{"id":"https://openalex.org/W2775682630","doi":"https://doi.org/10.26615/978-954-452-049-6_006","title":"An Extensible Multilingual Open Source Lemmatizer","display_name":"An Extensible Multilingual Open Source Lemmatizer","publication_year":2017,"publication_date":"2017-11-10","ids":{"openalex":"https://openalex.org/W2775682630","doi":"https://doi.org/10.26615/978-954-452-049-6_006","mag":"2775682630"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-049-6_006","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-049-6_006","pdf_url":"https://doi.org/10.26615/978-954-452-049-6_006","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/978-954-452-049-6_006","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065296262","display_name":"Ahmet Aker","orcid":"https://orcid.org/0000-0003-3381-0790"},"institutions":[{"id":"https://openalex.org/I62318514","display_name":"University of Duisburg-Essen","ror":"https://ror.org/04mz5ra38","country_code":"DE","type":"education","lineage":["https://openalex.org/I62318514"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ahmet Aker","raw_affiliation_strings":["Department of Information Engineering, University of Duisburg-Essen"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Duisburg-Essen","institution_ids":["https://openalex.org/I62318514"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065971982","display_name":"Johann Petrak","orcid":"https://orcid.org/0000-0001-8038-3096"},"institutions":[{"id":"https://openalex.org/I62318514","display_name":"University of Duisburg-Essen","ror":"https://ror.org/04mz5ra38","country_code":"DE","type":"education","lineage":["https://openalex.org/I62318514"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johann Petrak","raw_affiliation_strings":["Department of Information Engineering, University of Duisburg-Essen"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Duisburg-Essen","institution_ids":["https://openalex.org/I62318514"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076190931","display_name":"Firas Sabbah","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Firas Sabbah","raw_affiliation_strings":["Department of Computer Science, University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065296262"],"corresponding_institution_ids":["https://openalex.org/I62318514"],"apc_list":null,"apc_paid":null,"fwci":0.8314,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81546281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"45"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9890000224113464,"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":0.987500011920929,"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":0.951133131980896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8670785427093506},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.6861178874969482},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.6481934785842896},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6064510941505432},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.558005690574646},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.5365118980407715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.524777352809906},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5161532163619995},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5068441033363342},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.47911643981933594},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.47693151235580444},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.42824786901474},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41064202785491943},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16680908203125},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0736459493637085}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.951133131980896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8670785427093506},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.6861178874969482},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.6481934785842896},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6064510941505432},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.558005690574646},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.5365118980407715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524777352809906},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5161532163619995},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5068441033363342},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.47911643981933594},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.47693151235580444},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.42824786901474},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41064202785491943},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16680908203125},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0736459493637085},{"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},{"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":3,"locations":[{"id":"doi:10.26615/978-954-452-049-6_006","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-049-6_006","pdf_url":"https://doi.org/10.26615/978-954-452-049-6_006","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:124254","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:eprints.whiterose.ac.uk:133576","is_oa":false,"landing_page_url":"https://eprints.whiterose.ac.uk/133576/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-049-6_006","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-049-6_006","pdf_url":"https://doi.org/10.26615/978-954-452-049-6_006","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2221546192","display_name":null,"funder_award_id":"611223","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2288245420","display_name":"Collective Platform for Community Resilience and Social Innovation during Crises","funder_award_id":"687847","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2775682630.pdf","grobid_xml":"https://content.openalex.org/works/W2775682630.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W4508078","https://openalex.org/W331019419","https://openalex.org/W1531892924","https://openalex.org/W2052847729","https://openalex.org/W2097744935","https://openalex.org/W2129945445","https://openalex.org/W2143995218","https://openalex.org/W2251717670","https://openalex.org/W2951456787","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1561563106","https://openalex.org/W2116831595","https://openalex.org/W2234121772","https://openalex.org/W2884860922","https://openalex.org/W2226076398","https://openalex.org/W3042025871","https://openalex.org/W2113128227","https://openalex.org/W2061990085","https://openalex.org/W2251336637","https://openalex.org/W4311938462"],"abstract_inverted_index":{"We":[0,58],"present":[1],"GATE":[2,11],"DictLemmatizer,":[3],"a":[4],"multilingual":[5],"open":[6],"source":[7],"lemmatizer":[8],"for":[9,72],"the":[10,37,45,60,63],"NLP":[12],"framework":[13],"that":[14],"currently":[15],"supports":[16],"English,":[17],"German,":[18],"Italian,":[19],"French,":[20],"Dutch,":[21],"and":[22,24,51],"Spanish,":[23],"is":[25,33,42,68],"easily":[26],"extensible":[27],"to":[28],"other":[29],"languages.":[30],"The":[31,40],"software":[32],"freely":[34,70],"available":[35,71],"under":[36],"LGPL":[38],"license.":[39],"lemmatization":[41],"based":[43],"on":[44],"Helsinki":[46],"Finite-State":[47],"Transducer":[48],"Technology":[49],"(HFST)":[50],"lemma":[52],"dictionaries":[53],"automatically":[54],"created":[55],"from":[56],"Wiktionary.":[57],"evaluate":[59],"performance":[61],"of":[62],"lemmatizers":[64],"against":[65],"TreeTagger,":[66],"which":[67],"only":[69],"research":[73],"purposes.":[74]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2017-12-22T00:00:00"}
