{"id":"https://openalex.org/W1992942687","doi":"https://doi.org/10.1145/1141277.1141473","title":"Evaluation of a language identification system for mono- and multilingual text documents","display_name":"Evaluation of a language identification system for mono- and multilingual text documents","publication_year":2006,"publication_date":"2006-04-23","ids":{"openalex":"https://openalex.org/W1992942687","doi":"https://doi.org/10.1145/1141277.1141473","mag":"1992942687"},"language":"en","primary_location":{"id":"doi:10.1145/1141277.1141473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5065511280","display_name":"Olga Artemenko","orcid":"https://orcid.org/0000-0002-4057-1217"},"institutions":[{"id":"https://openalex.org/I155765044","display_name":"University of Hildesheim","ror":"https://ror.org/02f9det96","country_code":"DE","type":"education","lineage":["https://openalex.org/I155765044"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Olga Artemenko","raw_affiliation_strings":["University of Hildesheim, Hildesheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hildesheim, Hildesheim, Germany","institution_ids":["https://openalex.org/I155765044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009564435","display_name":"Thomas Mandl","orcid":"https://orcid.org/0000-0002-8398-9699"},"institutions":[{"id":"https://openalex.org/I155765044","display_name":"University of Hildesheim","ror":"https://ror.org/02f9det96","country_code":"DE","type":"education","lineage":["https://openalex.org/I155765044"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Mandl","raw_affiliation_strings":["University of Hildesheim, Hildesheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hildesheim, Hildesheim, Germany","institution_ids":["https://openalex.org/I155765044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003917118","display_name":"Margaryta Shramko","orcid":null},"institutions":[{"id":"https://openalex.org/I155765044","display_name":"University of Hildesheim","ror":"https://ror.org/02f9det96","country_code":"DE","type":"education","lineage":["https://openalex.org/I155765044"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Margaryta Shramko","raw_affiliation_strings":["University of Hildesheim, Hildesheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hildesheim, Hildesheim, Germany","institution_ids":["https://openalex.org/I155765044"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035349970","display_name":"Christa Womser\u2010Hacker","orcid":"https://orcid.org/0000-0001-7650-0384"},"institutions":[{"id":"https://openalex.org/I155765044","display_name":"University of Hildesheim","ror":"https://ror.org/02f9det96","country_code":"DE","type":"education","lineage":["https://openalex.org/I155765044"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christa Womser-Hacker","raw_affiliation_strings":["University of Hildesheim, Hildesheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hildesheim, Hildesheim, Germany","institution_ids":["https://openalex.org/I155765044"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I155765044"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"859","last_page":"860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9976999759674072,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9976999759674072,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9824000000953674,"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/T13155","display_name":"Digital Communication and Language","score":0.9193000197410583,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-science","display_name":"Computer science","score":0.8643718957901001},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7610145211219788},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6558482646942139},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6348473429679871},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5921576619148254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5425629615783691},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48590317368507385},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4660082459449768},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2741665244102478},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23816272616386414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8643718957901001},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7610145211219788},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6558482646942139},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6348473429679871},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5921576619148254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5425629615783691},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48590317368507385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4660082459449768},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2741665244102478},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23816272616386414},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1141277.1141473","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.65.1730","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.65.1730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.uni-hildesheim.de/~mandl/Publikationen/ArtemenkoLWA2005.pdf","raw_type":"text"},{"id":"pmh:oai:hispana.mcu.es:6655334","is_oa":false,"landing_page_url":"https://hispana.mcu.es/es/registros/registro.do?tipoRegistro=MTD&idBib=6655334","pdf_url":null,"source":{"id":"https://openalex.org/S4377196108","display_name":"Hispana","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Presentation"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2076330531","https://openalex.org/W2167820484","https://openalex.org/W2178472575"],"related_works":["https://openalex.org/W2898732673","https://openalex.org/W2410053581","https://openalex.org/W3213549959","https://openalex.org/W2296205523","https://openalex.org/W3129739276","https://openalex.org/W3108387573","https://openalex.org/W2924380321","https://openalex.org/W3082797515","https://openalex.org/W2271356425","https://openalex.org/W4383616786"],"abstract_inverted_index":{"Language":[0,88],"identification":[1,27],"is":[2,54,74],"a":[3,7,11,23],"classification":[4],"task":[5],"between":[6],"pre-defined":[8],"model":[9],"and":[10,30,48,50],"text":[12,52],"in":[13],"an":[14],"unknown":[15],"language.":[16],"This":[17],"paper":[18],"presents":[19],"the":[20,72],"implementation":[21],"of":[22],"tool":[24,34,77],"for":[25,28,38,43,66],"language":[26,39,81,92],"mono-":[29],"multi-lingual":[31,85],"documents.":[32],"The":[33,76],"includes":[35],"four":[36],"algorithms":[37,65],"identification.":[40],"An":[41],"evaluation":[42,94],"eight":[44],"languages":[45],"including":[46],"Ukrainian":[47],"Russian":[49],"various":[51],"lengths":[53],"presented.":[55],"It":[56],"could":[57],"be":[58],"shown":[59],"that":[60],"n-gram-based":[61],"approaches":[62],"outperform":[63],"word-based":[64],"short":[67],"texts.":[68],"For":[69],"longer":[70],"texts,":[71],"performance":[73],"comparable.":[75],"can":[78],"also":[79],"identify":[80],"changes":[82],"within":[83],"one":[84],"document.":[86],"Keywords":[87],"identification,":[89],"n-gram":[90],"indexing,":[91],"model,":[93],"1":[95]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
