raw_affiliation_strings":["Department of Philosophy, Linguistics and Theory of Science (FLoV) , Centre for Linguistic Theory and Studies in Probability (CLASP) , University of Gothenburg","Centre for Linguistic Theory and Studies in Probability (CLASP), University of Gothenburg","Department of Philosophy, Linguistics and Theory of Science (FLoV),"],"affiliations":[{"raw_affiliation_string":"Department of Philosophy, Linguistics and Theory of Science (FLoV) , Centre for Linguistic Theory and Studies in Probability (CLASP) , University of Gothenburg","institution_ids":["https://openalex.org/I4210121707"]},{"raw_affiliation_string":"Centre for Linguistic Theory and Studies in Probability (CLASP), University of Gothenburg","institution_ids":["https://openalex.org/I881427289"]},{"raw_affiliation_string":"Department of Philosophy, Linguistics and Theory of Science (FLoV),","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008737006"],"corresponding_institution_ids":["https://openalex.org/I4210121707","https://openalex.org/I881427289"],"apc_list":null,"apc_paid":null,"fwci":0.578,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76604468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"140"},"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":0.9994999766349792,"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/T13629","display_name":"Text Readability and Simplification","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.8769789934158325},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6561353802680969},{"id":"https://openalex.org/keywords/orthography","display_name":"Orthography","score":0.639823317527771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6349074840545654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6303725242614746},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5897149443626404},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5852298736572266},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5191687345504761},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4778963327407837},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43819886445999146},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41606244444847107},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36034131050109863},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08980077505111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8769789934158325},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6561353802680969},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.639823317527771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6349074840545654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6303725242614746},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5897149443626404},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5852298736572266},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5191687345504761},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4778963327407837},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43819886445999146},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41606244444847107},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36034131050109863},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08980077505111694},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d19-5518","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5518","pdf_url":"https://www.aclweb.org/anthology/D19-5518.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 5th Workshop on Noisy User-generated Text (W-NUT 2019)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-5518","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5518","pdf_url":"https://www.aclweb.org/anthology/D19-5518.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 5th Workshop on Noisy User-generated Text (W-NUT 2019)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2291942135","display_name":null,"funder_award_id":"2014-39","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320323421","display_name":"G\u00f6teborgs Universitet","ror":"https://ror.org/01tm6cn81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2986836143.pdf","grobid_xml":"https://content.openalex.org/works/W2986836143.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W74782881","https://openalex.org/W214028658","https://openalex.org/W408046128","https://openalex.org/W1895577753","https://openalex.org/W2064675550","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2250268234","https://openalex.org/W2251157848","https://openalex.org/W2251190179","https://openalex.org/W2251851155","https://openalex.org/W2252027930","https://openalex.org/W2252209719","https://openalex.org/W2266080033","https://openalex.org/W2613904329","https://openalex.org/W2760493402","https://openalex.org/W2793190264","https://openalex.org/W2807107081","https://openalex.org/W2885301267","https://openalex.org/W2886448360","https://openalex.org/W2950176361","https://openalex.org/W2963626623","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2970616054","https://openalex.org/W3151357476"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W2349956239","https://openalex.org/W611030372","https://openalex.org/W4389684388","https://openalex.org/W2729795264"],"abstract_inverted_index":{"We":[0],"work":[1],"with":[2,23,45,55,75],"Algerian,":[3],"an":[4,37,61,76],"under-resourced":[5],"non-standardised":[6],"Arabic":[7],"variety,":[8],"for":[9,87,97],"which":[10],"we":[11],"compile":[12],"a":[13,53,94],"new":[14],"parallel":[15],"corpus":[16],"consisting":[17],"of":[18],"user-generated":[19],"textual":[20],"data":[21,73],"matched":[22],"normalised":[24],"and":[25,31,49,60,67,91],"corrected":[26],"human":[27],"annotations":[28],"following":[29],"data-driven":[30],"our":[32],"linguistically":[33],"motivated":[34],"standard.We":[35],"use":[36],"end-toend":[38],"deep":[39],"neural":[40],"model":[41,54],"designed":[42],"to":[43],"deal":[44],"context-dependent":[46],"spelling":[47,89],"correction":[48,90],"normalisation.Results":[50],"indicate":[51],"that":[52,68],"two":[56],"CNN":[57],"sub-network":[58],"encoders":[59],"LSTM":[62],"decoder":[63],"performs":[64],"the":[65,82,88],"best,":[66],"word":[69],"context":[70],"matters.Additionally,":[71],"preprocessing":[72],"token-by-token":[74],"editdistance":[77],"based":[78],"aligner":[79],"significantly":[80],"improves":[81],"performance.We":[83],"get":[84],"promising":[85],"results":[86],"normalisation,":[92],"as":[93],"pre-processing":[95],"step":[96],"downstream":[98],"tasks,":[99],"on":[100],"detecting":[101],"binary":[102],"Semantic":[103],"Textual":[104],"Similarity.":[105]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}