{"id":"https://openalex.org/W7166881391","doi":"https://doi.org/10.18653/v1/2026.conll-main.17","title":"Harnessing Linguistic Dissimilarity for Language Generalization on Unseen Low-Resource Varieties","display_name":"Harnessing Linguistic Dissimilarity for Language Generalization on Unseen Low-Resource Varieties","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166881391","doi":"https://doi.org/10.18653/v1/2026.conll-main.17"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.conll-main.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.conll-main.17","pdf_url":"https://aclanthology.org/2026.conll-main.17.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.conll-main.17.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139803036","display_name":"Jinju Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinju Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139745774","display_name":"Haeji Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Haeji Jung","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130400046","display_name":"Youjeong Roh","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youjeong Roh","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063908850","display_name":"Jong Hwan Ko","orcid":"https://orcid.org/0000-0003-4434-4318"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong Hwan Ko","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126976076","display_name":"David R. Mortensen","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"David R. Mortensen","raw_affiliation_strings":["Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , Sungkyunkwan University \u3134 Language Technologies Institute , Carnegie Mellon University \u3137 Department of Computer Science , University of British Columbia \u3139 Electronics and Telecommunications Research Institute","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86746158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"284","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.453900009393692,"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":0.453900009393692,"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/T12090","display_name":"Language and cultural evolution","score":0.16220000386238098,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.04699999839067459,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5909000039100647},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3666999936103821},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.33009999990463257},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.2662000060081482}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5091999769210815},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.506600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5056999921798706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46650001406669617},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2896000146865845},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.conll-main.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.conll-main.17","pdf_url":"https://aclanthology.org/2026.conll-main.17.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Conference on Computational Natural Language Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.conll-main.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.conll-main.17","pdf_url":"https://aclanthology.org/2026.conll-main.17.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Conference on Computational Natural Language Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1610820195","display_name":null,"funder_award_id":"RS-2019-II190421","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G217022389","display_name":null,"funder_award_id":"RS[2019-II19(0421)]","funder_id":"https://openalex.org/F4320321378","funder_display_name":"Sungkyunkwan University"},{"id":"https://openalex.org/G2349693705","display_name":null,"funder_award_id":"RS-2021-II212052","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G438840348","display_name":null,"funder_award_id":"RS-2019-II190421","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4455823013","display_name":null,"funder_award_id":"IITP-2026-RS-2020-II201821","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6580753045","display_name":null,"funder_award_id":"RS-2020-II201821","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7988537878","display_name":null,"funder_award_id":"RS-2020-II201821","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8237108251","display_name":null,"funder_award_id":"RS-2021-II212052","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8366270861","display_name":null,"funder_award_id":"RS-2020-II201821","funder_id":"https://openalex.org/F4320321378","funder_display_name":"Sungkyunkwan University"},{"id":"https://openalex.org/G981685011","display_name":null,"funder_award_id":"II212052","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"}],"funders":[{"id":"https://openalex.org/F4320321378","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166881391.pdf","grobid_xml":"https://content.openalex.org/works/W7166881391.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Low-resource":[0],"language":[1,24],"varieties":[2,31],"used":[3],"by":[4,73],"specific":[5],"groups":[6],"remain":[7],"neglected":[8],"in":[9,141],"the":[10,121,142],"development":[11],"of":[12,18],"Multilingual":[13],"Language":[14,58],"Models.A":[15],"great":[16],"deal":[17],"cross-lingual":[19],"research":[20],"focuses":[21,62],"on":[22,63,114,129,153],"inter-lingual":[23],"transfer":[25,164],"which":[26,118,146],"strives":[27],"to":[28,49,169],"align":[29],"allied":[30],"and":[32],"minimize":[33],"differences":[34],"between":[35],"them.However,":[36],"for":[37,85,127,151],"low-resource":[38,86,159],"varieties,":[39],"linguistic":[40],"dissimilarity":[41],"is":[42],"also":[43,68],"an":[44,137],"important":[45],"cue":[46],"allowing":[47],"generalization":[48],"unseen":[50],"varieties.Unlike":[51],"prior":[52],"approaches,":[53],"we":[54,77,88,163],"propose":[55,78],"a":[56,80,90,102,149],"two-stage":[57],"Generalization":[59,184],"framework":[60,113],"that":[61,94],"capturing":[64],"variety-specific":[65,96,173,177],"cues":[66],"while":[67,101],"exploiting":[69],"rich":[70],"overlap":[71],"offered":[72],"high-resource":[74],"source":[75,167],"variety.First,":[76],"TOPPing,":[79],"source-selection":[81],"method":[82],"specifically":[83],"designed":[84],"varieties.Second,":[87],"suggest":[89],"lightweight":[91],"VA\u00c7A\u00cd-Bowl":[92,133],"architecture":[93],"learns":[95],"attributes":[97,107],"with":[98,134],"one":[99],"branch":[100,104],"parallel":[103],"captures":[105],"variety-invariant":[106],"using":[108],"adversarial":[109],"training.We":[110],"evaluate":[111],"our":[112],"structural":[115],"prediction":[116],"tasks,":[117],"are":[119,175,179],"among":[120],"few":[122],"tasks":[123,156],"available,":[124],"as":[125,148],"proxy":[126,150],"performance":[128,152],"other":[130,154],"downstream":[131,155],"tasks.Using":[132],"TOPPing":[135],"yields":[136],"average":[138],"54.62%":[139],"improvement":[140],"dependency":[143],"parsing":[144],"task,":[145],"serves":[147],"across":[157],"10":[158],"varieties.":[160],"1How":[161],"can":[162],"knowledge":[165],"from":[166],"variety":[168],"target":[170],"variety?Alignment":[171],"Only":[172],"features":[174,178],"collapsed":[176],"preserved":[180],"Variety":[181],"Representation":[182],"Variety-Aware":[183],"Training":[185],"Process":[186]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-07-02T00:00:00"}
