{"id":"https://openalex.org/W2130801696","doi":"https://doi.org/10.1145/2407085.2407097","title":"A study in language identification","display_name":"A study in language identification","publication_year":2012,"publication_date":"2012-12-05","ids":{"openalex":"https://openalex.org/W2130801696","doi":"https://doi.org/10.1145/2407085.2407097","mag":"2130801696"},"language":"en","primary_location":{"id":"doi:10.1145/2407085.2407097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407085.2407097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventeenth Australasian Document Computing Symposium","raw_type":"proceedings-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/A5036687408","display_name":"Rachel Mary Milne","orcid":null},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Rachel Mary Milne","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand","University of Otago, Dunedin, New Zealand "],"affiliations":[{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]},{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108505151","display_name":"Richard O\u2019Keefe","orcid":null},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Richard A. O'Keefe","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand","University of Otago, Dunedin, New Zealand "],"affiliations":[{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]},{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand ","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050903724","display_name":"Andrew Trotman","orcid":"https://orcid.org/0000-0003-1253-7123"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Andrew Trotman","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand","University of Otago, Dunedin, New Zealand "],"affiliations":[{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]},{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036687408"],"corresponding_institution_ids":["https://openalex.org/I80281795"],"apc_list":null,"apc_paid":null,"fwci":3.5359,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93075193,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"88","last_page":"95"},"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/T12380","display_name":"Authorship Attribution and Profiling","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/T10028","display_name":"Topic Modeling","score":0.9883999824523926,"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/computer-science","display_name":"Computer science","score":0.8443899154663086},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.788033127784729},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5870070457458496},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.585719108581543},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5425825715065002},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.49030211567878723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43775659799575806},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3120241165161133},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06996685266494751}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8443899154663086},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.788033127784729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5870070457458496},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.585719108581543},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5425825715065002},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.49030211567878723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43775659799575806},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3120241165161133},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06996685266494751},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2407085.2407097","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407085.2407097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventeenth Australasian Document Computing Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.250.4862","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.250.4862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.otago.ac.nz/homepages/andrew/papers/2012-8.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W1533946607","https://openalex.org/W1735309556","https://openalex.org/W1803521386","https://openalex.org/W2036822660","https://openalex.org/W2582743722","https://openalex.org/W6638115312","https://openalex.org/W6641506132","https://openalex.org/W6739917773"],"related_works":["https://openalex.org/W3213549959","https://openalex.org/W3129739276","https://openalex.org/W226586525","https://openalex.org/W3108387573","https://openalex.org/W2924380321","https://openalex.org/W3082797515","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837","https://openalex.org/W2362145681"],"abstract_inverted_index":{"Language":[0],"identification":[1],"is":[2,87],"automatically":[3],"determining":[4],"the":[5,23,26],"language":[6],"that":[7,38,60,70,78],"a":[8],"previously":[9],"unseen":[10],"document":[11],"was":[12],"written":[13],"in.":[14],"We":[15,76],"compared":[16],"several":[17],"prior":[18],"methods":[19,32],"on":[20,63,73],"samples":[21],"from":[22,55,68],"Wikipedia":[24],"and":[25,49],"EuroParl":[27],"collections.":[28],"Most":[29],"of":[30],"these":[31,39],"work":[33,61,71],"well.":[34],"But":[35],"we":[36],"identify":[37],"(and":[40],"presumably":[41],"other":[42],"document)":[43],"collections":[44],"are":[45,52,66],"heterogeneous":[46],"in":[47,80],"size,":[48],"short":[50,74],"documents":[51,65],"systematically":[53],"different":[54,67],"large":[56],"ones.":[57,75],"That":[58],"techniques":[59],"well":[62,72],"long":[64],"those":[69],"believe":[77],"improvement":[79],"algorithms":[81],"will":[82],"be":[83],"seen":[84],"if":[85],"length":[86],"taken":[88],"into":[89],"account.":[90]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
