{"id":"https://openalex.org/W4385565080","doi":"https://doi.org/10.18653/v1/2023.acl-long.524","title":"Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM\u2019s Translation Capability","display_name":"Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM\u2019s Translation Capability","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385565080","doi":"https://doi.org/10.18653/v1/2023.acl-long.524"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-long.524","doi":"https://doi.org/10.18653/v1/2023.acl-long.524","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.524","pdf_url":"https://aclanthology.org/2023.acl-long.524.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.acl-long.524.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059930218","display_name":"Eleftheria Briakou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eleftheria Briakou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048302740","display_name":"Colin Cherry","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Colin Cherry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090694771","display_name":"George F. Foster","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Foster","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3026,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.97088413,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9432","last_page":"9452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9564999938011169,"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":0.9564999938011169,"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":0.03849999979138374,"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/T10759","display_name":"Translation Studies and Practices","score":0.0012000000569969416,"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/palms","display_name":"Arecaceae","score":0.7310000061988831},{"id":"https://openalex.org/keywords/multilingual-language-models","display_name":"multilingual language models","score":0.8600000143051147},{"id":"https://openalex.org/keywords/ablation-study","display_name":"ablation study","score":0.6909999847412109},{"id":"https://openalex.org/keywords/model-scale","display_name":"model scale","score":0.8289999961853027}],"concepts":[{"id":"https://openalex.org/C13424479","wikidata":"https://www.wikidata.org/wiki/Q5687237","display_name":"Haystack","level":2,"score":0.8332809209823608},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8059849739074707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777696967124939},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.7207753658294678},{"id":"https://openalex.org/C49876356","wikidata":"https://www.wikidata.org/wiki/Q7002651","display_name":"Neuroscience of multilingualism","level":2,"score":0.7076351642608643},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5709273815155029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5620753169059753},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5223185420036316},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49318236112594604},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.43763267993927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.329404354095459},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.acl-long.524","doi":"https://doi.org/10.18653/v1/2023.acl-long.524","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.524","pdf_url":"https://aclanthology.org/2023.acl-long.524.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.10266","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.10266","pdf_url":"https://arxiv.org/pdf/2305.10266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.10266","doi":"https://doi.org/10.48550/arxiv.2305.10266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.10266","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-long.524","doi":"https://doi.org/10.18653/v1/2023.acl-long.524","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.524","pdf_url":"https://aclanthology.org/2023.acl-long.524.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385565080.pdf","grobid_xml":"https://content.openalex.org/works/W4385565080.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2250342921","https://openalex.org/W2257408573","https://openalex.org/W2626778328","https://openalex.org/W2680541203","https://openalex.org/W2739997338","https://openalex.org/W2798362442","https://openalex.org/W2885185669","https://openalex.org/W2892312507","https://openalex.org/W2903297715","https://openalex.org/W2970476646","https://openalex.org/W2981852735","https://openalex.org/W2988394319","https://openalex.org/W2991382858","https://openalex.org/W3098267758","https://openalex.org/W3119453866","https://openalex.org/W3119872155","https://openalex.org/W3130319171","https://openalex.org/W3137010024","https://openalex.org/W3169369929","https://openalex.org/W3205068155","https://openalex.org/W4226155321","https://openalex.org/W4385571264","https://openalex.org/W4385572225","https://openalex.org/W4385573174"],"related_works":["https://openalex.org/W4320858136","https://openalex.org/W4416997546","https://openalex.org/W4401042993","https://openalex.org/W7139187130","https://openalex.org/W4395680645","https://openalex.org/W4378771129","https://openalex.org/W4411120534","https://openalex.org/W7206179057","https://openalex.org/W4392677917","https://openalex.org/W7160855059"],"abstract_inverted_index":{"Large,":[0],"multilingual":[1],"language":[2,46],"models":[3],"exhibit":[4],"surprisingly":[5],"good":[6],"zero-or":[7],"few-shot":[8],"machine":[9],"translation":[10,18,24,38,42,79,128,146],"capabilities,":[11,147],"despite":[12],"having":[13],"never":[14],"seen":[15],"the":[16,27,41,49,86,96],"intentionally-included":[17],"examples":[19],"provided":[20],"to":[21,62,75,109,119,123],"typical":[22],"neural":[23],"systems.We":[25],"investigate":[26],"role":[28],"of":[29,34,44,88,98,133],"incidental":[30,66,89,106],"bilingualism-the":[31],"unintentional":[32],"consumption":[33],"bilingual":[35,90,107],"signals,":[36],"including":[37],"examples-in":[39],"explaining":[40],"capabilities":[43],"large":[45],"models,":[47],"taking":[48],"Pathways":[50],"Language":[51],"Model":[52],"(PaLM)":[53],"as":[54],"a":[55,59,131,142],"case":[56],"study.We":[57],"introduce":[58],"mixed-method":[60],"approach":[61],"measure":[63],"and":[64,112],"understand":[65],"bilingualism":[67],"at":[68,82],"scale.We":[69],"show":[70,113,137],"that":[71,114,138],"PaLM":[72],"is":[73,92],"exposed":[74],"over":[76],"30":[77],"million":[78],"pairs":[80],"across":[81],"least":[83],"44":[84],"languages.Furthermore,":[85],"amount":[87,97],"content":[91,101,108],"highly":[93],"correlated":[94],"with":[95,152],"monolingual":[99],"in-language":[100],"for":[102],"non-English":[103],"languages.We":[104],"relate":[105],"zero-shot":[110,127],"prompts":[111,122],"it":[115],"can":[116],"be":[117],"used":[118],"mine":[120],"new":[121],"improve":[124],"PaLM's":[125],"out-of-English":[126],"quality.Finally,":[129],"in":[130],"series":[132],"small-scale":[134],"ablations,":[135],"we":[136],"its":[139],"presence":[140],"has":[141],"substantial":[143],"impact":[144,150],"on":[145],"although":[148],"this":[149],"diminishes":[151],"model":[153],"scale.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":8}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-08-05T00:00:00"}
