{"id":"https://openalex.org/W2251602037","doi":"https://doi.org/10.18653/v1/w15-3716","title":"Lexicon-assisted tagging and lemmatization in Latin: A comparison of six taggers and two lemmatization models","display_name":"Lexicon-assisted tagging and lemmatization in Latin: A comparison of six taggers and two lemmatization models","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2251602037","doi":"https://doi.org/10.18653/v1/w15-3716","mag":"2251602037"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-3716","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3716","pdf_url":"https://www.aclweb.org/anthology/W15-3716.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\u00a0of\u00a0the\u00a09th\u00a0SIGHUM\u00a0Workshop\u00a0on\u00a0Language\u00a0Technology\u00a0for\u00a0Cultural\u00a0Heritage,\u00a0Social\u00a0Sciences,\u00a0and\u00a0Humanities\u00a0(LaTeCH)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-3716.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027015884","display_name":"Tim vor der Br\u00fcck","orcid":"https://orcid.org/0000-0003-1732-6392"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim vor der Br\u00fcck","raw_affiliation_strings":["Goethe\u2010University Frankfurt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Goethe\u2010University Frankfurt","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053947568","display_name":"Steffen Eger","orcid":"https://orcid.org/0000-0003-4663-8336"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Eger","raw_affiliation_strings":["Goethe\u2010University Frankfurt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Goethe\u2010University Frankfurt","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008340710","display_name":"Alexander Mehler","orcid":"https://orcid.org/0000-0003-2567-7539"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Mehler","raw_affiliation_strings":["Goethe\u2010University Frankfurt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Goethe\u2010University Frankfurt","institution_ids":["https://openalex.org/I114090438"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114090438"],"apc_list":null,"apc_paid":null,"fwci":1.0288,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78830593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"113"},"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/T12353","display_name":"Lexicography and Language Studies","score":0.9887999892234802,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/lemmatisation","display_name":"Lemmatisation","score":0.9894343614578247},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.8681427240371704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774502038955688},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7106808423995972},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.7017196416854858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6832446455955505},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.2518509030342102}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9894343614578247},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8681427240371704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774502038955688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7106808423995972},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.7017196416854858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6832446455955505},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.2518509030342102}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w15-3716","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3716","pdf_url":"https://www.aclweb.org/anthology/W15-3716.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\u00a0of\u00a0the\u00a09th\u00a0SIGHUM\u00a0Workshop\u00a0on\u00a0Language\u00a0Technology\u00a0for\u00a0Cultural\u00a0Heritage,\u00a0Social\u00a0Sciences,\u00a0and\u00a0Humanities\u00a0(LaTeCH)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-3716","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3716","pdf_url":"https://www.aclweb.org/anthology/W15-3716.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\u00a0of\u00a0the\u00a09th\u00a0SIGHUM\u00a0Workshop\u00a0on\u00a0Language\u00a0Technology\u00a0for\u00a0Cultural\u00a0Heritage,\u00a0Social\u00a0Sciences,\u00a0and\u00a0Humanities\u00a0(LaTeCH)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251602037.pdf","grobid_xml":"https://content.openalex.org/works/W2251602037.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W81205094","https://openalex.org/W102455190","https://openalex.org/W1502112145","https://openalex.org/W1541975828","https://openalex.org/W1558474697","https://openalex.org/W1773803948","https://openalex.org/W1850558006","https://openalex.org/W1973620349","https://openalex.org/W1979327299","https://openalex.org/W2008652694","https://openalex.org/W2039696003","https://openalex.org/W2114208974","https://openalex.org/W2116486825","https://openalex.org/W2131514140","https://openalex.org/W2135114651","https://openalex.org/W2135843243","https://openalex.org/W2152540201","https://openalex.org/W2169511760","https://openalex.org/W2250471514","https://openalex.org/W2250745152","https://openalex.org/W2295647960"],"related_works":["https://openalex.org/W2344644918","https://openalex.org/W2107817331","https://openalex.org/W3124131622","https://openalex.org/W2152051036","https://openalex.org/W2572912744","https://openalex.org/W1831473261","https://openalex.org/W4293870971","https://openalex.org/W2970358562","https://openalex.org/W1999382833","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,18,34,81,86,91],"survey":[3],"of":[4,38,51,74,83,93],"tagging":[5,12,36,45],"accuracies":[6],"-concerning":[7],"part-of-speech":[8],"and":[9,42,90],"full":[10,48],"morphological":[11,49],"-for":[13],"several":[14],"taggers":[15,58],"based":[16],"on":[17,77],"corpus":[19],"for":[20,69,85,95],"medieval":[21],"church":[22],"Latin":[23],"(see":[24],"www.comphistsem.org).":[25],"The":[26],"best":[27],"tagger":[28],"in":[29],"our":[30,60,78],"sample,":[31],"Lapos,":[32],"has":[33],"PoS":[35],"accuracy":[37,46,76],"close":[39],"to":[40,66],"96%":[41],"an":[43],"overall":[44],"(including":[47],"tagging)":[50],"about":[52],"85%.":[53],"When":[54],"we":[55],"'intersect'":[56],"the":[57,62],"with":[59],"lexicon,":[61],"latter":[63],"score":[64,82,92],"increases":[65],"almost":[67],"91%":[68],"Lapos.":[70],"A":[71],"conservative":[72],"assessment":[73],"lemmatization":[75,88],"data":[79],"estimates":[80],"93-94%":[84],"lexicon-based":[87],"strategy":[89],"94-95%":[94],"lemmatizing":[96],"via":[97],"trained":[98],"lemmatizers.":[99]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}