{"id":"https://openalex.org/W4389524328","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.595","title":"On Bilingual Lexicon Induction with Large Language Models","display_name":"On Bilingual Lexicon Induction with Large Language Models","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389524328","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.595"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.emnlp-main.595","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.595","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.emnlp-main.595","pdf_url":"https://aclanthology.org/2023.emnlp-main.595.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 2023 Conference on Empirical Methods in Natural Language Processing","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.emnlp-main.595.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002228588","display_name":"Yaoyiran Li","orcid":"https://orcid.org/0000-0001-9529-3878","observed_orcids":["https://orcid.org/0000-0001-9529-3878"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yaoyiran Li","raw_affiliation_strings":["Language Technology Lab, TAL, University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Lab, TAL, University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081393566","display_name":"Anna Korhonen","orcid":"https://orcid.org/0000-0002-3692-3144","observed_orcids":["https://orcid.org/0000-0002-3692-3144"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anna Korhonen","raw_affiliation_strings":["Language Technology Lab, TAL, University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Lab, TAL, University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014866912","display_name":"Ivan Vuli\u0107","orcid":"https://orcid.org/0000-0002-5161-5422","observed_orcids":["https://orcid.org/0000-0002-5161-5422"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ivan Vuli\u0107","raw_affiliation_strings":["Language Technology Lab, TAL, University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Lab, TAL, University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.9942,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80603975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9688000082969666,"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":0.9688000082969666,"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":0.029200000688433647,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0003000000142492354,"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/bilingual-lexicon-induction","display_name":"bilingual lexicon induction","score":0.9990000128746033},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8489999771118164},{"id":"https://openalex.org/keywords/multilingual-language-models","display_name":"multilingual language models","score":0.8769999742507935},{"id":"https://openalex.org/keywords/zero-shot-prompting","display_name":"zero-shot prompting","score":0.8360000252723694},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.7789999842643738},{"id":"https://openalex.org/keywords/few-shot-prompting","display_name":"few-shot prompting","score":0.7110000252723694},{"id":"https://openalex.org/keywords/text-to-text-models","display_name":"text-to-text models","score":0.7440000176429749},{"id":"https://openalex.org/keywords/typologically-diverse-languages","display_name":"typologically diverse languages","score":0.7070000171661377}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6622250080108643},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6595567464828491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559444665908813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616072952747345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5838256478309631},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.48036059737205505},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4459788501262665},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38859355449676514},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.19048437476158142},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07564482092857361},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.emnlp-main.595","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.595","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.emnlp-main.595","pdf_url":"https://aclanthology.org/2023.emnlp-main.595.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.13995","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.13995","pdf_url":"https://arxiv.org/pdf/2310.13995","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.2310.13995","doi":"https://doi.org/10.48550/arxiv.2310.13995","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.13995","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":"article-journal"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.emnlp-main.595","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.595","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.emnlp-main.595","pdf_url":"https://aclanthology.org/2023.emnlp-main.595.