{"id":"https://openalex.org/W2966017873","doi":"https://doi.org/10.18653/v1/w19-4009","title":"Harmonizing Different Lemmatization Strategies for Building a Knowledge Base of Linguistic Resources for Latin","display_name":"Harmonizing Different Lemmatization Strategies for Building a Knowledge Base of Linguistic Resources for Latin","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2966017873","doi":"https://doi.org/10.18653/v1/w19-4009","mag":"2966017873"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4009","pdf_url":"https://www.aclweb.org/anthology/W19-4009.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 the 13th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4009.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026809679","display_name":"Francesco Mambrini","orcid":"https://orcid.org/0000-0003-0834-7562"},"institutions":[{"id":"https://openalex.org/I103320735","display_name":"Universit\u00e0 Cattolica del Sacro Cuore","ror":"https://ror.org/03h7r5v07","country_code":"IT","type":"education","lineage":["https://openalex.org/I103320735"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Mambrini","raw_affiliation_strings":["CIRCSE Research Centre Universit Cattolica del Sacro Cuore Largo Gemelli, 1 -20123 Milan, Italy","CIRCSE Research Centre Universit\u00e0 Cattolica del Sacro Cuore Largo Gemelli, 1 -20123 Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIRCSE Research Centre Universit Cattolica del Sacro Cuore Largo Gemelli, 1 -20123 Milan, Italy","institution_ids":["https://openalex.org/I103320735"]},{"raw_affiliation_string":"CIRCSE Research Centre Universit\u00e0 Cattolica del Sacro Cuore Largo Gemelli, 1 -20123 Milan, Italy","institution_ids":["https://openalex.org/I103320735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001999759","display_name":"Marco Passarotti","orcid":"https://orcid.org/0000-0002-9806-7187"},"institutions":[{"id":"https://openalex.org/I103320735","display_name":"Universit\u00e0 Cattolica del Sacro Cuore","ror":"https://ror.org/03h7r5v07","country_code":"IT","type":"education","lineage":["https://openalex.org/I103320735"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Passarotti","raw_affiliation_strings":["CIRCSE Research Centre Universit Cattolica del Sacro Cuore Largo Gemelli, 1 -20123 Milan, Italy","CIRCSE Research Centre Universit\u00e0 Cattolica del Sacro Cuore Largo Gemelli, 1 -20123 Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIRCSE Research Centre Universit Cattolica del Sacro Cuore Largo Gemelli, 1 -20123 Milan, Italy","institution_ids":["https://openalex.org/I103320735"]},{"raw_affiliation_string":"CIRCSE Research Centre Universit\u00e0 Cattolica del Sacro Cuore Largo Gemelli, 1 -20123 Milan, Italy","institution_ids":["https://openalex.org/I103320735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8677,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80947715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"80"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9973000288009644,"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":0.9883999824523926,"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/lemmatisation","display_name":"Lemmatisation","score":0.9549314379692078},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8191845417022705},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7165507078170776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5973829030990601},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.5894542336463928},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.5808569192886353},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5259174108505249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5229271650314331},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5207871794700623},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.44276002049446106},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4296497404575348},{"id":"https://openalex.org/keywords/lexical-database","display_name":"Lexical database","score":0.4188680052757263},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39860761165618896},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23335999250411987}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9549314379692078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191845417022705},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7165507078170776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5973829030990601},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.5894542336463928},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.5808569192886353},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5259174108505249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5229271650314331},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5207871794700623},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.44276002049446106},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4296497404575348},{"id":"https://openalex.org/C2780403423","wikidata":"https://www.wikidata.org/wiki/Q6537700","display_name":"Lexical database","level":3,"score":0.4188680052757263},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39860761165618896},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23335999250411987},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-4009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4009","pdf_url":"https://www.aclweb.org/anthology/W19-4009.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 the 13th Linguistic Annotation Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4009","pdf_url":"https://www.aclweb.org/anthology/W19-4009.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 the 13th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1412362520","display_name":"Linking Latin. Building a Knowledge Base of Linguistic Resources for Latin","funder_award_id":"769994","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2966017873.pdf","grobid_xml":"https://content.openalex.org/works/W2966017873.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1007838","https://openalex.org/W16674320","https://openalex.org/W35086054","https://openalex.org/W98609384","https://openalex.org/W149715871","https://openalex.org/W1487060125","https://openalex.org/W1531315709","https://openalex.org/W1967278378","https://openalex.org/W1979656702","https://openalex.org/W2029718927","https://openalex.org/W2103017472","https://openalex.org/W2103147879","https://openalex.org/W2118617596","https://openalex.org/W2125176215","https://openalex.org/W2142522752","https://openalex.org/W2143995218","https://openalex.org/W2242459625","https://openalex.org/W2250358660","https://openalex.org/W2251602037","https://openalex.org/W2278140378","https://openalex.org/W2515814575","https://openalex.org/W2574521592","https://openalex.org/W2576013217","https://openalex.org/W2618315025","https://openalex.org/W2626122427","https://openalex.org/W2907684526","https://openalex.org/W4206805807","https://openalex.org/W4247772758","https://openalex.org/W4248576114"],"related_works":["https://openalex.org/W1561563106","https://openalex.org/W2116831595","https://openalex.org/W2902799010","https://openalex.org/W85228537","https://openalex.org/W2884860922","https://openalex.org/W2226076398","https://openalex.org/W3042025871","https://openalex.org/W2214441590","https://openalex.org/W2251336637","https://openalex.org/W2525334307"],"abstract_inverted_index":{"The":[0,60],"interoperability":[1],"between":[2],"lemmatized":[3,103],"corpora":[4],"of":[5,91,95,101],"Latin":[6,54,79],"and":[7,75,100,104],"other":[8],"resources":[9,52,77],"that":[10,24,47],"use":[11],"the":[12,20,36,56,63,82,85,88],"lemma":[13],"as":[14],"indexing":[15],"key":[16],"is":[17],"hampered":[18],"by":[19,39],"multiple":[21],"lemmatization":[22,42],"strategies":[23],"different":[25,41],"projects":[26],"adopt.":[27],"In":[28],"this":[29],"paper":[30,61,83],"we":[31,34],"discuss":[32],"how":[33],"tackle":[35],"challenges":[37],"raised":[38],"harmonizing":[40],"criteria":[43],"in":[44],"a":[45,96,102],"project":[46],"aims":[48],"to":[49,72],"connect":[50],"linguistic":[51],"for":[53,78],"using":[55],"Linked":[57],"Data":[58],"paradigm.":[59],"introduces":[62],"architecture":[64],"supporting":[65],"an":[66],"open-ended,":[67],"lemma-based":[68],"Knowledge":[69,89],"Base,":[70],"built":[71],"make":[73],"textual":[74],"lexical":[76,93],"interoperable.":[80],"Particularly,":[81],"describes":[84],"inclusion":[86],"into":[87],"Base":[90],"its":[92],"basis,":[94],"word":[97],"formation":[98],"lexicon":[99],"syntactically":[105],"annotated":[106],"corpus.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
