{"id":"https://openalex.org/W2175658516","doi":"https://doi.org/10.3115/v1/w14-4901","title":"STTS 2.0? Improving the Tagset for the Part-of-Speech-Tagging of German Spoken Data","display_name":"STTS 2.0? Improving the Tagset for the Part-of-Speech-Tagging of German Spoken Data","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2175658516","doi":"https://doi.org/10.3115/v1/w14-4901","mag":"2175658516"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-4901","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4901","pdf_url":"https://aclanthology.org/W14-4901.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-4901.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080895433","display_name":"Swantje Westpfahl","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099471","display_name":"Leibniz Institute for the German Language","ror":"https://ror.org/00hvwkt50","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210099471"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Swantje Westpfahl","raw_affiliation_strings":["Institut fr Deutsche Sprache, Mannheim","Institut f\u00fcr Deutsche Sprache, Mannheim"],"affiliations":[{"raw_affiliation_string":"Institut fr Deutsche Sprache, Mannheim","institution_ids":["https://openalex.org/I4210099471"]},{"raw_affiliation_string":"Institut f\u00fcr Deutsche Sprache, Mannheim","institution_ids":["https://openalex.org/I4210099471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5080895433"],"corresponding_institution_ids":["https://openalex.org/I4210099471"],"apc_list":null,"apc_paid":null,"fwci":2.96,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92500172,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":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":0.9934999942779541,"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/T10759","display_name":"Translation Studies and Practices","score":0.991599977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8064515590667725},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.8016459941864014},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.7590227127075195},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.650216817855835},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5728996396064758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5119651556015015},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4776964485645294},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4384564459323883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4375085234642029},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.42100590467453003},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3948456645011902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064515590667725},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8016459941864014},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.7590227127075195},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.650216817855835},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5728996396064758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5119651556015015},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4776964485645294},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4384564459323883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4375085234642029},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.42100590467453003},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3948456645011902},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":3,"locations":[{"id":"doi:10.3115/v1/w14-4901","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4901","pdf_url":"https://aclanthology.org/W14-4901.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.445","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-4901.pdf","raw_type":"text"},{"id":"pmh:oai:ids-pub.bsz-bw.de:3189","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bsz:mh39-31897","pdf_url":null,"source":{"id":"https://openalex.org/S4306401750","display_name":"Publication Server of the Institute for German Language (Institute for German Language)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210099471","host_organization_name":"Leibniz Institute for the German Language","host_organization_lineage":["https://openalex.org/I4210099471"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-4901","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4901","pdf_url":"https://aclanthology.org/W14-4901.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2175658516.pdf","grobid_xml":"https://content.openalex.org/works/W2175658516.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W29952999","https://openalex.org/W561623340","https://openalex.org/W644676989","https://openalex.org/W644745537","https://openalex.org/W997144428","https://openalex.org/W1501667647","https://openalex.org/W1531985070","https://openalex.org/W1539500366","https://openalex.org/W1916510280","https://openalex.org/W2033626711","https://openalex.org/W2143632084","https://openalex.org/W2166637769","https://openalex.org/W2183656857","https://openalex.org/W2404435330","https://openalex.org/W2404954229","https://openalex.org/W2479257170","https://openalex.org/W2522340720","https://openalex.org/W3098749202","https://openalex.org/W4230641198","https://openalex.org/W4248802399"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2065387230","https://openalex.org/W2323937687","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W648995381","https://openalex.org/W3033791384","https://openalex.org/W2141885522","https://openalex.org/W2776312268","https://openalex.org/W4246315097"],"abstract_inverted_index":{"Part-of-speech":[0],"tagging":[1],"(POS-tagging)":[2],"of":[3,9,13,24,38,57,85,92,94,110,121,135,141,161],"spoken":[4,26,58,95,162],"data":[5,164],"requires":[6],"different":[7],"means":[8],"annotation":[10],"than":[11,149],"POS-tagging":[12,91],"written":[14,72],"and":[15,103],"edited":[16],"texts.":[17],"In":[18,45],"order":[19,46],"to":[20,33,35,47,61,67,155],"capture":[21],"the":[22,36,53,79,88,98,104,107,127,136,139,166],"features":[23],"German":[25,96,163],"language,":[27],"a":[28,50,133,157],"distinct":[29],"tagset":[30,52],"is":[31,117,123,154,171],"needed":[32],"respond":[34],"kinds":[37],"elements":[39],"which":[40],"only":[41],"occur":[42],"in":[43,87,138,179],"speech.":[44],"create":[48,156],"such":[49],"coherent":[51],"most":[54,80],"prominent":[55,81],"phenomena":[56,175],"language":[59],"need":[60],"be":[62],"analyzed,":[63],"especially":[64],"with":[65,97],"respect":[66],"how":[68],"they":[69],"differ":[70],"from":[71,126],"language.":[73],"First":[74],"evaluations":[75],"have":[76],"shown":[77],"that":[78,118,173],"cause":[82],"(over":[83],"50%)":[84],"errors":[86],"existing":[89],"automatized":[90],"transcripts":[93],"Stuttgart":[99],"Tbingen":[100],"Tagset":[101],"(STTS)":[102],"treetagger":[105],"was":[106],"inaccurate":[108],"interpretation":[109],"speech":[111,142],"particles.":[112],"One":[113],"reason":[114],"for":[115,165],"this":[116,119],"class":[120],"words":[122],"virtually":[124],"absent":[125],"current":[128],"STTS.":[129],"This":[130],"paper":[131],"proposes":[132],"recategorization":[134],"STTS":[137],"field":[140],"particles":[143],"based":[144],"on":[145],"distributional":[146],"factors":[147],"rather":[148],"semantics.":[150],"The":[151],"ultimate":[152],"aim":[153],"comprehensive":[158],"reference":[159],"corpus":[160],"global":[167],"research":[168],"community.":[169],"It":[170],"imperative":[172],"all":[174],"are":[176],"reliably":[177],"recorded":[178],"future":[180],"part-of-speech":[181],"tag":[182],"labels.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
