{"id":"https://openalex.org/W2163708215","doi":"https://doi.org/10.1109/imcsit.2010.5680057","title":"Tools and methodologies for annotating syntax and named entities in the National Corpus of Polish","display_name":"Tools and methodologies for annotating syntax and named entities in the National Corpus of Polish","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2163708215","doi":"https://doi.org/10.1109/imcsit.2010.5680057","mag":"2163708215"},"language":"en","primary_location":{"id":"doi:10.1109/imcsit.2010.5680057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/imcsit.2010.5680057","pdf_url":null,"source":{"id":"https://openalex.org/S4210192132","display_name":"Proceedings of the International Multiconference on Computer Science and Information Technology","issn_l":"1896-7094","issn":["1896-7094","2157-5525","2157-5533"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Multiconference on Computer Science and Information Technology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086416584","display_name":"Jakub Waszczuk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I47996466","display_name":"University of Warmia and Mazury in Olsztyn","ror":"https://ror.org/05s4feg49","country_code":"PL","type":"education","lineage":["https://openalex.org/I47996466"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jakub Waszczuk","raw_affiliation_strings":["Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland","University of Warmia and Mazury, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"raw_affiliation_string":"University of Warmia and Mazury, Warsaw, Poland","institution_ids":["https://openalex.org/I47996466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066593460","display_name":"Katarzyna G\u0142owi\u0144ska","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Katarzyna Glowinska","raw_affiliation_strings":["Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056479939","display_name":"Agata Savary","orcid":"https://orcid.org/0000-0002-6473-6477"},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["FR","PL"],"is_corresponding":false,"raw_author_name":"Agata Savary","raw_affiliation_strings":["Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland","Laboratoire d'Informatique, Universit\u00e9 Fran\u00e7ois-Rabelais de Tours, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"raw_affiliation_string":"Laboratoire d'Informatique, Universit\u00e9 Fran\u00e7ois-Rabelais de Tours, France","institution_ids":["https://openalex.org/I110017253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030436217","display_name":"Adam Przepi\u00f3rkowski","orcid":"https://orcid.org/0000-0002-4398-2636"},"institutions":[{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I47996466","display_name":"University of Warmia and Mazury in Olsztyn","ror":"https://ror.org/05s4feg49","country_code":"PL","type":"education","lineage":["https://openalex.org/I47996466"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Adam Przepiorkowski","raw_affiliation_strings":["Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland","University of Warmia and Mazury, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Polish Academy of Sciences, Warsaw, Poland","institution_ids":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"raw_affiliation_string":"University of Warmia and Mazury, Warsaw, Poland","institution_ids":["https://openalex.org/I47996466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7248,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91895109,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"19","issue":null,"first_page":"531","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T12353","display_name":"Lexicography and Language Studies","score":0.9699000120162964,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12658","display_name":"Language and Culture","score":0.9643999934196472,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8492615222930908},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.826011061668396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6682358980178833},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5789868831634521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5157842636108398},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5093053579330444},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.5013384819030762},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.45650890469551086},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.4212476909160614},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.42001867294311523},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4128063917160034},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38196831941604614},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30676430463790894},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24678286910057068}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8492615222930908},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.826011061668396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6682358980178833},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5789868831634521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5157842636108398},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5093053579330444},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.5013384819030762},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.45650890469551086},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.4212476909160614},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.42001867294311523},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4128063917160034},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38196831941604614},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30676430463790894},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24678286910057068},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/imcsit.2010.5680057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/imcsit.2010.5680057","pdf_url":null,"source":{"id":"https://openalex.org/S4210192132","display_name":"Proceedings of the International Multiconference on Computer Science and Information Technology","issn_l":"1896-7094","issn":["1896-7094","2157-5525","2157-5533"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Multiconference on Computer Science and Information Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W24675619","https://openalex.org/W37695403","https://openalex.org/W44059908","https://openalex.org/W116102626","https://openalex.org/W116785612","https://openalex.org/W1532742788","https://openalex.org/W1602986904","https://openalex.org/W1632114991","https://openalex.org/W2006147030","https://openalex.org/W2014674511","https://openalex.org/W2035967403","https://openalex.org/W2045182725","https://openalex.org/W2047477415","https://openalex.org/W2052286186","https://openalex.org/W2096871981","https://openalex.org/W2097125878","https://openalex.org/W2130714056","https://openalex.org/W2172028209","https://openalex.org/W2292928549","https://openalex.org/W2503692847","https://openalex.org/W2568962674","https://openalex.org/W2742297936","https://openalex.org/W4285719527","https://openalex.org/W4299784046","https://openalex.org/W6600985528","https://openalex.org/W6601747083","https://openalex.org/W6604749457","https://openalex.org/W6636649193","https://openalex.org/W6679144773","https://openalex.org/W6742423752"],"related_works":["https://openalex.org/W1571453868","https://openalex.org/W1043255351","https://openalex.org/W2135057643","https://openalex.org/W2109902858","https://openalex.org/W1533278948","https://openalex.org/W1781980207","https://openalex.org/W2951759144","https://openalex.org/W28706907","https://openalex.org/W2949524199","https://openalex.org/W2575884139"],"abstract_inverted_index":{"The":[0],"on-going":[1],"project":[2],"aiming":[3],"at":[4],"the":[5,8,21,29,34,42,58,62,72,75,87,97,124],"creation":[6],"of":[7,11,16,36,44,61,74,86,107,113,141],"National":[9],"Corpus":[10],"Polish":[12],"assumes":[13],"several":[14],"levels":[15],"linguistic":[17],"annotation.":[18],"We":[19,47,93,133],"present":[20],"technical":[22],"environment":[23,137],"and":[24,39,41,53,64,83,109,119,128],"methodological":[25],"background":[26],"developed":[27],"for":[28,57,91,104,110,149],"three":[30],"upper":[31],"annotation":[32,152],"levels:":[33],"level":[35,43],"syntactic":[37,76],"words":[38],"groups,":[40],"named":[45],"entities.":[46],"show":[48,95],"how":[49,96],"knowledge-based":[50],"platforms":[51],"Spejd":[52],"Sprout":[54],"are":[55],"used":[56],"automatic":[59,125],"pre-annotation":[60],"corpus,":[63],"we":[65],"discuss":[66],"some":[67],"particular":[68],"problems":[69],"faced":[70],"during":[71],"elaboration":[73],"grammar,":[77],"which":[78],"contains":[79],"over":[80],"800":[81],"rules":[82],"is":[84],"one":[85],"largest":[88],"chunking":[89],"grammars":[90],"Polish.":[92],"also":[94],"tree":[98],"editor":[99],"TrEd":[100],"has":[101],"been":[102],"customized":[103,120],"manual":[105],"post-editing":[106],"annotations,":[108],"further":[111],"revision":[112],"discrepancies.":[114],"Our":[115],"XML":[116],"format":[117],"converters":[118],"archiving":[121],"repository":[122],"ensure":[123],"data":[126],"flow":[127],"efficient":[129],"corpus":[130,151],"file":[131],"management.":[132],"believe":[134],"that":[135],"this":[136],"or":[138,147],"substantial":[139],"parts":[140],"it":[142],"can":[143],"be":[144],"reused":[145],"in":[146],"adapted":[148],"other":[150],"tasks.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
