{"id":"https://openalex.org/W2799060650","doi":"https://doi.org/10.18653/v1/p18-2089","title":"Addressing Noise in Multidialectal Word Embeddings","display_name":"Addressing Noise in Multidialectal Word Embeddings","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2799060650","doi":"https://doi.org/10.18653/v1/p18-2089","mag":"2799060650"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-2089","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2089","pdf_url":"https://www.aclweb.org/anthology/P18-2089.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-2089.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056150502","display_name":"Alexander Erdmann","orcid":null},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Alexander Erdmann","raw_affiliation_strings":["Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089887413","display_name":"Nasser Zalmout","orcid":null},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Nasser Zalmout","raw_affiliation_strings":["Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"https://orcid.org/0000-0002-1831-3457"},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":["Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056150502"],"corresponding_institution_ids":["https://openalex.org/I120250893"],"apc_list":null,"apc_paid":null,"fwci":3.4613,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93661794,"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":"558","last_page":"565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T10201","display_name":"Speech Recognition and Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8078429102897644},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6859075427055359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6075472235679626},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5889562964439392},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5728630423545837},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5389033555984497},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5325008630752563},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4926045536994934},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.4642793536186218},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42738527059555054},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4152037799358368},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16151681542396545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078429102897644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6859075427055359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6075472235679626},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5889562964439392},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5728630423545837},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5389033555984497},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5325008630752563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4926045536994934},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.4642793536186218},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42738527059555054},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4152037799358368},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16151681542396545},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/p18-2089","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2089","pdf_url":"https://www.aclweb.org/anthology/P18-2089.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-2089","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2089","pdf_url":"https://www.aclweb.org/anthology/P18-2089.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313203","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821"},{"id":"https://openalex.org/F4320319918","display_name":"York University","ror":"https://ror.org/05fq50484"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2799060650.pdf","grobid_xml":"https://content.openalex.org/works/W2799060650.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W137260243","https://openalex.org/W137989762","https://openalex.org/W168564468","https://openalex.org/W201141796","https://openalex.org/W342285082","https://openalex.org/W1610818344","https://openalex.org/W1614298861","https://openalex.org/W1828724394","https://openalex.org/W1957504465","https://openalex.org/W1977195462","https://openalex.org/W2109704865","https://openalex.org/W2117202778","https://openalex.org/W2118090838","https://openalex.org/W2124807415","https://openalex.org/W2126725946","https://openalex.org/W2147272182","https://openalex.org/W2153579005","https://openalex.org/W2158199200","https://openalex.org/W2250539671","https://openalex.org/W2251137535","https://openalex.org/W2251765408","https://openalex.org/W2251805974","https://openalex.org/W2413534664","https://openalex.org/W2493916176","https://openalex.org/W2518324938","https://openalex.org/W2561995736","https://openalex.org/W2574075017","https://openalex.org/W2584934697","https://openalex.org/W2595715041","https://openalex.org/W2740534027","https://openalex.org/W2740918723","https://openalex.org/W2741602058","https://openalex.org/W2757376562","https://openalex.org/W2762484717","https://openalex.org/W2788190679","https://openalex.org/W2804967932","https://openalex.org/W2805089673","https://openalex.org/W2806335230","https://openalex.org/W2806573136","https://openalex.org/W2806962830","https://openalex.org/W2807107081","https://openalex.org/W2950577311","https://openalex.org/W2952037945","https://openalex.org/W2952972707","https://openalex.org/W2962777061","https://openalex.org/W2962824887","https://openalex.org/W2963042536","https://openalex.org/W2963231544","https://openalex.org/W2963943537","https://openalex.org/W4293863842","https://openalex.org/W4294170691","https://openalex.org/W4299579390","https://openalex.org/W4300167661"],"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/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2081317458","https://openalex.org/W2597655663"],"abstract_inverted_index":{"Word":[0],"embeddings":[1,13],"are":[2,25],"crucial":[3],"to":[4,38,49,53,110,123],"many":[5],"natural":[6],"language":[7],"processing":[8],"tasks.":[9],"The":[10],"quality":[11],"of":[12,89],"relies":[14],"on":[15,115,131,139],"large":[16,22],"nonnoisy":[17],"corpora.":[18],"Arabic":[19],"dialects":[20,70,79],"lack":[21],"corpora":[23],"and":[24,117],"noisy,":[26,132],"being":[27],"linguistically":[28],"disparate":[29,69],"with":[30],"no":[31],"standardized":[32],"spelling.":[33],"We":[34],"make":[35],"three":[36],"contributions":[37],"address":[39],"this":[40],"noise.":[41],"First,":[42],"we":[43,64,93,128],"describe":[44],"simple":[45],"but":[46],"effective":[47],"adaptations":[48],"word":[50],"embedding":[51,73],"tools":[52],"maximize":[54],"the":[55,106],"informative":[56],"content":[57],"leveraged":[58],"in":[59,71,105],"each":[60],"training":[61],"sentence.":[62],"Second,":[63],"analyze":[65,111],"methods":[66],"for":[67],"representing":[68],"one":[72],"space,":[74],"either":[75],"by":[76],"mapping":[77],"individual":[78],"into":[80],"a":[81,86],"shared":[82],"space":[83],"or":[84],"learning":[85],"joint":[87],"model":[88],"all":[90],"dialects.":[91],"Finally,":[92],"evaluate":[94],"via":[95],"dictionary":[96],"induction,":[97],"showing":[98],"that":[99],"two":[100],"metrics":[101],"not":[102],"typically":[103],"reported":[104],"task":[107],"enable":[108],"us":[109],"our":[112],"contributions'":[113],"effects":[114],"low":[116,133],"high":[118,140],"frequency":[119,134,141],"words.":[120],"In":[121],"addition":[122],"boosting":[124],"performance":[125],"between":[126],"2-53%,":[127],"specifically":[129],"improve":[130],"forms":[135],"without":[136],"compromising":[137],"accuracy":[138],"forms.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}