{"id":"https://openalex.org/W2980693453","doi":"https://doi.org/10.1145/3350546.3352543","title":"Design and implementation of an open source Greek POS Tagger and Entity Recognizer using spaCy","display_name":"Design and implementation of an open source Greek POS Tagger and Entity Recognizer using spaCy","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2980693453","doi":"https://doi.org/10.1145/3350546.3352543","mag":"2980693453"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3350546.3352543","pdf_url":null,"source":{"id":"https://openalex.org/S4363608074","display_name":"IEEE/WIC/ACM International Conference on Web Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/1912.10162","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020524648","display_name":"Eleni Partalidou","orcid":null},"institutions":[],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Eleni Partalidou","raw_affiliation_strings":["DataScouting, Greece"],"affiliations":[{"raw_affiliation_string":"DataScouting, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009239738","display_name":"Eleftherios Spyromitros-Xioufis","orcid":"https://orcid.org/0000-0001-9178-8603"},"institutions":[],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Eleftherios Spyromitros-Xioufis","raw_affiliation_strings":["DataScouting, Greece"],"affiliations":[{"raw_affiliation_string":"DataScouting, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049192036","display_name":"Stavros Doropoulos","orcid":null},"institutions":[],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stavros Doropoulos","raw_affiliation_strings":["DataScouting, Greece"],"affiliations":[{"raw_affiliation_string":"DataScouting, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039053440","display_name":"Stavros Vologiannidis","orcid":"https://orcid.org/0000-0003-2945-0841"},"institutions":[{"id":"https://openalex.org/I183898223","display_name":"International Hellenic University","ror":"https://ror.org/00708jp83","country_code":"GR","type":"education","lineage":["https://openalex.org/I183898223"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stavros Vologiannidis","raw_affiliation_strings":["Dpt of Computer, Informatics and Telecommunications Engineering, International Hellenic University, Greece"],"affiliations":[{"raw_affiliation_string":"Dpt of Computer, Informatics and Telecommunications Engineering, International Hellenic University, Greece","institution_ids":["https://openalex.org/I183898223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047747213","display_name":"Konstantinos Diamantaras","orcid":"https://orcid.org/0000-0003-1373-4022"},"institutions":[],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Diamantaras","raw_affiliation_strings":["DataScouting, Greece"],"affiliations":[{"raw_affiliation_string":"DataScouting, Greece","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.386,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.756592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":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":0.9999,"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":0.9887,"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/feature","display_name":"Feature (linguistics)","score":0.53670824},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.51106536},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named Entity Recognition","score":0.50182676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.88296866},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6506637},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.64137983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6392884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5961278},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.56656075},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.53670824},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.51106536},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.50182676},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.48507252},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.45433787},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.44695106},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.431263},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42764974},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14678949},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14352772},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09395018},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3350546.3352543","pdf_url":null,"source":{"id":"https://openalex.org/S4363608074","display_name":"IEEE/WIC/ACM International Conference on Web Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.10162","pdf_url":"http://arxiv.org/pdf/1912.10162","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.10162","pdf_url":"http://arxiv.org/pdf/1912.10162","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.6}],"grants":[{"funder":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020","award_id":null}],"datasets":[],"versions":[],"referenced_works_count":7,"referenced_works":["https://openalex.org/W189286601","https://openalex.org/W2493916176","https://openalex.org/W2710777912","https://openalex.org/W2963667932","https://openalex.org/W2963863756","https://openalex.org/W4285719527","https://openalex.org/W89689174"],"related_works":["https://openalex.org/W632256878","https://openalex.org/W4311938462","https://openalex.org/W3199871245","https://openalex.org/W3198729192","https://openalex.org/W2915436880","https://openalex.org/W2491403535","https://openalex.org/W2479811461","https://openalex.org/W2113128227","https://openalex.org/W2104915799","https://openalex.org/W1964783010"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,28,57,74,109],"machine":[4],"learning":[5],"approach":[6],"to":[7],"part-of-speech":[8],"tagging":[9],"and":[10,23,66,89,135],"named":[11,34,104],"entity":[12,105],"recognition":[13,106],"for":[14,33,69,130,140],"Greek,":[15],"focusing":[16],"on":[17],"the":[18,48,54,71,84,87,93,99,113,128,145],"extraction":[19],"of":[20,25,31,47,76,86,101],"morphological":[21],"features":[22],"classification":[24],"tokens":[26,88],"into":[27,53],"small":[29],"set":[30],"classes":[32],"entities.":[35],"The":[36,44],"architecture":[37],"model":[38,110],"that":[39,59,81,111,124],"was":[40,51,67,79,120],"used":[41,68],"is":[42,137],"introduced.":[43],"greek":[45],"version":[46],"spaCy":[49],"platform":[50],"added":[52],"source":[55],"code,":[56],"feature":[58],"did":[60],"not":[61],"exist":[62],"before":[63],"our":[64],"contribution,":[65],"building":[70],"models.":[72],"Additionally,":[73],"part":[75,100],"speech":[77],"tagger":[78],"trained":[80],"can":[82],"detect":[83],"morphology":[85],"performs":[90],"higher":[91],"than":[92],"state-of-the-art":[94],"results":[95,147],"when":[96],"classifying":[97],"only":[98],"speech.":[102],"For":[103],"using":[107],"spaCy,":[108],"extends":[112],"standard":[114],"ENAMEX":[115],"type":[116],"(organization,":[117],"location,":[118],"person)":[119],"built.":[121],"Certain":[122],"experiments":[123],"were":[125],"conducted":[126],"indicate":[127],"need":[129],"flexibility":[131],"in":[132],"out-of-vocabulary":[133],"words":[134],"there":[136],"an":[138],"effort":[139],"resolving":[141],"this":[142],"issue.":[143],"Finally,":[144],"evaluation":[146],"are":[148],"discussed.":[149]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2980693453","counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5}],"updated_date":"2025-03-15T15:38:14.028369","created_date":"2019-10-25"}