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389524328.pdf","grobid_xml":"https://content.openalex.org/works/W4389524328.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W2126725946","https://openalex.org/W2133837072","https://openalex.org/W2294774419","https://openalex.org/W2493916176","https://openalex.org/W2626778328","https://openalex.org/W2762484717","https://openalex.org/W2766182427","https://openalex.org/W2769280657","https://openalex.org/W2798908575","https://openalex.org/W2891555348","https://openalex.org/W2891896107","https://openalex.org/W2892266277","https://openalex.org/W2908510526","https://openalex.org/W2914073025","https://openalex.org/W2946451995","https://openalex.org/W2950797315","https://openalex.org/W2963341956","https://openalex.org/W2970037872","https://openalex.org/W2981540061","https://openalex.org/W2981852735","https://openalex.org/W2982399380","https://openalex.org/W2983040767","https://openalex.org/W3001434439","https://openalex.org/W3022891705","https://openalex.org/W3030163527","https://openalex.org/W3032816972","https://openalex.org/W3033843238","https://openalex.org/W3034402523","https://openalex.org/W3034623056","https://openalex.org/W3092733346","https://openalex.org/W3092858501","https://openalex.org/W3109407175","https://openalex.org/W3120971868","https://openalex.org/W3136071852","https://openalex.org/W3148786556","https://openalex.org/W3152956381","https://openalex.org/W3166938950","https://openalex.org/W3168867926","https://openalex.org/W3169483174","https://openalex.org/W3171465070","https://openalex.org/W3175035375","https://openalex.org/W4221151632","https://openalex.org/W4224308101","https://openalex.org/W4226278401","https://openalex.org/W4226395792","https://openalex.org/W4230872509","https://openalex.org/W4321177597","https://openalex.org/W4322718191","https://openalex.org/W4361194234","https://openalex.org/W4385565080","https://openalex.org/W4385565879","https://openalex.org/W4385570133","https://openalex.org/W4385571124","https://openalex.org/W4385572225","https://openalex.org/W4385572801","https://openalex.org/W4385574002","https://openalex.org/W4386566630","https://openalex.org/W4391494850","https://openalex.org/W7133225605"],"related_works":["https://openalex.org/W4385574002","https://openalex.org/W4388093082","https://openalex.org/W6906729889","https://openalex.org/W4393160944","https://openalex.org/W4403063875","https://openalex.org/W2606243775","https://openalex.org/W2978158280","https://openalex.org/W4416609163","https://openalex.org/W2950797315","https://openalex.org/W7094111072"],"abstract_inverted_index":{"Bilingual":[0],"Lexicon":[1],"Induction":[2],"(BLI)":[3],"is":[4,145],"a":[5,14,97,138,182],"core":[6],"task":[7],"in":[8,28],"multilingual":[9,63],"NLP":[10,29],"that":[11,158],"still,":[12],"to":[13,59,129,148],"large":[15],"extent,":[16],"relies":[17],"on":[18,132,193],"calculating":[19],"cross-lingual":[20],"word":[21],"representations.Inspired":[22],"by":[23],"the":[24,37,40,46,52,146,168],"global":[25],"paradigm":[26],"shift":[27],"towards":[30],"Large":[31],"Language":[32],"Models":[33],"(LLMs),":[34],"we":[35,82],"examine":[36],"potential":[38],"of":[39,43,48,99,115,124,140,153,184],"latest":[41],"generation":[42],"LLMs":[44,64],"for":[45,66,88,176],"development":[47],"bilingual":[49],"lexicons.We":[50],"ask":[51],"following":[53],"research":[54],"question:":[55],"Is":[56],"it":[57],"possible":[58],"prompt":[60],"and":[61,68,75,91,187],"fine-tune":[62],"(mLLMs)":[65],"BLI,":[67],"how":[69],"does":[70],"this":[71,80],"approach":[72],"compare":[73],"against":[74],"complement":[76],"current":[77],"BLI":[78,90,135,151,174,194],"approaches?To":[79],"end,":[81],"systematically":[83],"study":[84],"1)":[85],"zero-shot":[86],"prompting":[87,95,160],"unsupervised":[89],"2)":[92],"fewshot":[93],"in-context":[94,162],"with":[96,119,161,195,199],"set":[98],"seed":[100],"translation":[101],"pairs,":[102],"both":[103],"without":[104],"any":[105],"LLM":[106],"finetuning,":[107],"as":[108,110],"well":[109],"3)":[111],"standard":[112,134],"BLI-oriented":[113],"finetuning":[114],"smaller":[116],"LLMs.We":[117],"experiment":[118],"18":[120],"open-source":[121],"text-to-text":[122,154],"mLLMs":[123],"different":[125],"sizes":[126],"(from":[127],"0.3B":[128],"13B":[130],"parameters)":[131],"two":[133],"benchmarks":[136],"covering":[137],"range":[139],"typologically":[141],"diverse":[142],"languages.Our":[143],"work":[144],"first":[147],"demonstrate":[149],"strong":[150],"capabilities":[152],"mLLMs.The":[155],"results":[156],"reveal":[157],"few-shot":[159],"examples":[163],"from":[164],"nearest":[165],"neighbours":[166],"achieves":[167],"best":[169],"performance,":[170],"establishing":[171],"new":[172],"state-of-the-art":[173],"scores":[175],"many":[177],"language":[178],"pairs.We":[179],"also":[180,197],"conduct":[181],"series":[183],"in-depth":[185],"analyses":[186],"ablation":[188],"studies,":[189],"providing":[190],"more":[191],"insights":[192],"(m)LLMs,":[196],"along":[198],"their":[200],"limitations.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-12-11T00:00:00"}