{"id":"https://openalex.org/W2251648400","doi":"https://doi.org/10.3115/v1/p14-5003","title":"Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition","display_name":"Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251648400","doi":"https://doi.org/10.3115/v1/p14-5003","mag":"2251648400"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-5003","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-5003","pdf_url":"https://doi.org/10.3115/v1/p14-5003","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/p14-5003","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047678040","display_name":"Jana Strakov\u00e1","orcid":"https://orcid.org/0000-0003-0075-2408"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jana Strakov\u00e1","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060081515","display_name":"Milan Straka","orcid":"https://orcid.org/0000-0003-3295-5576"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milan Straka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102738283","display_name":"Jan Haji\u010d","orcid":"https://orcid.org/0000-0002-3503-7730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Haji\u010d","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047678040"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":23.6761,"has_fulltext":false,"cited_by_count":150,"citation_normalized_percentile":{"value":0.99540202,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"18"},"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":0.9994999766349792,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.9416157007217407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7949260473251343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6049412488937378},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6048491597175598},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5631259679794312},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5491346716880798},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.42086827754974365},{"id":"https://openalex.org/keywords/morphology","display_name":"Morphology (biology)","score":0.41526052355766296},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19675999879837036},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.07516685128211975},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.06501880288124084}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9416157007217407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949260473251343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6049412488937378},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6048491597175598},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5631259679794312},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5491346716880798},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.42086827754974365},{"id":"https://openalex.org/C499950583","wikidata":"https://www.wikidata.org/wiki/Q183252","display_name":"Morphology (biology)","level":2,"score":0.41526052355766296},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19675999879837036},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.07516685128211975},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.06501880288124084},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/p14-5003","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-5003","pdf_url":"https://doi.org/10.3115/v1/p14-5003","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.667.8148","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.667.8148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/P/P14/P14-5003.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/p14-5003","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-5003","pdf_url":"https://doi.org/10.3115/v1/p14-5003","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W61303690","https://openalex.org/W116785612","https://openalex.org/W149084605","https://openalex.org/W158051523","https://openalex.org/W1632114991","https://openalex.org/W1910352655","https://openalex.org/W2004763266","https://openalex.org/W2007780422","https://openalex.org/W2008652694","https://openalex.org/W2016995838","https://openalex.org/W2080637049","https://openalex.org/W2081687495","https://openalex.org/W2087713756","https://openalex.org/W2096765155","https://openalex.org/W2135843243","https://openalex.org/W2144578941","https://openalex.org/W2154326713","https://openalex.org/W2170986599","https://openalex.org/W2172251087","https://openalex.org/W3198160809"],"related_works":["https://openalex.org/W2234121772","https://openalex.org/W2293592765","https://openalex.org/W2969562660","https://openalex.org/W2886260596","https://openalex.org/W2251602037","https://openalex.org/W2891344292","https://openalex.org/W187699659","https://openalex.org/W4206668191","https://openalex.org/W2976376712","https://openalex.org/W2100299435"],"abstract_inverted_index":{"We":[0],"present":[1],"two":[2],"recently":[3],"released":[4],"open-source":[5],"taggers:":[6],"NameTag":[7],"is":[8],"a":[9,44],"free":[10,78,93],"soft-ware":[11],"for":[12,41,56,59,72,94],"named":[13],"entity":[14],"recognition":[15],"(NER)":[16],"which":[17,60,91],"achieves":[18],"state-of-the-art":[19,39],"perfor-mance":[20],"on":[21],"Czech;":[22],"MorphoDiTa":[23],"(Morpho-logical":[24],"Dictionary":[25],"and":[26,36,43,83,112,115],"Tagger)":[27],"performs":[28],"morphological":[29,33],"analysis":[30],"(with":[31],"lemmatiza-tion),":[32],"generation,":[34],"tagging":[35],"tokenization":[37],"with":[38,87,109],"re-sults":[40],"Czech":[42],"throughput":[45],"around":[46],"10-200K":[47],"words":[48],"per":[49],"second.":[50],"The":[51,102],"taggers":[52],"can":[53],"be":[54,70],"trained":[55,88],"any":[57],"language":[58],"annotated":[61],"data":[62],"exist,":[63],"but":[64],"they":[65],"are":[66,77,84,92],"specifi-cally":[67],"designed":[68],"to":[69],"efficient":[71],"inflective":[73],"languages,":[74],"Both":[75],"tools":[76],"software":[79],"under":[80,97],"LGPL":[81],"license":[82],"distributed":[85],"along":[86],"linguistic":[89],"models":[90],"non-commercial":[95],"use":[96],"the":[98],"CC":[99],"BY-NC-SA":[100],"license.":[101],"releases":[103],"in-clude":[104],"standalone":[105],"tools,":[106],"C++":[107],"libraries":[108],"Java,":[110],"Python":[111],"Perl":[113],"bindings":[114],"web":[116],"services.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":30},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-19T21:40:30.786675","created_date":"2025-10-10T00:00:00"}
