{"id":"https://openalex.org/W4400611583","doi":"https://doi.org/10.48550/arxiv.2407.08269","title":"LLMs' morphological analyses of complex FST-generated Finnish words","display_name":"LLMs' morphological analyses of complex FST-generated Finnish words","publication_year":2024,"publication_date":"2024-07-11","ids":{"openalex":"https://openalex.org/W4400611583","doi":"https://doi.org/10.48550/arxiv.2407.08269"},"language":"en","primary_location":{"id":"pmh:oai:helda.helsinki.fi:10138/586268","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/586268","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["ddh","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10138/586268","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000562801","display_name":"Anssi Moisio","orcid":"https://orcid.org/0000-0002-2018-3524","observed_orcids":["https://orcid.org/0000-0002-2018-3524"]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Moisio, Anssi","raw_affiliation_strings":["Department of Information and Communications Engineering , Aalto University , Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communications Engineering , Aalto University , Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061159001","display_name":"Mathias Creutz","orcid":"https://orcid.org/0000-0003-1862-4172","observed_orcids":["https://orcid.org/0000-0003-1862-4172"]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Creutz, Mathias","raw_affiliation_strings":["Department of Digital Humanities , University of Helsinki , Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Digital Humanities , University of Helsinki , Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974","observed_orcids":["https://orcid.org/0000-0001-5278-7974"]},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kurimo, Mikko","raw_affiliation_strings":["Department of Information and Communications Engineering , Aalto University , Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communications Engineering , Aalto University , Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07793715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9634000062942505,"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":0.9634000062942505,"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":0.029600000008940697,"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":0.0034000000450760126,"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/morphological-analysis","display_name":"morphological analysis","score":0.7730000019073486},{"id":"https://openalex.org/keywords/finnish","display_name":"Finnish language","score":0.6370000243186951},{"id":"https://openalex.org/keywords/finnish-nouns","display_name":"Finnish nouns","score":0.7160000205039978},{"id":"https://openalex.org/keywords/finite-state-transducers","display_name":"finite-state transducers","score":0.7839999794960022},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.6489999890327454},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9079999923706055},{"id":"https://openalex.org/keywords/gpt-4-turbo","display_name":"GPT-4 Turbo","score":0.7080000042915344},{"id":"https://openalex.org/keywords/llama-2","display_name":"Llama 2","score":0.6399999856948853},{"id":"https://openalex.org/keywords/poros","display_name":"Poros","score":0.5379999876022339},{"id":"https://openalex.org/keywords/rule-based-grammar","display_name":"rule-based grammar","score":0.44699999690055847},{"id":"https://openalex.org/keywords/neural-language-models","display_name":"neural language models","score":0.41100001335144043}],"concepts":[{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.33082497119903564}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:helda.helsinki.fi:10138/586268","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/586268","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["ddh","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},{"id":"pmh:oai:arXiv.org:2407.08269","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.08269","pdf_url":"https://arxiv.org/pdf/2407.08269","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.2407.08269","doi":"https://doi.org/10.48550/arxiv.2407.08269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.08269","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:helda.helsinki.fi:10138/586268","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/586268","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["ddh","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321726","display_name":"Suomen Kulttuurirahasto","ror":"https://ror.org/027xav248"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403581943","https://openalex.org/W7149226311","https://openalex.org/W2995104523","https://openalex.org/W4416524150","https://openalex.org/W4388650609","https://openalex.org/W4387929749","https://openalex.org/W4416035730","https://openalex.org/W7204698366","https://openalex.org/W7137780040","https://openalex.org/W3164540780"],"abstract_inverted_index":{"Rule-based":[0],"language":[1],"processing":[2],"systems":[3,9],"have":[4,68],"been":[5],"overshadowed":[6],"by":[7,40],"neural":[8,19],"in":[10,22,44,70,89],"terms":[11],"of":[12,47,50,74],"utility,":[13],"but":[14],"it":[15],"remains":[16],"unclear":[17],"whether":[18],"NLP":[20],"systems,":[21],"practice,":[23],"learn":[24],"the":[25,38,57,71,75,90],"grammar":[26],"rules":[27],"that":[28,84],"humans":[29],"use.":[30],"This":[31],"work":[32],"aims":[33],"to":[34,67],"shed":[35],"light":[36],"on":[37],"issue":[39],"evaluating":[41],"state-of-the-art":[42],"LLMs":[43],"a":[45],"task":[46,91],"morphological":[48,79],"analysis":[49],"complex":[51],"Finnish":[52],"noun":[53],"forms.":[54],"We":[55,82],"generate":[56],"forms":[58],"using":[59],"an":[60],"FST":[61],"tool,":[62],"and":[63,95,99],"they":[64],"are":[65],"unlikely":[66],"occurred":[69],"training":[72],"sets":[73],"LLMs,":[76],"therefore":[77],"requiring":[78],"generalisation":[80],"capacity.":[81],"find":[83],"GPT-4-turbo":[85],"has":[86],"some":[87],"difficulties":[88],"while":[92],"GPT-3.5-turbo":[93],"struggles":[94],"smaller":[96],"models":[97],"Llama2-70B":[98],"Poro-34B":[100],"fail":[101],"nearly":[102],"completely.":[103]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-07-14T00:00:00"}
