LLMs’ morphological analyses of complex FST-generated Finnish words
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AZY425EGI" target="_blank" >RIV/00216208:11320/25:ZY425EGI - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204300266&partnerID=40&md5=16b91e77debc9e24c0833ddfc0801ed9" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204300266&partnerID=40&md5=16b91e77debc9e24c0833ddfc0801ed9</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
LLMs’ morphological analyses of complex FST-generated Finnish words
Original language description
Rule-based language processing systems have been overshadowed by neural systems in terms of utility, but it remains unclear whether neural NLP systems, in practice, learn the grammar rules that humans use. This work aims to shed light on the issue by evaluating state-of-the-art LLMs in a task of morphological analysis of complex Finnish noun forms. We generate the forms using an FST tool, and they are unlikely to have occurred in the training sets of the LLMs, therefore requiring morphological generalisation capacity. We find that GPT-4-turbo has some difficulties in the task while GPT-3.5turbo struggles and smaller models Llama2-70B and Poro-34B fail nearly completely. ©2024 Association for Computational Linguistics.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
CMCL - Ed. Workshop Cogn. Model. Comput. Linguist., Proc. Workshop
ISBN
979-889176143-8
ISSN
—
e-ISSN
—
Number of pages
13
Pages from-to
242-254
Publisher name
Association for Computational Linguistics (ACL)
Place of publication
—
Event location
Bangkok
Event date
Jan 1, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—