{"id":"https://openalex.org/W4385573522","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.51","title":"NLP DI at NADI Shared Task Subtask-1: Sub-word Level Convolutional Neural Models and Pre-trained Binary Classifiers for Dialect Identification","display_name":"NLP DI at NADI Shared Task Subtask-1: Sub-word Level Convolutional Neural Models and Pre-trained Binary Classifiers for Dialect Identification","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4385573522","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.51"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.wanlp-1.51","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.51","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.wanlp-1.51","pdf_url":"https://aclanthology.org/2022.wanlp-1.51.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.wanlp-1.51.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101663690","display_name":"Vani Kanjirangat","orcid":"https://orcid.org/0000-0002-2526-1413","observed_orcids":["https://orcid.org/0000-0002-2526-1413"]},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Vani Kanjirangat","raw_affiliation_strings":["IDSIA-USI/SUPSI, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDSIA-USI/SUPSI, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017310324","display_name":"Tanja Samard\u017ci\u0107","orcid":"https://orcid.org/0000-0001-6451-3946","observed_orcids":["https://orcid.org/0000-0001-6451-3946"]},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tanja Samardzic","raw_affiliation_strings":["URPP Language and Space, UZH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"URPP Language and Space, UZH","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063528547","display_name":"Ljiljana Dolamic","orcid":"https://orcid.org/0000-0002-0656-5315","observed_orcids":["https://orcid.org/0000-0002-0656-5315"]},"institutions":[{"id":"https://openalex.org/I4405253476","display_name":"Bundesamt f\u00fcr R\u00fcstung armasuisse","ror":"https://ror.org/00pw7mk43","country_code":"CH","type":"government","lineage":["https://openalex.org/I2801872989","https://openalex.org/I4405253476"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ljiljana Dolamic","raw_affiliation_strings":["armasuisse S+T, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"armasuisse S+T, Switzerland","institution_ids":["https://openalex.org/I4405253476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025307528","display_name":"Fabio Rinaldi","orcid":"https://orcid.org/0000-0001-5718-5462","observed_orcids":["https://orcid.org/0000-0001-5718-5462"]},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabio Rinaldi","raw_affiliation_strings":["IDSIA-USI/SUPSI, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDSIA-USI/SUPSI, Switzerland","institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20865668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"468","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4528999924659729,"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":0.4528999924659729,"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":0.19619999825954437,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.10760000348091125,"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/dialect-identification","display_name":"dialect identification","score":0.9779999852180481},{"id":"https://openalex.org/keywords/bert-fine-tuning","display_name":"BERT fine-tuning","score":0.8450000286102295},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.7179999947547913},{"id":"https://openalex.org/keywords/binary-classifiers","display_name":"binary classifiers","score":0.7990000247955322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781720757484436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7754608988761902},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.691437304019928},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6537318229675293},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6173835396766663},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5634952187538147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5519511103630066},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5404667854309082},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5061392188072205},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5060285925865173},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4926374554634094},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46732938289642334},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.435749351978302},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43104735016822815},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4264032244682312},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4221495985984802},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4216132164001465},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3991282880306244},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1412406861782074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08949211239814758},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2022.wanlp-1.51","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.51","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.wanlp-1.51","pdf_url":"https://aclanthology.org/2022.wanlp-1.51.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.wanlp-1.51","doi":"https://doi.org/10.18653/v1/2022.wanlp-1.51","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2022.wanlp-1.51","pdf_url":"https://aclanthology.org/2022.wanlp-1.51.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385573522.pdf","grobid_xml":"https://content.openalex.org/works/W4385573522.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2109704865","https://openalex.org/W2160802179","https://openalex.org/W2561747913","https://openalex.org/W2799821893","https://openalex.org/W2896457183","https://openalex.org/W2899166839","https://openalex.org/W2914220664","https://openalex.org/W2914798463","https://openalex.org/W2948210185","https://openalex.org/W2951412882","https://openalex.org/W2951559648","https://openalex.org/W2963486098","https://openalex.org/W2970513828","https://openalex.org/W2970814728","https://openalex.org/W2978948973","https://openalex.org/W3008110149","https://openalex.org/W3118759378","https://openalex.org/W3119566336","https://openalex.org/W3119989085","https://openalex.org/W3120373775","https://openalex.org/W3120439194","https://openalex.org/W3120535942","https://openalex.org/W3135784975","https://openalex.org/W3155312056","https://openalex.org/W3155756977","https://openalex.org/W4385573366","https://openalex.org/W4394657514"],"related_works":["https://openalex.org/W4389518440","https://openalex.org/W4385573495","https://openalex.org/W4389518265","https://openalex.org/W3120535942","https://openalex.org/W4385573141","https://openalex.org/W4385573054","https://openalex.org/W4385572949","https://openalex.org/W4385573366","https://openalex.org/W3119370506","https://openalex.org/W3119566336"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,58,100],"describe":[4],"our":[5],"systems":[6],"submitted":[7],"to":[8],"the":[9,49,55,64,73,81,93,97,102,106,132,136,147],"NADI":[10],"Subtask":[11],"1:":[12],"country-wise":[13],"dialect":[14],"classifications.We":[15],"designed":[16],"two":[17],"types":[18],"of":[19,33,54,125,143],"solutions.The":[20],"first":[21],"type":[22,37],"is":[23,38],"convolutional":[24],"neural":[25],"network":[26],"CNN)":[27],"classifiers":[28,40],"trained":[29,109],"on":[30,80,96,110,123,135],"subword":[31,111],"segments":[32],"optimized":[34],"lengths.The":[35],"second":[36],"fine-tuned":[39],"with":[41,48,60,72,105,114,140],"BERT-based":[42],"language":[43,86],"specific":[44,87],"pre-trained":[45,88],"models.To":[46],"deal":[47],"missing":[50,129],"dialects":[51,130,144],"in":[52],"one":[53],"test":[56,94,137],"sets,":[57],"experimented":[59],"binary":[61],"classifiers,":[62],"analyzing":[63],"predicted":[65],"probability":[66],"distribution":[67],"patterns":[68],"and":[69],"comparing":[70],"them":[71],"development":[74,82],"set":[75,83,138,149],"patterns.The":[76],"better":[77],"performing":[78],"approach":[79],"was":[84],"fine-tuning":[85],"model":[89,108,117],"(best":[90],"Fscore":[91],"26.59%).On":[92],"set,":[95],"other":[98],"hand,":[99],"obtained":[101,113],"best":[103,119],"performance":[104,134],"CNN":[107],"tokens":[112],"a":[115,141],"Unigram":[116],"(the":[118],"F-score":[120],"26.12%).Re-training":[121],"models":[122],"samples":[124],"training":[126,148],"data":[127],"simulating":[128],"gave":[131],"maximum":[133],"version":[139],"number":[142],"lesser":[145],"than":[146],"(F-score":[150],"16.44%)":[151]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}