{"id":"https://openalex.org/W2738819518","doi":"https://doi.org/10.1145/3078081.3078111","title":"Analysis of Part-Of-Speech Tagging of Historical German Texts","display_name":"Analysis of Part-Of-Speech Tagging of Historical German Texts","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2738819518","doi":"https://doi.org/10.1145/3078081.3078111","mag":"2738819518"},"language":"en","primary_location":{"id":"doi:10.1145/3078081.3078111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078081.3078111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"},"type":"article","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/A5055568228","display_name":"Markus Paluch","orcid":null},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Markus Paluch","raw_affiliation_strings":["Seminar for German Philology, University of Goettingen"],"affiliations":[{"raw_affiliation_string":"Seminar for German Philology, University of Goettingen","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037074903","display_name":"Gabriela Rotari","orcid":null},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gabriela Rotari","raw_affiliation_strings":["Seminar for German Philology, University of Goettingen"],"affiliations":[{"raw_affiliation_string":"Seminar for German Philology, University of Goettingen","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039626478","display_name":"David Steding","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155092","display_name":"Czech Academy of Sciences, Institute of Computer Science","ror":"https://ror.org/0496n6574","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210155092"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"David Steding","raw_affiliation_strings":["Institute of Computer Science, University of Goettingen"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Goettingen","institution_ids":["https://openalex.org/I4210155092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023876711","display_name":"Maximilian We\u00df","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155092","display_name":"Czech Academy of Sciences, Institute of Computer Science","ror":"https://ror.org/0496n6574","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210155092"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Maximilian We\u00df","raw_affiliation_strings":["Institute of Computer Science, University of Goettingen"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Goettingen","institution_ids":["https://openalex.org/I4210155092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081559083","display_name":"Maria Moritz","orcid":"https://orcid.org/0000-0003-3402-6543"},"institutions":[{"id":"https://openalex.org/I4210155092","display_name":"Czech Academy of Sciences, Institute of Computer Science","ror":"https://ror.org/0496n6574","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210155092"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Maria Moritz","raw_affiliation_strings":["Institute of Computer Science, University of Goettingen"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Goettingen","institution_ids":["https://openalex.org/I4210155092"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009651400","display_name":"Marco B\u00fcchler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155092","display_name":"Czech Academy of Sciences, Institute of Computer Science","ror":"https://ror.org/0496n6574","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210155092"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Marco B\u00fcchler","raw_affiliation_strings":["Institute of Computer Science, University of Goettingen"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Goettingen","institution_ids":["https://openalex.org/I4210155092"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055568228"],"corresponding_institution_ids":["https://openalex.org/I74656192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09059498,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"46"},"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":0.9883999824523926,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9815000295639038,"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/variety","display_name":"Variety (cybernetics)","score":0.8927584886550903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8506344556808472},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6857819557189941},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6190400123596191},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.612104058265686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.586464524269104},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.5504945516586304},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.5491856932640076},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39887237548828125},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12680360674858093}],"concepts":[{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.8927584886550903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8506344556808472},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6857819557189941},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6190400123596191},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.612104058265686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.586464524269104},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.5504945516586304},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.5491856932640076},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39887237548828125},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12680360674858093},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"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:10.1145/3078081.3078111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078081.3078111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8799999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W591062983","https://openalex.org/W1508110294","https://openalex.org/W1532325895","https://openalex.org/W1544085509","https://openalex.org/W1570448133","https://openalex.org/W1832573434","https://openalex.org/W2007321142","https://openalex.org/W2040870580","https://openalex.org/W2052847729","https://openalex.org/W2054533749","https://openalex.org/W2183676055","https://openalex.org/W2250368612","https://openalex.org/W2281492572","https://openalex.org/W2403707901","https://openalex.org/W2406510907","https://openalex.org/W2406543193","https://openalex.org/W2490527329","https://openalex.org/W2738658885","https://openalex.org/W2794746432","https://openalex.org/W2915177913","https://openalex.org/W2994982620","https://openalex.org/W3165200737","https://openalex.org/W4213009331","https://openalex.org/W4233141554","https://openalex.org/W4235200889","https://openalex.org/W4250308211","https://openalex.org/W6771369255","https://openalex.org/W6999105280"],"related_works":["https://openalex.org/W3124131622","https://openalex.org/W2970358562","https://openalex.org/W2513202451","https://openalex.org/W2795445283","https://openalex.org/W2285263069","https://openalex.org/W3190705690","https://openalex.org/W2575750760","https://openalex.org/W2056380474","https://openalex.org/W3198290408","https://openalex.org/W4385574727"],"abstract_inverted_index":{"The":[0],"amount":[1],"of":[2,28,85,117,135],"data":[3,65],"in":[4,23,83,143],"contemporary":[5],"digital":[6],"corpora":[7],"is":[8,31,81,91],"too":[9],"large":[10,133],"to":[11,131,139],"be":[12,126],"processed":[13],"manually,":[14],"which":[15,76,90],"increases":[16],"the":[17,26,69,73,93,108,115,122,129],"necessity":[18],"for":[19,34,95],"computer":[20],"linguistic":[21],"tools":[22,106,119],"humanities.":[24],"However,":[25],"processing":[27],"natural":[29],"languages":[30,38],"a":[32,44,54,77,144],"challenge":[33],"automatic":[35],"tools,":[36],"because":[37],"are":[39,48,51,102],"used":[40,49],"heterogeneously.":[41],"To":[42],"process":[43,132],"text,":[45],"often":[46,66],"taggers":[47],"that":[50,121],"trained":[52,78],"on":[53,75,107],"standardized":[55],"language":[56,86,110],"variety":[57,87],"(e.g.":[58],"recent":[59],"newspaper":[60],"articles).":[61],"Unfortunately,":[62],"these":[63,118],"training":[64],"differ":[67],"from":[68],"target":[70,109],"texts":[71,137],"(i.e.":[72],"text":[74],"model":[79],"later":[80],"applied)":[82],"terms":[84],"and":[88,138],"register,":[89],"especially":[92],"case":[94],"historical":[96],"texts.":[97],"Therefore,":[98],"additional,":[99],"manual":[100,123],"analyses":[101],"usually":[103],"inevitable.":[104],"Training":[105],"variety,":[111],"however,":[112],"can":[113],"improve":[114],"results":[116,142],"so":[120],"prost-processing":[124],"could":[125],"avoided.":[127],"Thus,":[128],"need":[130],"datasets":[134],"diachronic":[136],"obtain":[140],"accurate":[141],"short":[145],"time-span":[146],"requires":[147],"an":[148],"adaptable":[149],"approach.":[150]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
