{"id":"https://openalex.org/W3103065189","doi":"https://doi.org/10.18653/v1/2020.findings-emnlp.323","title":"Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher","display_name":"Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3103065189","doi":"https://doi.org/10.18653/v1/2020.findings-emnlp.323","mag":"3103065189"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.findings-emnlp.323","pdf_url":"https://www.aclweb.org/anthology/2020.findings-emnlp.323.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/2020.findings-emnlp.323.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070865859","display_name":"Giannis Karamanolakis","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giannis Karamanolakis","raw_affiliation_strings":["Columbia University, New York, NY 10027, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY 10027, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061246300","display_name":"Daniel Hsu","orcid":"https://orcid.org/0000-0002-3495-7113"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Hsu","raw_affiliation_strings":["Columbia University, New York, NY 10027, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY 10027, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080063580","display_name":"Luis Gravano","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Gravano","raw_affiliation_strings":["Columbia University, New York, NY 10027, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY 10027, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.505,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":23,"citation_normalized_percentile":{"value":0.999907,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3604","last_page":"3622"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9999,"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/T10028","display_name":"Topic Modeling","score":0.9999,"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":0.9998,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9981,"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/training-set","display_name":"Training set","score":0.4135676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79037106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.66899407},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6485494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6270622},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.51811546},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5111347},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.50589937},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4135676},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18995509},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.findings-emnlp.323","pdf_url":"https://www.aclweb.org/anthology/2020.findings-emnlp.323.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2010.02562","pdf_url":"https://arxiv.org/pdf/2010.02562","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.findings-emnlp.323","pdf_url":"https://www.aclweb.org/anthology/2020.findings-emnlp.323.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.6,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":58,"referenced_works":["https://openalex.org/W1818534184","https://openalex.org/W1821462560","https://openalex.org/W1828724394","https://openalex.org/W193524605","https://openalex.org/W2027197817","https://openalex.org/W2071332064","https://openalex.org/W2134797427","https://openalex.org/W2142262074","https://openalex.org/W2148861942","https://openalex.org/W2150749667","https://openalex.org/W2167660864","https://openalex.org/W2171068337","https://openalex.org/W2251033195","https://openalex.org/W2270364989","https://openalex.org/W2274912527","https://openalex.org/W2294370754","https://openalex.org/W2295710275","https://openalex.org/W2295781714","https://openalex.org/W2514567832","https://openalex.org/W2573062194","https://openalex.org/W2589796525","https://openalex.org/W2741602058","https://openalex.org/W2770073503","https://openalex.org/W2784713665","https://openalex.org/W2888507208","https://openalex.org/W2888536529","https://openalex.org/W2889191148","https://openalex.org/W2889720764","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2952037945","https://openalex.org/W2952289666","https://openalex.org/W2952638691","https://openalex.org/W2963026768","https://openalex.org/W2963047628","https://openalex.org/W2963118869","https://openalex.org/W2963165489","https://openalex.org/W2963308086","https://openalex.org/W2963341956","https://openalex.org/W2963721344","https://openalex.org/W2964266061","https://openalex.org/W2970037872","https://openalex.org/W2970189355","https://openalex.org/W2970193165","https://openalex.org/W2970854433","https://openalex.org/W2971015282","https://openalex.org/W2971327614","https://openalex.org/W2973088264","https://openalex.org/W2980282514","https://openalex.org/W2985620815","https://openalex.org/W2995015695","https://openalex.org/W2995230342","https://openalex.org/W3001495003","https://openalex.org/W3099859218","https://openalex.org/W3104723404","https://openalex.org/W3118485687","https://openalex.org/W342285082","https://openalex.org/W4299579390"],"related_works":["https://openalex.org/W83146503","https://openalex.org/W783305165","https://openalex.org/W4285877427","https://openalex.org/W3203938600","https://openalex.org/W3098003361","https://openalex.org/W2981877337","https://openalex.org/W2972060578","https://openalex.org/W2169074127","https://openalex.org/W2163707935","https://openalex.org/W202723009"],"abstract_inverted_index":{"Cross-lingual":[0],"text":[1],"classification":[2],"alleviates":[3],"the":[4,64,72,91,106,121,124,133],"need":[5],"for":[6,23],"manually":[7],"labeled":[8,16,47],"documents":[9,17,130],"in":[10,63,71,127,141,194,201],"a":[11,54,75,82,101,114,152,176,206],"target":[12,46,65,129],"language":[13,66],"by":[14,145,190],"leveraging":[15,175],"from":[18],"other":[19],"languages.":[20],"Existing":[21],"approaches":[22,42,189],"transferring":[24,146],"supervision":[25,62],"across":[26,97],"languages":[27,98,203],"require":[28],"expensive":[29,38,188],"cross-lingual":[30,39,55,69,159],"resources,":[31,70],"such":[32],"as":[33],"parallel":[34],"corpora,":[35],"while":[36],"less":[37],"representation":[40],"learning":[41],"train":[43],"classifiers":[44],"without":[45],"documents.":[48],"In":[49],"this":[50],"work,":[51],"we":[52],"propose":[53],"teacher-student":[56],"method,":[57],"CLTS,":[58],"that":[59,118],"generates":[60],"\"weak\"":[61],"using":[67,204],"minimal":[68],"form":[73],"of":[74,78,123,172,209],"small":[76,207],"number":[77,208],"word":[79,210],"translations.":[80,211],"Given":[81],"limited":[83],"translation":[84],"budget,":[85],"CLTS":[86,111,135,167,197],"extracts":[87],"and":[88,99,131,138,184],"transfers":[89],"only":[90],"most":[92],"important":[93],"task-specific":[94],"seed":[95,108,125,149],"words":[96,126],"initializes":[100],"teacher":[102],"classifier":[103],"based":[104,162],"on":[105,163],"translated":[107],"words.":[109],"Then,":[110],"iteratively":[112],"trains":[113],"more":[115,187],"powerful":[116],"student":[117,156,173,179],"also":[119],"exploits":[120],"context":[122],"unlabeled":[128],"outperforms":[132,157,185],"teacher.":[134],"is":[136],"simple":[137],"surprisingly":[139],"effective":[140],"18":[142],"diverse":[143],"languages:":[144],"just":[147,205],"20":[148],"words,":[150],"even":[151,186],"bag-of-words":[153],"logistic":[154],"regression":[155],"state-of-the-art":[158],"methods":[160],"(e.g.,":[161],"multilingual":[164],"BERT).":[165],"Moreover,":[166],"can":[168],"accommodate":[169],"any":[170],"type":[171],"classifier:":[174],"monolingual":[177],"BERT":[178],"leads":[180],"to":[181,192],"further":[182],"improvements":[183],"up":[191],"12%":[193],"accuracy.":[195],"Finally,":[196],"addresses":[198],"emerging":[199],"tasks":[200],"low-resource":[202]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3103065189","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-01-06T21:37:36.790512","created_date":"2020-11-23"}