{"id":"https://openalex.org/W4392305643","doi":"https://doi.org/10.5220/0012307200003636","title":"A Challenging Data Set for Evaluating Part-of-Speech Taggers","display_name":"A Challenging Data Set for Evaluating Part-of-Speech Taggers","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392305643","doi":"https://doi.org/10.5220/0012307200003636"},"language":"en","primary_location":{"id":"doi:10.5220/0012307200003636","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012307200003636","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0012307200003636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028236337","display_name":"Mattias Wahde","orcid":"https://orcid.org/0000-0001-6679-637X"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Mattias Wahde","raw_affiliation_strings":["Chalmers University of Technology, SE-412 96 Gothenburg, Sweden, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, SE-412 96 Gothenburg, Sweden, --- Select a Country ---","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092241314","display_name":"Minerva Suvanto","orcid":"https://orcid.org/0009-0003-1751-151X"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Minerva Suvanto","raw_affiliation_strings":["Chalmers University of Technology, SE-412 96 Gothenburg, Sweden, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, SE-412 96 Gothenburg, Sweden, --- Select a Country ---","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108167393","display_name":"Marco L. Della Vedova","orcid":"https://orcid.org/0000-0002-4703-7500"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Marco Vedova","raw_affiliation_strings":["Chalmers University of Technology, SE-412 96 Gothenburg, Sweden, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, SE-412 96 Gothenburg, Sweden, --- Select a Country ---","institution_ids":["https://openalex.org/I66862912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028236337"],"corresponding_institution_ids":["https://openalex.org/I66862912"],"apc_list":null,"apc_paid":null,"fwci":0.3636,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61830239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"86"},"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9962999820709229,"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":0.8793475031852722},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.818966269493103},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6918010115623474},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6798847913742065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6693709492683411},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6413881182670593},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.625344455242157},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.6242409348487854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6077961325645447},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.502530574798584},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43800896406173706},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41639888286590576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41581061482429504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05603352189064026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8793475031852722},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.818966269493103},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6918010115623474},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6798847913742065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6693709492683411},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6413881182670593},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.625344455242157},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.6242409348487854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6077961325645447},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.502530574798584},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43800896406173706},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41639888286590576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41581061482429504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05603352189064026},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0012307200003636","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012307200003636","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:research.chalmers.se:540882","is_oa":true,"landing_page_url":"https://research.chalmers.se/en/publication/66fa6351-6aec-4ac7-834c-2586d7ffee64","pdf_url":"https://research.chalmers.se/publication/540882/file/540882_Fulltext.pdf","source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:research.chalmers.se:540190","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/540190","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.5220/0012307200003636","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012307200003636","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1515847863","https://openalex.org/W1623072288","https://openalex.org/W1899794420","https://openalex.org/W1996430422","https://openalex.org/W2143995218","https://openalex.org/W2153862129","https://openalex.org/W2880875857","https://openalex.org/W2950121111","https://openalex.org/W2964185534","https://openalex.org/W4206965408","https://openalex.org/W4250788613","https://openalex.org/W4385571365","https://openalex.org/W4386694320"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2786391746","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W2991483587","https://openalex.org/W2971899271","https://openalex.org/W1990237101"],"abstract_inverted_index":{"We":[0,101],"introduce":[1],"a":[2,66,107],"novel,":[3],"challenging":[4,71],"test":[5,35],"set":[6,36],"for":[7,37,65,121,134],"part-of-speech":[8],"(POS)":[9],"tagging,":[10,92],"consisting":[11],"of":[12,53,73,90,106,118,140],"sentences":[13],"in":[14,98,130,143],"which":[15],"only":[16],"one":[17,52],"word":[18,62],"is":[19,30],"POS-tagged.":[20],"First":[21],"derived":[22],"from":[23],"Wiktionary,":[24],"and":[25,93],"then":[26],"manually":[27],"curated,":[28],"it":[29],"intended":[31],"as":[32],"an":[33,116],"out-of-sample":[34,123],"POS":[38,74,91,110],"taggers":[39,57,83],"trained":[40],"over":[41,112],"larger":[42],"data":[43],"sets.":[44],"Sentences":[45],"were":[46],"selected":[47],"such":[48],"that":[49,80],"at":[50],"least":[51],"four":[54],"standard":[55],"benchmark":[56,82],"would":[58],"incorrectly":[59],"tag":[60],"the":[61,81,104,131],"under":[63],"consideration":[64],"given":[67],"sentence,":[68],"thus":[69],"identifying":[70],"instances":[72,89,139],"tagging.":[75],"Somewhat":[76],"surprisingly,":[77],"we":[78,94,137],"find":[79,138],"often":[84],"fail":[85],"on":[86],"rather":[87,144],"straightforward":[88],"analyze":[95],"these":[96],"failures":[97],"some":[99],"detail.":[100],"also":[102],"compute":[103],"performance":[105,129],"state-of-the-art":[108],"DNN-based":[109],"tagger":[111],"our":[113],"set,":[114],"obtaining":[115],"accuracy":[117],"around":[119],"0.87":[120],"this":[122,135],"test,":[124],"far":[125],"below":[126],"its":[127],"reported":[128],"literature.":[132],"Also":[133],"tagger,":[136],"failure":[141],"even":[142],"simple":[145],"cases.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}