{"id":"https://openalex.org/W3139630677","doi":"https://doi.org/10.1109/asonam49781.2020.9381393","title":"Language Identification on Massive Datasets of Short Messages using an Attention Mechanism CNN","display_name":"Language Identification on Massive Datasets of Short Messages using an Attention Mechanism CNN","publication_year":2020,"publication_date":"2020-12-07","ids":{"openalex":"https://openalex.org/W3139630677","doi":"https://doi.org/10.1109/asonam49781.2020.9381393","mag":"3139630677"},"language":"en","primary_location":{"id":"doi:10.1109/asonam49781.2020.9381393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asonam49781.2020.9381393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","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/A5054977514","display_name":"Duy-Tin Vo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Duy-Tin Vo","raw_affiliation_strings":["Chata Technologies Inc., Calgary, Alberta"],"affiliations":[{"raw_affiliation_string":"Chata Technologies Inc., Calgary, Alberta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065888080","display_name":"Richard Khoury","orcid":"https://orcid.org/0000-0001-8237-4548"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard Khoury","raw_affiliation_strings":["Universit\u00e9 Laval, Quebec"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Laval, Quebec","institution_ids":["https://openalex.org/I43406934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054977514"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9279,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81242762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9991000294685364,"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":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8315283060073853},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7556653022766113},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.7490278482437134},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.555359423160553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5248365998268127},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.4776690900325775},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.17994734644889832}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8315283060073853},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7556653022766113},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.7490278482437134},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.555359423160553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5248365998268127},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.4776690900325775},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.17994734644889832},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asonam49781.2020.9381393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asonam49781.2020.9381393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1974288322","https://openalex.org/W2140432583","https://openalex.org/W2169200297","https://openalex.org/W2251452598","https://openalex.org/W2251862917","https://openalex.org/W2399058661","https://openalex.org/W2406858762","https://openalex.org/W2407436506","https://openalex.org/W2470673105","https://openalex.org/W2561747913","https://openalex.org/W2741636242","https://openalex.org/W2757188127","https://openalex.org/W2799012885","https://openalex.org/W2962824509","https://openalex.org/W2963461183","https://openalex.org/W2963861211","https://openalex.org/W3088333221","https://openalex.org/W4300928910","https://openalex.org/W6680785544","https://openalex.org/W6684503276","https://openalex.org/W6691368250","https://openalex.org/W6712435717","https://openalex.org/W6713928960","https://openalex.org/W6714042959","https://openalex.org/W6717114878","https://openalex.org/W6730696447"],"related_works":["https://openalex.org/W2382997850","https://openalex.org/W3204019825","https://openalex.org/W3213549959","https://openalex.org/W3129739276","https://openalex.org/W3108387573","https://openalex.org/W2924380321","https://openalex.org/W3082797515","https://openalex.org/W2532974797","https://openalex.org/W2271356425","https://openalex.org/W4383616786"],"abstract_inverted_index":{"Language":[0],"Identification":[1],"(LID)":[2],"is":[3,156,173],"a":[4,37,41,49,66,97,123,148,157],"challenging":[5],"task,":[6],"especially":[7],"when":[8],"the":[9,83,196],"input":[10],"texts":[11],"are":[12,60,87],"short":[13],"and":[14,63,81,128,184,191],"noisy":[15],"such":[16],"as":[17,71],"microblog":[18],"posts":[19],"on":[20,26,65,77,103],"social":[21],"media":[22],"or":[23,47],"chat":[24],"logs":[25],"gaming":[27],"forums.":[28],"The":[29],"task":[30],"has":[31],"been":[32],"tackled":[33],"by":[34,74,200],"either":[35],"designing":[36],"feature":[38],"set":[39,124,142],"for":[40],"traditional":[42],"classifier":[43,53],"(e.g.":[44,54],"Naive":[45],"Bayes)":[46],"applying":[48],"deep":[50],"neural":[51,152,160],"network":[52,161],"Bi-directional":[55],"GRU,":[56],"Encoder-Decoder).":[57],"These":[58],"methods":[59],"usually":[61],"trained":[62],"tested":[64],"private":[67],"corpus,":[68],"then":[69],"used":[70],"off-the-shelf":[72],"packages":[73],"other":[75],"researchers":[76],"their":[78],"own":[79],"datasets,":[80],"consequently":[82],"various":[84],"results":[85,168],"published":[86],"not":[88],"directly":[89],"comparable.":[90],"In":[91],"this":[92,111,141],"paper,":[93],"we":[94,129,146],"first":[95],"create":[96],"new":[98],"massive":[99],"labeled":[100],"dataset":[101,112,132],"based":[102],"one":[104],"year":[105],"of":[106,125,143,178,180],"Twitter":[107],"data.":[108],"We":[109],"use":[110],"to":[113,121,140,175],"test":[114],"several":[115],"existing":[116],"LID":[117,153],"systems,":[118],"in":[119,189],"order":[120],"obtain":[122],"coherent":[126],"benchmarks,":[127],"make":[130],"our":[131,171],"publicly":[133],"available":[134],"so":[135],"that":[136,170],"others":[137],"can":[138],"add":[139],"benchmarks.":[144],"Finally,":[145],"propose":[147],"shallow":[149],"but":[150],"efficient":[151],"system,":[154],"which":[155],"ngram-regional":[158],"convolution":[159],"enhanced":[162],"with":[163],"an":[164],"attention":[165],"mechanism.":[166],"Experimental":[167],"show":[169],"architecture":[172],"able":[174],"predict":[176],"tens":[177],"thousands":[179],"samples":[181],"per":[182],"second":[183],"surpasses":[185],"all":[186],"state-of-the-art":[187],"systems":[188],"accuracy":[190],"F1":[192],"score,":[193],"including":[194],"outperforming":[195],"popular":[197],"langid":[198],"system":[199],"5%.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}