{"id":"https://openalex.org/W2168677000","doi":"https://doi.org/10.3115/v1/p14-2125","title":"Sentence Level Dialect Identification for Machine Translation System Selection","display_name":"Sentence Level Dialect Identification for Machine Translation System Selection","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2168677000","doi":"https://doi.org/10.3115/v1/p14-2125","mag":"2168677000"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-2125","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2125","pdf_url":"https://aclanthology.org/P14-2125.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 52nd 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://aclanthology.org/P14-2125.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060898802","display_name":"Wael Salloum","orcid":null},"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"]},{"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":true,"raw_author_name":"Wael Salloum","raw_affiliation_strings":["\u2020Department of Computer Science, The George Washington University, Washington DC, USA","Center for Computational Learning Systems, Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"\u2020Department of Computer Science, The George Washington University, Washington DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Center for Computational Learning Systems, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077304103","display_name":"Heba Elfardy","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"]},{"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":"Heba Elfardy","raw_affiliation_strings":["Center for Computational Learning Systems, Columbia University, New York, USA","\u2020Department of Computer Science, The George Washington University, Washington DC, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computational Learning Systems, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"\u2020Department of Computer Science, The George Washington University, Washington DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027078335","display_name":"Linda Alamir-Salloum","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"]},{"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":"Linda Alamir-Salloum","raw_affiliation_strings":["\u2020Department of Computer Science, The George Washington University, Washington DC, USA","Center for Computational Learning Systems, Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"\u2020Department of Computer Science, The George Washington University, Washington DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Center for Computational Learning Systems, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"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"]},{"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":"Nizar Habash","raw_affiliation_strings":["\u2020Department of Computer Science, The George Washington University, Washington DC, USA","Center for Computational Learning Systems, Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"\u2020Department of Computer Science, The George Washington University, Washington DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Center for Computational Learning Systems, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"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/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]},{"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":["\u2020Department of Computer Science, The George Washington University, Washington DC, USA","Center for Computational Learning Systems, Columbia University, New York, USA"],"affiliations":[{"raw_affiliation_string":"\u2020Department of Computer Science, The George Washington University, Washington DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Center for Computational Learning Systems, Columbia University, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060898802"],"corresponding_institution_ids":["https://openalex.org/I193531525","https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":4.9082,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95425564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"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":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9939000010490417,"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":0.773465633392334},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7078423500061035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6682485938072205},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6552302241325378},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6352946758270264},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6018392443656921},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5991512537002563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5849446654319763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3981826901435852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773465633392334},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7078423500061035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6682485938072205},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6552302241325378},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6352946758270264},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6018392443656921},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5991512537002563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849446654319763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3981826901435852},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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":"doi:10.3115/v1/p14-2125","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2125","pdf_url":"https://aclanthology.org/P14-2125.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.656.8117","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.656.8117","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/P/P14/P14-2125.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/p14-2125","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2125","pdf_url":"https://aclanthology.org/P14-2125.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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2168677000.pdf","grobid_xml":"https://content.openalex.org/works/W2168677000.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W23077562","https://openalex.org/W137989762","https://openalex.org/W162697342","https://openalex.org/W222053410","https://openalex.org/W1544567521","https://openalex.org/W1631260214","https://openalex.org/W2101105183","https://openalex.org/W2105891181","https://openalex.org/W2109704865","https://openalex.org/W2110660056","https://openalex.org/W2122609803","https://openalex.org/W2124807415","https://openalex.org/W2126784811","https://openalex.org/W2133990480","https://openalex.org/W2137498753","https://openalex.org/W2146574666","https://openalex.org/W2147272182","https://openalex.org/W2156554947","https://openalex.org/W2156985047","https://openalex.org/W2160538511","https://openalex.org/W2162010692","https://openalex.org/W2164503643","https://openalex.org/W2171802951","https://openalex.org/W2250732891","https://openalex.org/W2250822480","https://openalex.org/W2251986002","https://openalex.org/W2394840413","https://openalex.org/W2595715041","https://openalex.org/W2786062171","https://openalex.org/W3170253630"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2375873920","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W2728761353","https://openalex.org/W2883671469"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,33],"study":[4],"the":[5,35,48],"use":[6],"of":[7,37],"sentencelevel":[8],"dialect":[9,20],"identification":[10],"in":[11],"optimizing":[12],"machine":[13,40],"translation":[14,41],"system":[15,52,61],"selection":[16,62],"when":[17],"translating":[18],"mixed":[19],"input.":[21],"We":[22],"test":[23,70],"our":[24],"approach":[25],"on":[26,67],"Arabic,":[27],"a":[28,59,68],"prototypical":[29],"diglossic":[30],"language;":[31],"and":[32,57],"optimize":[34],"combination":[36],"four":[38],"different":[39],"systems.":[42],"Our":[43],"best":[44,49],"result":[45],"improves":[46],"over":[47,58],"single":[50],"MT":[51],"baseline":[53,63],"by":[54,64],"1.0%":[55],"BLEU":[56,66],"strong":[60],"0.6%":[65],"blind":[69],"set.":[71]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}