{"id":"https://openalex.org/W3199226759","doi":"https://doi.org/10.18653/v1/2022.findings-acl.321","title":"Improving Zero-Shot Cross-lingual Transfer Between Closely Related Languages by Injecting Character-Level Noise","display_name":"Improving Zero-Shot Cross-lingual Transfer Between Closely Related Languages by Injecting Character-Level Noise","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3199226759","doi":"https://doi.org/10.18653/v1/2022.findings-acl.321","mag":"3199226759"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.findings-acl.321","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-acl.321","pdf_url":"https://aclanthology.org/2022.findings-acl.321.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.findings-acl.321.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047249362","display_name":"No\u00ebmi Aepli","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"No\u00ebmi Aepli","raw_affiliation_strings":["Department of Computational Linguistics, University of Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Linguistics, University of Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005771535","display_name":"Rico Sennrich","orcid":"https://orcid.org/0000-0002-1438-4741"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CH","GB"],"is_corresponding":false,"raw_author_name":"Rico Sennrich","raw_affiliation_strings":["Department of Computational Linguistics, University of Zurich","School of Informatics, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Linguistics, University of Zurich","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"School of Informatics, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4074","last_page":"4083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.7317966222763062},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6341086030006409},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5567730665206909},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5418503880500793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511510968208313},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5013749599456787},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48742344975471497},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4634961783885956},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.455910325050354},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4556998014450073},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3206877112388611},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1844324767589569},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1292901635169983},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10485202074050903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7317966222763062},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6341086030006409},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5567730665206909},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5418503880500793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511510968208313},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5013749599456787},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48742344975471497},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4634961783885956},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.455910325050354},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4556998014450073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3206877112388611},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1844324767589569},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1292901635169983},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10485202074050903},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/2022.findings-acl.321","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-acl.321","pdf_url":"https://aclanthology.org/2022.findings-acl.321.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:www.zora.uzh.ch:224511","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Aepli, No\u00ebmi; Sennrich, Rico (2022). Improving Zero-Shot Cross-lingual Transfer Between Closely Related Languages by Injecting Character-Level Noise. In: Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, May 2022. Association for Computational Linguistics, 4074-4083.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.ed.ac.uk:publications/52504f20-1309-4a0f-9998-ff4e9396604e","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/52504f20-1309-4a0f-9998-ff4e9396604e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/52504f20-1309-4a0f-9998-ff4e9396604e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/52504f20-1309-4a0f-9998-ff4e9396604e","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Aepli, N & Sennrich, R 2022, Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by Injecting Character-level Noise. in S Muresan, P Nakov & A Villavicencio (eds), Findings of the Association for Computational Linguistics: ACL 2022. pp. 4074-4083, 60th Annual Meeting of the Association for Computational Linguistics, Dublin, Ireland, 22/05/22. < https://aclanthology.org/2022.findings-acl.321 >","raw_type":"contributionToPeriodical"},{"id":"doi:10.5167/uzh-224511","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-224511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.18653/v1/2022.findings-acl.321","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.findings-acl.321","pdf_url":"https://aclanthology.org/2022.findings-acl.321.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6048348966","display_name":"Multi-Task Learning with Multilingual Resources for Better Natural Language Understanding","funder_award_id":"176727","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G7444390329","display_name":"Sustainable Natural Language Processing for Low-Resource Language Variations","funder_award_id":"191934","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3199226759.pdf","grobid_xml":"https://content.openalex.org/works/W3199226759.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1940872118","https://openalex.org/W2025768430","https://openalex.org/W2119202242","https://openalex.org/W2251378216","https://openalex.org/W2510573142","https://openalex.org/W2579343286","https://openalex.org/W2740840489","https://openalex.org/W2767899794","https://openalex.org/W2805443429","https://openalex.org/W2912742782","https://openalex.org/W2914120296","https://openalex.org/W2916835973","https://openalex.org/W2917956622","https://openalex.org/W2962784628","https://openalex.org/W2963062785","https://openalex.org/W2963341956","https://openalex.org/W2963586344","https://openalex.org/W2964132420","https://openalex.org/W2971277088","https://openalex.org/W2980282514","https://openalex.org/W2984051011","https://openalex.org/W2989853453","https://openalex.org/W2995983139","https://openalex.org/W2998653650","https://openalex.org/W3013840636","https://openalex.org/W3035207248","https://openalex.org/W3037116584","https://openalex.org/W3037582736","https://openalex.org/W3100198908","https://openalex.org/W3119691817","https://openalex.org/W3153498076","https://openalex.org/W3166790124","https://openalex.org/W3169244955","https://openalex.org/W4294536576","https://openalex.org/W4300973022"],"related_works":["https://openalex.org/W2386430105","https://openalex.org/W2356521405","https://openalex.org/W2038534795","https://openalex.org/W2384358604","https://openalex.org/W1567829292","https://openalex.org/W3001063351","https://openalex.org/W3196905815","https://openalex.org/W2351370765","https://openalex.org/W3133811809","https://openalex.org/W1967452726"],"abstract_inverted_index":{"Cross-lingual":[0],"transfer":[1,47,86,121],"between":[2,48,93,122],"a":[3,39],"high-resource":[4,60],"language":[5,12,62,94,106,123],"and":[6,83,90,100,103],"its":[7],"dialects":[8],"or":[9],"closely":[10,49],"related":[11,50],"varieties":[13,95],"should":[14],"be":[15],"facilitated":[16],"by":[17],"their":[18],"similarity.":[19],"However,":[20],"current":[21],"approaches":[22],"that":[23],"operate":[24],"in":[25,119],"the":[26,56,59,68,97,113],"embedding":[27],"space":[28],"do":[29],"not":[30],"take":[31],"surface":[32],"similarity":[33],"into":[34],"account.":[35],"This":[36],"work":[37,109],"presents":[38],"simple":[40,116],"yet":[41],"effective":[42],"strategy":[43,76],"to":[44,54,66],"improve":[45],"cross-lingual":[46],"varieties.":[51,124],"We":[52],"propose":[53],"augment":[55],"data":[57],"of":[58,87,115],"source":[61],"with":[63],"character-level":[64],"noise":[65,118],"make":[67],"model":[69],"more":[70],"robust":[71],"towards":[72],"spelling":[73],"variations.":[74],"Our":[75,108],"shows":[77],"consistent":[78],"improvements":[79],"over":[80],"several":[81],"languages":[82],"tasks:":[84],"Zero-shot":[85],"POS":[88],"tagging":[89],"topic":[91],"identification":[92],"from":[96],"Finnic,":[98],"West":[99],"North":[101],"Germanic,":[102],"Western":[104],"Romance":[105],"branches.":[107],"provides":[110],"evidence":[111],"for":[112],"usefulness":[114],"surface-level":[117],"improving":[120]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2022-07-25T00:00:00"}