{"id":"https://openalex.org/W2740917210","doi":"https://doi.org/10.18653/v1/w17-1213","title":"A Perplexity-Based Method for Similar Languages Discrimination","display_name":"A Perplexity-Based Method for Similar Languages Discrimination","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740917210","doi":"https://doi.org/10.18653/v1/w17-1213","mag":"2740917210"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-1213","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1213","pdf_url":"https://www.aclweb.org/anthology/W17-1213.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/W17-1213.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063153446","display_name":"Pablo Gamallo","orcid":"https://orcid.org/0000-0002-5819-2469"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Gamallo","raw_affiliation_strings":["Univ. of Santiago de Compostela Galiza"],"affiliations":[{"raw_affiliation_string":"Univ. of Santiago de Compostela Galiza","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000537188","display_name":"Jos\u00e9 Ramom Pichel Campos","orcid":"https://orcid.org/0000-0001-5172-6803"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jose Ramom Pichel","raw_affiliation_strings":["imaxin|software, Santiago de Compostela, Galiza"],"affiliations":[{"raw_affiliation_string":"imaxin|software, Santiago de Compostela, Galiza","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027820865","display_name":"I\u00f1aki Alegria","orcid":"https://orcid.org/0000-0002-0272-1472"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"I\u00f1aki Alegria","raw_affiliation_strings":["IXA group Univ. of the Basque Country UPV/EHU"],"affiliations":[{"raw_affiliation_string":"IXA group Univ. of the Basque Country UPV/EHU","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000537188"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3238,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93812195,"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":"109","last_page":"114"},"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":0.9994000196456909,"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":0.996999979019165,"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/perplexity","display_name":"Perplexity","score":0.9901336431503296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8338022232055664},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7593163847923279},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6466565728187561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6075183153152466},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5968921184539795},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.5540317296981812},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.5237545967102051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4493579566478729},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1755342185497284}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9901336431503296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8338022232055664},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7593163847923279},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6466565728187561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6075183153152466},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5968921184539795},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.5540317296981812},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.5237545967102051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4493579566478729},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1755342185497284},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/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/w17-1213","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1213","pdf_url":"https://www.aclweb.org/anthology/W17-1213.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/w17-1213","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-1213","pdf_url":"https://www.aclweb.org/anthology/W17-1213.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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5299999713897705},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G2278230719","display_name":null,"funder_award_id":"ED431G/08","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G2631452109","display_name":null,"funder_award_id":"(ERDF)","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5452741828","display_name":null,"funder_award_id":"2016-2019","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6701530383","display_name":null,"funder_award_id":"2016 BBVA","funder_id":"https://openalex.org/F4320323113","funder_display_name":"Banco Bilbao Vizcaya Argentaria"}],"funders":[{"id":"https://openalex.org/F4320309764","display_name":"Fundaci\u00f3n BBVA","ror":"https://ror.org/01jzs3b90"},{"id":"https://openalex.org/F4320323113","display_name":"Banco Bilbao Vizcaya Argentaria","ror":"https://ror.org/0537dnd74"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740917210.pdf","grobid_xml":"https://content.openalex.org/works/W2740917210.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1791088224","https://openalex.org/W2097927681","https://openalex.org/W2137698233","https://openalex.org/W2162019804","https://openalex.org/W2295824561","https://openalex.org/W2525157157","https://openalex.org/W2553512497","https://openalex.org/W2561747913","https://openalex.org/W2620806258","https://openalex.org/W2733060938","https://openalex.org/W2785973019","https://openalex.org/W2787236793","https://openalex.org/W2949541304","https://openalex.org/W2949952663","https://openalex.org/W2950186769"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2020757772","https://openalex.org/W2902731467"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"the":[3,7,13,75,100],"system":[4,24,47],"submitted":[5],"by":[6,32],"Citius":[8],"Ixa":[9],"Imaxin":[10],"team":[11],"to":[12,65,97],"VarDial":[14],"2017":[15],"(DSL":[16],"and":[17,57],"GDI":[18],"tasks).":[19],"The":[20,37],"strategy":[21],"underlying":[22],"our":[23],"is":[25,44],"based":[26],"on":[27],"a":[28,45,67],"language":[29],"distance":[30],"computed":[31],"means":[33],"of":[34,50,54],"model":[35,39,70],"perplexity.":[36],"best":[38],"configuration":[40],"we":[41,77,88],"have":[42,78],"tested":[43],"voting":[46],"making":[48],"use":[49],"several":[51],"n-grams":[52],"models":[53],"both":[55],"words":[56],"characters,":[58],"even":[59],"if":[60],"word":[61],"unigrams":[62],"turned":[63],"out":[64],"be":[66],"very":[68],"competitive":[69],"with":[71,93],"reasonable":[72],"results":[73],"in":[74,86],"tasks":[76],"participated.":[79],"An":[80],"error":[81],"analysis":[82],"has":[83],"been":[84],"performed":[85],"which":[87],"identified":[89],"many":[90],"test":[91],"examples":[92],"no":[94],"linguistic":[95],"evidences":[96],"distinguish":[98],"among":[99],"variants.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4}],"updated_date":"2026-03-16T09:10:04.655348","created_date":"2025-10-10T00:00:00"}