{"id":"https://openalex.org/W4405468751","doi":"https://doi.org/10.48550/arxiv.2412.10960","title":"Can LLMs Help Create Grammar?: Automating Grammar Creation for Endangered Languages with In-Context Learning","display_name":"Can LLMs Help Create Grammar?: Automating Grammar Creation for Endangered Languages with In-Context Learning","publication_year":2024,"publication_date":"2024-12-14","ids":{"openalex":"https://openalex.org/W4405468751","doi":"https://doi.org/10.48550/arxiv.2412.10960"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.10960","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10960","pdf_url":"https://arxiv.org/pdf/2412.10960","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.10960","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108988332","display_name":"Piyapath T Spencer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Spencer, Piyapath T","raw_affiliation_strings":["Center for Information and Language Processing (CIS) , LMU Munich , Germany","Language and Information Technology Programme , Faculty of Arts , CU , Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing (CIS) , LMU Munich , Germany","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Language and Information Technology Programme , Faculty of Arts , CU , Thailand","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115505294","display_name":"Nanthipat Kongborrirak","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kongborrirak, Nanthipat","raw_affiliation_strings":["Language and Information Technology Programme , Faculty of Arts , CU , Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language and Information Technology Programme , Faculty of Arts , CU , Thailand","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9932000041007996,"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":0.9932000041007996,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.0019000000320374966,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.001500000013038516,"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/large-language-models","display_name":"large language models","score":0.8640000224113464},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.9559999704360962},{"id":"https://openalex.org/keywords/endangered-languages","display_name":"endangered languages","score":0.8930000066757202},{"id":"https://openalex.org/keywords/language-documentation","display_name":"language documentation","score":0.7749999761581421},{"id":"https://openalex.org/keywords/grammar-generation","display_name":"grammar generation","score":0.5199999809265137},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7429999709129333},{"id":"https://openalex.org/keywords/bilingual-dictionary","display_name":"bilingual dictionary","score":0.8740000128746033},{"id":"https://openalex.org/keywords/parallel-sentences","display_name":"parallel sentences","score":0.722000002861023},{"id":"https://openalex.org/keywords/lexical-entries","display_name":"lexical entries","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.7150545120239258},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5780041813850403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5628566145896912},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5246051549911499},{"id":"https://openalex.org/C179345059","wikidata":"https://www.wikidata.org/wiki/Q11394","display_name":"Endangered species","level":3,"score":0.5187899470329285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4363902807235718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33621418476104736},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.21467873454093933},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.15690746903419495},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"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/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.10960","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10960","pdf_url":"https://arxiv.org/pdf/2412.10960","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.2412.10960","doi":"https://doi.org/10.48550/arxiv.2412.10960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.10960","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":"pmh:oai:arXiv.org:2412.10960","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10960","pdf_url":"https://arxiv.org/pdf/2412.10960","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405468751.pdf","grobid_xml":"https://content.openalex.org/works/W4405468751.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4392340140","https://openalex.org/W4402684126","https://openalex.org/W4411399356","https://openalex.org/W7127953373","https://openalex.org/W4415432669","https://openalex.org/W7162479607","https://openalex.org/W7166880788","https://openalex.org/W7118000250","https://openalex.org/W4404781548","https://openalex.org/W7166877046"],"abstract_inverted_index":{"Yes!":[0],"In":[1],"the":[2,9,52,72,77,85,117,127,147],"present-day":[3],"documenting":[4],"and":[5,61,68,89,110,144],"preserving":[6],"endangered":[7,150],"languages,":[8],"application":[10],"of":[11,41,54,71,129,149],"Large":[12],"Language":[13],"Models":[14],"(LLMs)":[15],"presents":[16],"a":[17,47,137],"promising":[18],"approach.":[19],"This":[20,124],"paper":[21],"explores":[22],"how":[23],"LLMs,":[24],"particularly":[25],"through":[26],"in-context":[27],"learning,":[28],"can":[29,104],"assist":[30],"in":[31,56],"generating":[32,141],"grammatical":[33,59,108,121],"information":[34],"for":[35,119,140],"low-resource":[36],"languages":[37],"with":[38],"limited":[39],"amount":[40],"data.":[42],"We":[43],"takes":[44],"Moklen":[45],"as":[46,116],"case":[48],"study":[49,125],"to":[50,91,94,131,146],"evaluate":[51],"efficacy":[53],"LLMs":[55,103,130],"producing":[57],"coherent":[58],"rules":[60],"lexical":[62,111],"entries":[63],"using":[64],"only":[65],"bilingual":[66],"dictionaries":[67],"parallel":[69],"sentences":[70],"unknown":[73],"language":[74,133],"without":[75],"building":[76],"model":[78],"from":[79],"scratch.":[80],"Our":[81,99],"methodology":[82],"involves":[83],"organising":[84],"existing":[86],"linguistic":[87,142],"data":[88,143],"prompting":[90],"efficiently":[92],"enable":[93],"generate":[95],"formal":[96],"XLE":[97],"grammar.":[98],"results":[100],"demonstrate":[101],"that":[102],"successfully":[105],"capture":[106],"key":[107],"structures":[109],"information,":[112],"although":[113],"challenges":[114],"such":[115],"potential":[118,128],"English":[120],"biases":[122],"remain.":[123],"highlights":[126],"enhance":[132],"documentation":[134],"efforts,":[135],"providing":[136],"cost-effective":[138],"solution":[139],"contributing":[145],"preservation":[148],"languages.":[151]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-12-18T00:00:00"}