{"id":"https://openalex.org/W2740303418","doi":"https://doi.org/10.18653/v1/w17-1215","title":"Discriminating between Similar Languages with Word-level Convolutional Neural Networks","display_name":"Discriminating between Similar Languages with Word-level Convolutional Neural Networks","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740303418","doi":"https://doi.org/10.18653/v1/w17-1215","mag":"2740303418"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-1215","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1215","pdf_url":"https://www.aclweb.org/anthology/W17-1215.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 Fourth Workshop on NLP for Similar Languages,\n          Varieties and Dialects (VarDial)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-1215.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059281326","display_name":"Marcelo Criscuolo","orcid":"https://orcid.org/0000-0002-6712-146X"},"institutions":[{"id":"https://openalex.org/I4210092357","display_name":"Institute of Mathematics and Computer Science","ror":"https://ror.org/00fy4at53","country_code":"MD","type":"facility","lineage":["https://openalex.org/I112090838","https://openalex.org/I4210092357"]},{"id":"https://openalex.org/I4210157032","display_name":"Institute of Mathematical Sciences","ror":"https://ror.org/05e9bn444","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210157032"]},{"id":"https://openalex.org/I73544541","display_name":"Mathematical Sciences Research Institute","ror":"https://ror.org/05hs5r386","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I73544541"]}],"countries":["ES","MD","US"],"is_corresponding":false,"raw_author_name":"Marcelo Criscuolo","raw_affiliation_strings":["Institute of Mathematical and Computer Sciences University of So Paulo","Institute of Mathematical and Computer Sciences University of S\u00e3o Paulo"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematical and Computer Sciences University of So Paulo","institution_ids":["https://openalex.org/I73544541","https://openalex.org/I4210157032"]},{"raw_affiliation_string":"Institute of Mathematical and Computer Sciences University of S\u00e3o Paulo","institution_ids":["https://openalex.org/I4210092357"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059202822","display_name":"Sandra Maria Alu\u00edsio","orcid":"https://orcid.org/0000-0001-5108-2630"},"institutions":[{"id":"https://openalex.org/I4210092357","display_name":"Institute of Mathematics and Computer Science","ror":"https://ror.org/00fy4at53","country_code":"MD","type":"facility","lineage":["https://openalex.org/I112090838","https://openalex.org/I4210092357"]}],"countries":["MD"],"is_corresponding":true,"raw_author_name":"Sandra Maria Aluisio","raw_affiliation_strings":["Institute of Mathematical and Computer Sciences University of S\u00e3o Paulo"],"affiliations":[{"raw_affiliation_string":"Institute of Mathematical and Computer Sciences University of S\u00e3o Paulo","institution_ids":["https://openalex.org/I4210092357"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059202822"],"corresponding_institution_ids":["https://openalex.org/I4210092357"],"apc_list":null,"apc_paid":null,"fwci":1.6512,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87529189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.8509896397590637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6892935633659363},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6821247339248657},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6590752005577087},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6448602676391602},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6089688539505005},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5734425783157349},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.5456077456474304},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5339248180389404},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5065661668777466},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4755494296550751},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46749842166900635},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07583990693092346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8509896397590637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6892935633659363},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6821247339248657},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6590752005577087},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6448602676391602},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6089688539505005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5734425783157349},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.5456077456474304},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5339248180389404},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5065661668777466},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4755494296550751},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46749842166900635},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07583990693092346},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-1215","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1215","pdf_url":"https://www.aclweb.org/anthology/W17-1215.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 Fourth Workshop on NLP for Similar Languages,\n          Varieties and Dialects (VarDial)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-1215","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1215","pdf_url":"https://www.aclweb.org/anthology/W17-1215.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 Fourth Workshop on NLP for Similar Languages,\n          Varieties and Dialects (VarDial)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740303418.pdf","grobid_xml":"https://content.openalex.org/works/W2740303418.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W92274471","https://openalex.org/W244375653","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1832693441","https://openalex.org/W1966443646","https://openalex.org/W2131744502","https://openalex.org/W2158899491","https://openalex.org/W2250175451","https://openalex.org/W2271840356","https://openalex.org/W2280395961","https://openalex.org/W2525157157","https://openalex.org/W2539338396","https://openalex.org/W2553512497","https://openalex.org/W2561747913","https://openalex.org/W2620806258","https://openalex.org/W2786879936","https://openalex.org/W2949541304","https://openalex.org/W2949952663","https://openalex.org/W2950577311","https://openalex.org/W2952230511","https://openalex.org/W2962875213","https://openalex.org/W2964078312","https://openalex.org/W2964121744","https://openalex.org/W3088953058","https://openalex.org/W4299312355"],"related_works":["https://openalex.org/W1622568043","https://openalex.org/W2056183469","https://openalex.org/W2055565857","https://openalex.org/W4230802329","https://openalex.org/W2151852566","https://openalex.org/W2087366038","https://openalex.org/W4299645117","https://openalex.org/W2164592990","https://openalex.org/W1498610659","https://openalex.org/W2038474459"],"abstract_inverted_index":{"Discriminating":[0],"between":[1,138],"Similar":[2],"Languages":[3],"(DSL)":[4],"is":[5,65],"a":[6,26,66,133],"challenging":[7],"task":[8,24],"addressed":[9],"at":[10],"the":[11,21,30,110,121,127],"VarDial":[12],"Workshop":[13],"series.":[14],"We":[15,48,80],"report":[16],"on":[17],"our":[18],"participation":[19],"in":[20],"DSL":[22],"shared":[23],"with":[25,52,76,83],"two-stage":[27],"system.":[28],"In":[29],"first":[31,114],"stage,":[32],"character":[33],"n-grams":[34],"are":[35],"used":[36],"to":[37,109,136],"separate":[38],"language":[39,46],"groups,":[40],"then":[41],"specialized":[42],"classifiers":[43],"distinguish":[44],"similar":[45,139],"varieties.":[47],"have":[49],"conducted":[50],"experiments":[51],"three":[53],"system":[54,111],"configurations":[55],"and":[56,88,105],"submitted":[57],"one":[58],"run":[59,94],"for":[60],"each.":[61],"Our":[62,92],"main":[63],"approach":[64,135],"word-level":[67],"convolutional":[68],"neural":[69],"network":[70],"(CNN)":[71],"that":[72,112],"learns":[73],"task-specific":[74],"vectors":[75],"minimal":[77],"text":[78],"preprocessing.":[79],"also":[81],"experiment":[82],"multi-layer":[84],"perceptron":[85],"(MLP)":[86],"networks":[87],"another":[89],"hybrid":[90],"configuration.":[91],"best":[93,128],"achieved":[95],"an":[96],"accuracy":[97],"of":[98],"90.76%,":[99],"ranking":[100],"8th":[101],"among":[102],"11":[103],"participants":[104],"getting":[106],"very":[107],"close":[108],"ranked":[113],"(less":[115],"than":[116],"2":[117],"points).":[118],"Even":[119],"though":[120],"CNN":[122],"model":[123],"could":[124],"not":[125],"achieve":[126],"results,":[129],"it":[130],"still":[131],"makes":[132],"viable":[134],"discriminating":[137],"languages.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}