{"id":"https://openalex.org/W1999111115","doi":"https://doi.org/10.1093/llc/fqq011","title":"Weigh your words--memory-based lemmatization for Middle Dutch","display_name":"Weigh your words--memory-based lemmatization for Middle Dutch","publication_year":2010,"publication_date":"2010-08-04","ids":{"openalex":"https://openalex.org/W1999111115","doi":"https://doi.org/10.1093/llc/fqq011","mag":"1999111115"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqq011","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqq011","pdf_url":null,"source":{"id":"https://openalex.org/S84784070","display_name":"Literary and Linguistic Computing","issn_l":"0268-1145","issn":["0268-1145","1477-4615"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Literary and Linguistic Computing","raw_type":"journal-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/A5068789709","display_name":"Mike Kestemont","orcid":"https://orcid.org/0000-0003-3590-693X"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"M. Kestemont","raw_affiliation_strings":["Institute for the Study of Literature in the Netherlands (ISLN) and University of Antwerp, Belgium"],"affiliations":[{"raw_affiliation_string":"Institute for the Study of Literature in the Netherlands (ISLN) and University of Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083411784","display_name":"Walter Daelemans","orcid":"https://orcid.org/0000-0002-9832-7890"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"W. Daelemans","raw_affiliation_strings":["CLiPS Computational Linguistics Group, University of Antwerp, Belgium"],"affiliations":[{"raw_affiliation_string":"CLiPS Computational Linguistics Group, University of Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112282583","display_name":"Guy De Pauw","orcid":null},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"G. De Pauw","raw_affiliation_strings":["CLiPS Computational Linguistics Group, University of Antwerp, Belgium"],"affiliations":[{"raw_affiliation_string":"CLiPS Computational Linguistics Group, University of Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068789709"],"corresponding_institution_ids":["https://openalex.org/I149213910"],"apc_list":null,"apc_paid":null,"fwci":6.3146,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96281415,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":"3","first_page":"287","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9871000051498413,"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":0.9868000149726868,"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/lemmatisation","display_name":"Lemmatisation","score":0.9811298251152039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818364679813385},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.8038100004196167},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6543526649475098},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6325187087059021},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.5953795313835144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5874656438827515},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.5822126865386963},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5720575451850891},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.4932493567466736},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4556960165500641},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4165027439594269},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0967603325843811}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9811298251152039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818364679813385},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.8038100004196167},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6543526649475098},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6325187087059021},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.5953795313835144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5874656438827515},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.5822126865386963},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5720575451850891},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4932493567466736},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4556960165500641},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4165027439594269},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0967603325843811},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"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/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/llc/fqq011","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqq011","pdf_url":null,"source":{"id":"https://openalex.org/S84784070","display_name":"Literary and Linguistic Computing","issn_l":"0268-1145","issn":["0268-1145","1477-4615"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Literary and Linguistic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W106674071","https://openalex.org/W1551773846","https://openalex.org/W1581712682","https://openalex.org/W1595487059","https://openalex.org/W1647671624","https://openalex.org/W1882181510","https://openalex.org/W1987869189","https://openalex.org/W1994994499","https://openalex.org/W2018329146","https://openalex.org/W2043302885","https://openalex.org/W2056357537","https://openalex.org/W2074231493","https://openalex.org/W2075880254","https://openalex.org/W2098162425","https://openalex.org/W2117180230","https://openalex.org/W2147169507","https://openalex.org/W2149179161","https://openalex.org/W2187123015","https://openalex.org/W2403513632","https://openalex.org/W2614137764","https://openalex.org/W2795016055"],"related_works":["https://openalex.org/W1561563106","https://openalex.org/W2116831595","https://openalex.org/W2290235882","https://openalex.org/W2884860922","https://openalex.org/W1999111115","https://openalex.org/W2152384045","https://openalex.org/W3042025871","https://openalex.org/W4205718632","https://openalex.org/W3144673486","https://openalex.org/W19599141"],"abstract_inverted_index":{"This":[0,10,164],"article":[1,82],"deals":[2],"with":[3,65,101],"the":[4,50,67,113,118,127,176],"lemmatization":[5,114,162],"of":[6,32,35,99,115,179,187,196],"Middle":[7,72,180],"Dutch":[8,73,181],"literature.":[9,182],"text":[11],"collection\u2014like":[12],"any":[13],"other":[14,190],"medieval":[15],"corpus\u2014is":[16],"characterized":[17],"by":[18,151],"an":[19,40],"enormous":[20],"spelling":[21,93,125,141],"variation,":[22,55],"which":[23],"makes":[24],"it":[25,48],"difficult":[26],"to":[27,122,131,138,147,157,189],"perform":[28],"a":[29,86,97,133,152,158,171],"computational":[30,177],"analysis":[31],"this":[33,81,102],"kind":[34],"data.":[36],"Lemmatization":[37],"is":[38,66,167],"therefore":[39],"essential":[41],"preprocessing":[42],"step":[43,173],"in":[44,58,161,175],"many":[45],"applications,":[46],"since":[47],"allows":[49],"abstraction":[51],"from":[52],"superficial":[53],"textual":[54],"for":[56,112],"instance":[57],"spelling.":[59],"The":[60,143],"data":[61],"we":[62,83],"will":[63],"work":[64],"Corpus-Gysseling,":[68],"containing":[69],"all":[70],"surviving":[71],"literary":[74],"manuscripts":[75],"dated":[76],"before":[77],"1300":[78],"AD.":[79],"In":[80],"shall":[84],"present":[85],"language-independent":[87,198],"system":[88,145],"that":[89],"can":[90],"\u2018learn\u2019":[91],"intra-lemma":[92],"variation.":[94],"We":[95],"describe":[96],"series":[98],"experiments":[100],"system,":[103],"using":[104],"Memory-Based":[105],"Machine":[106],"Learning":[107],"and":[108,169],"propose":[109],"two":[110],"solutions":[111],"our":[116],"data:":[117],"first":[119],"procedure":[120],"attempts":[121,146],"generate":[123],"new":[124],"variants,":[126],"second":[128],"one":[129],"seeks":[130],"implement":[132],"novel":[134],"string":[135],"distance":[136],"metric":[137],"better":[139],"detect":[140],"variants.":[142],"latter":[144],"rerank":[148],"candidates":[149],"suggested":[150],"classic":[153],"Levenshtein":[154],"distance,":[155],"leading":[156],"substantial":[159,172],"gain":[160],"accuracy.":[163],"research":[165,191],"result":[166],"encouraging":[168],"means":[170],"forward":[174],"study":[178],"Our":[183],"techniques":[184],"might":[185],"be":[186],"interest":[188],"domains":[192],"as":[193],"well":[194],"because":[195],"their":[197],"nature.":[199]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}