{"id":"https://openalex.org/W2251071163","doi":"https://doi.org/10.3115/v1/w14-5316","title":"The NRC System for Discriminating Similar Languages","display_name":"The NRC System for Discriminating Similar Languages","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251071163","doi":"https://doi.org/10.3115/v1/w14-5316","mag":"2251071163"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-5316","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5316","pdf_url":"https://aclanthology.org/W14-5316.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 First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-5316.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065257553","display_name":"Cyril Goutte","orcid":"https://orcid.org/0000-0003-4939-6555"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Cyril Goutte","raw_affiliation_strings":["Multilingual Text Processing National Research Council Canada Ottawa, ON K1A0R6"],"affiliations":[{"raw_affiliation_string":"Multilingual Text Processing National Research Council Canada Ottawa, ON K1A0R6","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108724394","display_name":"Serge L\u00e9ger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Serge L\u00e9ger","raw_affiliation_strings":["Multilingual Text Processing National Research Council Canada Ottawa, ON K1A0R6"],"affiliations":[{"raw_affiliation_string":"Multilingual Text Processing National Research Council Canada Ottawa, ON K1A0R6","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078390032","display_name":"Marine Carpuat","orcid":"https://orcid.org/0000-0003-1693-0782"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marine Carpuat","raw_affiliation_strings":["Multilingual Text Processing National Research Council Canada Ottawa, ON K1A0R6"],"affiliations":[{"raw_affiliation_string":"Multilingual Text Processing National Research Council Canada Ottawa, ON K1A0R6","institution_ids":["https://openalex.org/I4210159778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065257553"],"corresponding_institution_ids":["https://openalex.org/I4210159778"],"apc_list":null,"apc_paid":null,"fwci":15.2227,"has_fulltext":true,"cited_by_count":57,"citation_normalized_percentile":{"value":0.99066545,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"139","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.998199999332428,"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":0.7262476086616516},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7184804081916809},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6533839702606201},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6255656480789185},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5641725659370422},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4928913116455078},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.4879600405693054},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.4781269133090973},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4651632606983185},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4331413507461548},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.4179227948188782},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17127293348312378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262476086616516},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7184804081916809},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6533839702606201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6255656480789185},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5641725659370422},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4928913116455078},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.4879600405693054},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.4781269133090973},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4651632606983185},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4331413507461548},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4179227948188782},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17127293348312378},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/v1/w14-5316","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5316","pdf_url":"https://aclanthology.org/W14-5316.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 First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:21275282","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/fra/voir/objet/?id=bd4a662e-ed67-47ef-8165-abde04de494c","pdf_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=bd4a662e-ed67-47ef-8165-abde04de494c","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.678.515","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.678.515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-5316.pdf","raw_type":"text"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:21275281","is_oa":false,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=1d8527ac-4ebe-42d3-a94e-953c17f86e0c","pdf_url":null,"source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"address"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-5316","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5316","pdf_url":"https://aclanthology.org/W14-5316.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 First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251071163.pdf","grobid_xml":"https://content.openalex.org/works/W2251071163.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W106310140","https://openalex.org/W137989762","https://openalex.org/W162697342","https://openalex.org/W244375653","https://openalex.org/W1494021613","https://openalex.org/W1550206324","https://openalex.org/W1612003148","https://openalex.org/W2049633694","https://openalex.org/W2089086886","https://openalex.org/W2149684865","https://openalex.org/W2162019804","https://openalex.org/W2177050153","https://openalex.org/W2181262297","https://openalex.org/W4255244004"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W4396941953","https://openalex.org/W2987280934","https://openalex.org/W4241564561","https://openalex.org/W1487808658"],"abstract_inverted_index":{"We":[0],"describe":[1],"the":[2,6,12,37,47,61,100,108,116],"system":[3,21],"built":[4],"by":[5],"National":[7],"Research":[8],"Council":[9],"Canada":[10],"for":[11],"\"Discriminating":[13],"between":[14,42,94],"similar":[15],"languages\"":[16],"(DSL)":[17],"shared":[18],"task.":[19],"Our":[20],"uses":[22],"various":[23],"statistical":[24],"classifiers":[25,77],"and":[26,96,118],"makes":[27],"predictions":[28],"based":[29],"on":[30,60,79,99],"a":[31,54,72,80],"two-stage":[32],"process:":[33],"we":[34,70],"first":[35],"predict":[36],"language":[38],"group,":[39],"then":[40],"discriminate":[41],"languages":[43],"or":[44],"variants":[45],"within":[46],"group.":[48,101],"Language":[49],"groups":[50],"are":[51],"predicted":[52],"using":[53],"generative":[55],"classifier":[56],"with":[57,91],"99.99%":[58],"accuracy":[59,88,93],"five":[62],"target":[63],"groups.":[64],"Within":[65],"each":[66],"group":[67],"(except":[68],"English),":[69],"use":[71],"voting":[73],"combination":[74],"of":[75,82,89],"discriminative":[76],"trained":[78],"variety":[81],"feature":[83],"spaces,":[84],"achieving":[85],"an":[86],"average":[87],"95.71%,":[90],"per-group":[92],"90.95%":[95],"100%":[97],"depending":[98],"This":[102],"approach":[103],"turns":[104],"out":[105],"to":[106,115],"reach":[107],"best":[109],"performance":[110],"among":[111],"all":[112],"systems":[113],"submitted":[114],"open":[117],"closed":[119],"tasks.":[120]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}