{"id":"https://openalex.org/W2250320249","doi":"https://doi.org/10.3115/v1/w14-5309","title":"Part-of-Speech Tag Disambiguation by Cross-Linguistic Majority Vote","display_name":"Part-of-Speech Tag Disambiguation by Cross-Linguistic Majority Vote","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250320249","doi":"https://doi.org/10.3115/v1/w14-5309","mag":"2250320249"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-5309","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5309","pdf_url":"https://aclanthology.org/W14-5309.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","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-5309.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047249362","display_name":"No\u00ebmi Aepli","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"No\u00ebmi Aepli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016371704","display_name":"Ruprecht von Waldenfels","orcid":"https://orcid.org/0000-0001-5822-5040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruprecht von Waldenfels","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017310324","display_name":"Tanja Samard\u017ci\u0107","orcid":"https://orcid.org/0000-0001-6451-3946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanja Samard\u017ei\u0107","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047249362"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9832,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92607094,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9927999973297119,"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/macedonian","display_name":"Macedonian","score":0.8905754089355469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.860649585723877},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7513375282287598},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6818008422851562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6497554779052734},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6071566939353943},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.545005738735199},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5335657596588135},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5254613161087036},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5015971660614014},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4475399851799011},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2160780429840088},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09356638789176941}],"concepts":[{"id":"https://openalex.org/C2777642646","wikidata":"https://www.wikidata.org/wiki/Q9296","display_name":"Macedonian","level":2,"score":0.8905754089355469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.860649585723877},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7513375282287598},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6818008422851562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6497554779052734},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6071566939353943},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.545005738735199},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5335657596588135},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5254613161087036},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5015971660614014},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4475399851799011},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2160780429840088},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09356638789176941},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-5309","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5309","pdf_url":"https://aclanthology.org/W14-5309.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:www.zora.uzh.ch:127261","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Aepli, No\u00ebmi; von Waldenfels, Ruprecht; Samard\u017ei\u0107, Tanja  (2014). Part-of-Speech Tag Disambiguation by Cross-Linguistic Majority Vote.  In: First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects, Dublin, Ireland, 23 August 2014, Proceedings of the First Workshop on Applying NLP Tools to Similar Languages.","raw_type":"Conference or Workshop Item"},{"id":"doi:10.5167/uzh-127261","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-127261","pdf_url":null,"source":{"id":"https://openalex.org/S7407051291","display_name":"Universit\u00e4t Z\u00fcrich, ZORA","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.3115/v1/w14-5309","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5309","pdf_url":"https://aclanthology.org/W14-5309.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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250320249.pdf","grobid_xml":"https://content.openalex.org/works/W2250320249.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W418403830","https://openalex.org/W2016630033","https://openalex.org/W2072291547","https://openalex.org/W2084499688","https://openalex.org/W2111283389","https://openalex.org/W2143081933","https://openalex.org/W2156985047","https://openalex.org/W2339852109","https://openalex.org/W2758240489"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W2971899271","https://openalex.org/W1972167985","https://openalex.org/W2350644419","https://openalex.org/W3165517033"],"abstract_inverted_index":{"In":[0,29],"this":[1],"paper,":[2],"we":[3,31],"present":[4],"an":[5],"approach":[6,34,76,131],"to":[7,24,50,141],"developing":[8],"resources":[9,126],"for":[10,40,60,122,127],"a":[11,70,87,96,119],"low-resource":[12],"language,":[13],"taking":[14],"advantage":[15],"of":[16,72,89,95,104,113,125],"the":[17,56,100,111],"fact":[18],"that":[19],"it":[20,136],"is":[21,77,107,132],"closely":[22],"related":[23],"languages":[25],"with":[26],"more":[27],"resources.":[28],"particular,":[30],"test":[32],"our":[33],"on":[35,79,99],"Macedonian,":[36],"which":[37],"lacks":[38],"tools":[39],"natural":[41],"language":[42,143],"processing":[43],"as":[44,46,118],"well":[45],"data":[47,102],"in":[48,144],"order":[49],"build":[51],"such":[52],"tools.":[53],"We":[54],"improve":[55],"Macedonian":[57],"training":[58],"set":[59,88,103],"supervised":[61],"part-ofspeech":[62],"tagging":[63],"by":[64],"transferring":[65],"available":[66],"manual":[67],"annotations":[68],"from":[69],"number":[71],"similar":[73,145],"languages.":[74],"Our":[75],"based":[78],"multilingual":[80],"parallel":[81],"corpora,":[82],"automatic":[83,134],"word":[84],"alignment,":[85],"and":[86,135],"rules":[90],"(majority":[91],"vote).":[92],"The":[93,129],"performance":[94],"tagger":[97],"trained":[98],"improved":[101],"88%":[105],"accuracy":[106],"significantly":[108],"better":[109],"than":[110],"baseline":[112],"76%.":[114],"It":[115],"can":[116,137],"serve":[117],"stepping":[120],"stone":[121],"further":[123],"improvement":[124],"Macedonian.":[128],"proposed":[130],"entirely":[133],"be":[138],"easily":[139],"adapted":[140],"other":[142],"circumstances.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}