{"id":"https://openalex.org/W1993955525","doi":"https://doi.org/10.1145/2645791.2645795","title":"Uncovering Languages from written documents","display_name":"Uncovering Languages from written documents","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W1993955525","doi":"https://doi.org/10.1145/2645791.2645795","mag":"1993955525"},"language":"en","primary_location":{"id":"doi:10.1145/2645791.2645795","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2645791.2645795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Panhellenic Conference on Informatics","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/A5081787499","display_name":"Nikitas \u039d. Karanikolas","orcid":"https://orcid.org/0000-0003-1777-892X"},"institutions":[{"id":"https://openalex.org/I40479246","display_name":"Technological Educational Institute of Athens","ror":"https://ror.org/044m46d61","country_code":"GR","type":"education","lineage":["https://openalex.org/I40479246"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikitas N. Karanikolas","raw_affiliation_strings":["Dept. of Informatics, TEI of Athens, Ag. Spyridonos street +30-1 - 5385737"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Informatics, TEI of Athens, Ag. Spyridonos street +30-1 - 5385737","institution_ids":["https://openalex.org/I40479246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021165220","display_name":"Panagiotis Ouranos","orcid":null},"institutions":[{"id":"https://openalex.org/I40479246","display_name":"Technological Educational Institute of Athens","ror":"https://ror.org/044m46d61","country_code":"GR","type":"education","lineage":["https://openalex.org/I40479246"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panagiotis Ouranos","raw_affiliation_strings":["Dept. of Informatics, TEI of Athens, Ag. Spyridonos street +30-1 - 5385737"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Informatics, TEI of Athens, Ag. Spyridonos street +30-1 - 5385737","institution_ids":["https://openalex.org/I40479246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40479246"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9607999920845032,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9415000081062317,"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/unicode","display_name":"Unicode","score":0.9035015106201172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8607258796691895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6397015452384949},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.5423409342765808},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5272245407104492},{"id":"https://openalex.org/keywords/serbian","display_name":"Serbian","score":0.5231327414512634},{"id":"https://openalex.org/keywords/bulgarian","display_name":"Bulgarian","score":0.5223516225814819},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5094991326332092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4974372684955597},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4944736957550049},{"id":"https://openalex.org/keywords/lexicographical-order","display_name":"Lexicographical order","score":0.4661753177642822},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.4271208643913269},{"id":"https://openalex.org/keywords/symbol","display_name":"Symbol (formal)","score":0.4160211980342865},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.41554999351501465},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3906106948852539},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.37281733751296997},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3324270248413086},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.31231018900871277}],"concepts":[{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.9035015106201172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607258796691895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6397015452384949},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5423409342765808},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5272245407104492},{"id":"https://openalex.org/C2778408831","wikidata":"https://www.wikidata.org/wiki/Q9299","display_name":"Serbian","level":2,"score":0.5231327414512634},{"id":"https://openalex.org/C2780343019","wikidata":"https://www.wikidata.org/wiki/Q7918","display_name":"Bulgarian","level":2,"score":0.5223516225814819},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5094991326332092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4974372684955597},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4944736957550049},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.4661753177642822},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.4271208643913269},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.4160211980342865},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.41554999351501465},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3906106948852539},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37281733751296997},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3324270248413086},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31231018900871277},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":1,"locations":[{"id":"doi:10.1145/2645791.2645795","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2645791.2645795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Panhellenic Conference on Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1533946607","https://openalex.org/W1598996557","https://openalex.org/W2024338393","https://openalex.org/W2025547042","https://openalex.org/W2130544183"],"related_works":["https://openalex.org/W2583250843","https://openalex.org/W1953677193","https://openalex.org/W4297017343","https://openalex.org/W3043497271","https://openalex.org/W4312821327","https://openalex.org/W2492257482","https://openalex.org/W2950192240","https://openalex.org/W4365460525","https://openalex.org/W4365145460","https://openalex.org/W2969746599"],"abstract_inverted_index":{"Language":[0],"identification":[1,51],"is":[2,8,32,38,47],"the":[3,9,29,59,63,73,85,100,104],"process":[4,52],"of":[5,34,69,76,81,87,112],"understanding":[6],"what":[7],"language":[10,50],"used":[11,64,74],"in":[12],"a":[13,39,48,110],"document.":[14],"There":[15],"are":[16,26],"non-computational":[17],"(manual)":[18],"approaches":[19],"and":[20,92,102],"also":[21],"computational":[22,49],"ones.":[23],"More":[24],"problematic":[25],"cases":[27,68,80],"where":[28],"input":[30],"text":[31],"composed":[33],"several":[35],"languages.":[36],"This":[37],"common":[40],"situation":[41],"on":[42],"Web":[43],"documents.":[44],"Our":[45],"approach":[46],"which":[53],"can":[54],"address":[55],"multiple-language":[56],"documents":[57],"from":[58],"Web.":[60],"It":[61],"elaborates":[62],"single--byte":[65],"alphabet":[66],"(in":[67,79],"codepage":[70],"based":[71],"texts),":[72,84],"subset":[75],"Unicode":[77],"characters":[78],"multiple--byte":[82],"encoded":[83],"prevalence":[86],"certain":[88],"function":[89],"words,":[90],"n--grams":[91],"other":[93],"more":[94],"granular":[95],"symbol":[96],"manipulations.":[97],"We":[98],"discuss":[99],"methods":[101],"evaluate":[103],"system":[105],"with":[106,109],"resources":[107],"(documents)":[108],"mixture":[111],"languages":[113],"(Bulgarian,":[114],"Byelorussian,":[115],"Russian,":[116],"Greek,":[117],"Serbian,":[118],"etc).":[119]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
