{"id":"https://openalex.org/W2097227294","doi":"https://doi.org/10.3115/v1/w14-5317","title":"Experiments in Sentence Language Identification with Groups of Similar Languages","display_name":"Experiments in Sentence Language Identification with Groups of Similar Languages","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2097227294","doi":"https://doi.org/10.3115/v1/w14-5317","mag":"2097227294"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-5317","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5317","pdf_url":null,"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://doi.org/10.3115/v1/w14-5317","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103532563","display_name":"Ben King","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ben King","raw_affiliation_strings":["(University of Michigan)"],"affiliations":[{"raw_affiliation_string":"(University of Michigan)","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081787254","display_name":"Dragomir Radev","orcid":"https://orcid.org/0000-0001-7830-6489"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dragomir Radev","raw_affiliation_strings":["(University of Michigan)"],"affiliations":[{"raw_affiliation_string":"(University of Michigan)","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021488280","display_name":"Steven Abney","orcid":"https://orcid.org/0000-0002-7467-6690"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Abney","raw_affiliation_strings":["(University of Michigan)"],"affiliations":[{"raw_affiliation_string":"(University of Michigan)","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103532563"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":7.5963,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.97269204,"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":"146","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","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/T12380","display_name":"Authorship Attribution and Profiling","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/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9847999811172485,"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/serbian","display_name":"Serbian","score":0.7831273674964905},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.7741439342498779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7501999139785767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6662328243255615},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6273043751716614},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6151442527770996},{"id":"https://openalex.org/keywords/bosnian","display_name":"Bosnian","score":0.6138690114021301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6045717597007751},{"id":"https://openalex.org/keywords/romanian","display_name":"Romanian","score":0.6010292768478394},{"id":"https://openalex.org/keywords/slovak","display_name":"Slovak","score":0.5856909155845642},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5817797780036926},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.5699437856674194},{"id":"https://openalex.org/keywords/malay","display_name":"Malay","score":0.5691573023796082},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5665010213851929},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.5605524182319641},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5296827554702759},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.47513511776924133},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41516536474227905}],"concepts":[{"id":"https://openalex.org/C2778408831","wikidata":"https://www.wikidata.org/wiki/Q9299","display_name":"Serbian","level":2,"score":0.7831273674964905},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.7741439342498779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501999139785767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6662328243255615},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6273043751716614},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6151442527770996},{"id":"https://openalex.org/C2777914927","wikidata":"https://www.wikidata.org/wiki/Q9303","display_name":"Bosnian","level":2,"score":0.6138690114021301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6045717597007751},{"id":"https://openalex.org/C129400051","wikidata":"https://www.wikidata.org/wiki/Q7913","display_name":"Romanian","level":2,"score":0.6010292768478394},{"id":"https://openalex.org/C2780102689","wikidata":"https://www.wikidata.org/wiki/Q9058","display_name":"Slovak","level":3,"score":0.5856909155845642},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5817797780036926},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.5699437856674194},{"id":"https://openalex.org/C2776938241","wikidata":"https://www.wikidata.org/wiki/Q9237","display_name":"Malay","level":2,"score":0.5691573023796082},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5665010213851929},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.5605524182319641},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5296827554702759},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47513511776924133},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41516536474227905},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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":2,"locations":[{"id":"doi:10.3115/v1/w14-5317","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5317","pdf_url":null,"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:CiteSeerX.psu:10.1.1.679.2440","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.679.2440","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/W14-5317.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-5317","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5317","pdf_url":null,"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":0.7699999809265137,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W213769128","https://openalex.org/W244375653","https://openalex.org/W402546610","https://openalex.org/W968157591","https://openalex.org/W1974288322","https://openalex.org/W2004915807","https://openalex.org/W2107251449","https://openalex.org/W2123660869","https://openalex.org/W2132609289","https://openalex.org/W2140432583","https://openalex.org/W2163614729","https://openalex.org/W2183864645","https://openalex.org/W2251862917","https://openalex.org/W2429914308"],"related_works":["https://openalex.org/W4322005531","https://openalex.org/W2970603448","https://openalex.org/W2907914472","https://openalex.org/W2550694662","https://openalex.org/W4304945117","https://openalex.org/W4389036602","https://openalex.org/W4379434316","https://openalex.org/W4379230072","https://openalex.org/W2053214716","https://openalex.org/W2490249517"],"abstract_inverted_index":{"Language":[0],"identification":[1],"is":[2,41],"a":[3],"simple":[4],"problem":[5],"that":[6],"becomes":[7],"much":[8],"more":[9],"difficult":[10],"when":[11],"its":[12],"usual":[13],"assumptions":[14],"are":[15],"broken.":[16],"In":[17],"this":[18],"paper":[19],"we":[20],"consider":[21],"the":[22,34],"task":[23],"of":[24,28],"classifying":[25],"short":[26],"segments":[27],"text":[29],"in":[30],"closely-related":[31],"languages":[32],"for":[33],"Discriminating":[35],"Similar":[36],"Languages":[37],"shared":[38],"task,":[39],"which":[40],"broken":[42]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
