{"id":"https://openalex.org/W4386624637","doi":"https://doi.org/10.3233/shti230712","title":"DE-Lemma: A Maximum-Entropy Based Lemmatizer for German Medical Text","display_name":"DE-Lemma: A Maximum-Entropy Based Lemmatizer for German Medical Text","publication_year":2023,"publication_date":"2023-09-12","ids":{"openalex":"https://openalex.org/W4386624637","doi":"https://doi.org/10.3233/shti230712","pmid":"https://pubmed.ncbi.nlm.nih.gov/37697853"},"language":"en","primary_location":{"id":"doi:10.3233/shti230712","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti230712","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230712","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230712","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044780509","display_name":"Martin Wiesner","orcid":"https://orcid.org/0000-0003-3346-9633"},"institutions":[{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin Wiesner","raw_affiliation_strings":["Dept. of Medical Informatics, Heilbronn University, Heilbronn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Medical Informatics, Heilbronn University, Heilbronn, Germany","institution_ids":["https://openalex.org/I41121874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044780509"],"corresponding_institution_ids":["https://openalex.org/I41121874"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32592778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"307","issue":null,"first_page":"189","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T13629","display_name":"Text Readability and Simplification","score":0.9923999905586243,"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":0.9900000095367432,"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/lemma","display_name":"Lemma (botany)","score":0.9153951406478882},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.8627355098724365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.66008460521698},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.6232151985168457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6127711534500122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5385134816169739},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4322468638420105},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.41489723324775696},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32626035809516907},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09411722421646118}],"concepts":[{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.9153951406478882},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8627355098724365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.66008460521698},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.6232151985168457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6127711534500122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5385134816169739},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4322468638420105},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.41489723324775696},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32626035809516907},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09411722421646118},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D018806","descriptor_name":"APACHE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018806","descriptor_name":"APACHE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018806","descriptor_name":"APACHE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti230712","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti230712","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230712","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:37697853","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37697853","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/shti230712","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti230712","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230712","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386624637.pdf","grobid_xml":"https://content.openalex.org/works/W4386624637.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W331019419","https://openalex.org/W1502957213","https://openalex.org/W1773803948","https://openalex.org/W1901822430","https://openalex.org/W2027979924","https://openalex.org/W2097744935","https://openalex.org/W2250697067","https://openalex.org/W2915977242","https://openalex.org/W2963714641","https://openalex.org/W2976376712","https://openalex.org/W2989976338","https://openalex.org/W2991253660","https://openalex.org/W2996400930","https://openalex.org/W3144414978","https://openalex.org/W4239297201","https://openalex.org/W4242712885","https://openalex.org/W4244421730","https://openalex.org/W4310969345","https://openalex.org/W6823447472"],"related_works":["https://openalex.org/W2315527029","https://openalex.org/W2065387230","https://openalex.org/W2323937687","https://openalex.org/W648995381","https://openalex.org/W3033791384","https://openalex.org/W2141885522","https://openalex.org/W2776312268","https://openalex.org/W4246315097","https://openalex.org/W2047632477","https://openalex.org/W1992088235"],"abstract_inverted_index":{"When":[0],"processing":[1],"written":[2,78],"German":[3,28,97],"language,":[4],"it":[5],"is":[6],"helpful,":[7],"to":[8],"use":[9],"the":[10,31,52,58],"base":[11],"form":[12],"(or:":[13],"lemma)":[14],"of":[15,109,126],"possibly":[16],"inflected":[17],"words,":[18],"such":[19,68],"as":[20],"verbs,":[21],"nouns":[22],"or":[23,37,43,65],"named":[24],"entities.":[25],"However,":[26],"for":[27,56,76,88],"text":[29,77],"from":[30,94,114],"(bio)medical":[32,110],"domain,":[33],"e.g.,":[34],"discharge":[35,116],"letters,":[36],"entries":[38],"stored":[39],"in":[40,50,63,79],"electronic":[41],"medical":[42,59],"health":[44],"records":[45],"(EMR,":[46],"EHR),":[47],"difficulties":[48],"exist":[49],"finding":[51],"correct":[53],"lemma,":[54],"as,":[55],"instance,":[57],"language":[60],"has":[61],"roots":[62],"Latin":[64],"Greek.":[66],"In":[67],"cases,":[69],"stemming":[70],"techniques":[71],"might":[72],"provide":[73],"inaccurate":[74],"results":[75],"German.":[80],"This":[81],"study":[82],"demonstrates":[83],"a":[84,107],"Machine":[85],"Learning":[86],"approach":[87],"training":[89],"Apache":[90],"OpenNLP-based":[91],"lemmatizer":[92],"models":[93,103],"publicly":[95],"available":[96],"treebanks.":[98],"The":[99,118],"resulting":[100],"four":[101],"\"DE-Lemma\"":[102],"were":[104],"evaluated":[105],"against":[106],"sample":[108],"nouns,":[111],"randomly":[112],"selected":[113],"real-world":[115],"letters.":[117],"most":[119],"promising":[120],"DE-Lemma":[121],"model":[122],"achieved":[123],"an":[124],"accuracy":[125],"88.0%":[127],"(F1":[128],"=":[129],".936).":[130]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}