{"id":"https://openalex.org/W3197349059","doi":"https://doi.org/10.1007/978-3-030-83527-9_19","title":"Introducing NYTK-NerKor, A Gold Standard Hungarian Named Entity Annotated Corpus","display_name":"Introducing NYTK-NerKor, A Gold Standard Hungarian Named Entity Annotated Corpus","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3197349059","doi":"https://doi.org/10.1007/978-3-030-83527-9_19","mag":"3197349059"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-83527-9_19","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-83527-9_19","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-030-83527-9_19","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052133748","display_name":"Eszter Simon","orcid":"https://orcid.org/0000-0001-7496-7634"},"institutions":[{"id":"https://openalex.org/I2802350943","display_name":"ELTE Hungarian Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Eszter Simon","raw_affiliation_strings":["Hungarian Research Centre for Linguistics, Budapest, Hungary","Hungarian Research Centre for Linguistics"],"affiliations":[{"raw_affiliation_string":"Hungarian Research Centre for Linguistics, Budapest, Hungary","institution_ids":["https://openalex.org/I2802350943"]},{"raw_affiliation_string":"Hungarian Research Centre for Linguistics","institution_ids":["https://openalex.org/I2802350943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015377592","display_name":"No\u00e9mi Vad\u00e1sz","orcid":null},"institutions":[{"id":"https://openalex.org/I2802350943","display_name":"ELTE Hungarian Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"No\u00e9mi Vad\u00e1sz","raw_affiliation_strings":["Hungarian Research Centre for Linguistics, Budapest, Hungary","Hungarian Research Centre for Linguistics"],"affiliations":[{"raw_affiliation_string":"Hungarian Research Centre for Linguistics, Budapest, Hungary","institution_ids":["https://openalex.org/I2802350943"]},{"raw_affiliation_string":"Hungarian Research Centre for Linguistics","institution_ids":["https://openalex.org/I2802350943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015377592","https://openalex.org/A5052133748"],"corresponding_institution_ids":["https://openalex.org/I2802350943"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":3.0961,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93155627,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"234"},"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/T10028","display_name":"Topic Modeling","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/T13629","display_name":"Text Readability and Simplification","score":0.9121000170707703,"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":0.8846373558044434},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8145129680633545},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6015903353691101},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.568478524684906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5380245447158813},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5004405975341797},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4329512417316437},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.41588473320007324},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12976974248886108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8846373558044434},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8145129680633545},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6015903353691101},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.568478524684906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5380245447158813},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5004405975341797},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4329512417316437},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.41588473320007324},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12976974248886108},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-83527-9_19","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-83527-9_19","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-83527-9_19","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-83527-9_19","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W50420911","https://openalex.org/W1532548519","https://openalex.org/W1625582487","https://openalex.org/W1846321791","https://openalex.org/W1967169497","https://openalex.org/W2144578941","https://openalex.org/W2213450577","https://openalex.org/W2484884186","https://openalex.org/W2578622609","https://openalex.org/W2758799719","https://openalex.org/W2775590885","https://openalex.org/W2806481024","https://openalex.org/W2915429162","https://openalex.org/W2951166594","https://openalex.org/W2964927090","https://openalex.org/W2970279348","https://openalex.org/W3215499059","https://openalex.org/W6767250937"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W3126131230","https://openalex.org/W2347541121","https://openalex.org/W4288804799","https://openalex.org/W2080951048","https://openalex.org/W3089617106","https://openalex.org/W3032237421","https://openalex.org/W3011883280","https://openalex.org/W2390346111","https://openalex.org/W2369082698"],"abstract_inverted_index":{"Here":[0],"we":[1],"present":[2],"NYTK-NerKor,":[3],"a":[4,61,68,88],"gold":[5,45],"standard":[6,46],"Hungarian":[7],"named":[8],"entity":[9],"annotated":[10,79],"corpus":[11,20,167],"containing":[12,149],"1":[13],"million":[14],"tokens.":[15],"This":[16],"is":[17,81,112,134,168],"the":[18,77,101,105,115,171],"largest":[19],"ever":[21],"in":[22,60,84,87,99,161],"its":[23,162,176],"kind.":[24],"It":[25],"contains":[26,44],"balanced":[27,69,89],"text":[28,150],"selection":[29,70],"from":[30,71,152,175],"five":[31],"genres:":[32],"fiction,":[33],"legal,":[34],"news,":[35],"web,":[36],"and":[37,57,74,121,155,157,164],"Wikipedia.":[38],"A":[39],"ca.":[40],"200,000":[41],"tokens":[42],"subcorpus":[43,80],"morphological":[47,110],"annotation":[48,103],"besides":[49],"NE":[50,102],"labels.":[51],"We":[52],"provide":[53,67],"official":[54],"train,":[55],"development":[56],"test":[58],"datasets":[59],"proportion":[62],"of":[63,93,126,141],"80%-10%-10%.":[64],"All":[65],"sets":[66,86],"all":[72,85],"genres":[73,154],"sources,":[75,156],"while":[76,109],"morphologically":[78],"also":[82],"represented":[83],"way.":[90],"The":[91,124,166],"format":[92,163],"data":[94],"files":[95],"are":[96],"CoNLL-U":[97],"Plus,":[98],"which":[100],"follows":[104],"CoNLL2002":[106],"labelling":[107],"standard,":[108],"information":[111],"encoded":[113],"using":[114],"well-known":[116],"Universal":[117],"Dependencies":[118],"POS":[119],"tags":[120],"morphosyntactic":[122],"features.":[123],"novelty":[125],"NYTK-NerKor":[127],"as":[128],"opposed":[129],"to":[130],"similar":[131],"existing":[132],"corpora":[133],"that":[135],"it":[136],"is:":[137],"by":[138],"an":[139],"order":[140],"magnitude":[142],"larger,":[143],"freely":[144],"available":[145,169],"for":[146],"any":[147],"purposes,":[148],"material":[151],"different":[153],"following":[158],"international":[159],"standards":[160],"tagset.":[165],"under":[170],"license":[172],"CC-BY-SA":[173],"4.0":[174],"GitHub":[177],"repository:":[178],"https://github.com/nytud/NYTK-NerKor.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}