LLMs’ morphological analyses of complex FST-generated Finnish words

Anssi Moisio, Mathias Creutz, Mikko Kurimo

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

Abstrakti

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.

AlkuperäiskieliEnglanti
OtsikkoCMCL 2024 - 13th Edition of the Workshop on Cognitive Modeling and Computational Linguistics, Proceedings of the Workshop
ToimittajatTatsuki Kuribayashi, Giulia Rambelli, Ece Takmaz, Philipp Wicke, Yohei Oseki
KustantajaAssociation for Computational Linguistics
Sivut242-254
Sivumäärä13
ISBN (elektroninen)979-8-89176-143-8
DOI - pysyväislinkit
TilaJulkaistu - 2024
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaWorkshop on Cognitive Modeling and Computational Linguistics - Bangkok, Thaimaa
Kesto: 15 elok. 202415 elok. 2024

Julkaisusarja

NimiCMCL 2024 - 13th Edition of the Workshop on Cognitive Modeling and Computational Linguistics, Proceedings of the Workshop

Conference

ConferenceWorkshop on Cognitive Modeling and Computational Linguistics
LyhennettäCMCL
Maa/AlueThaimaa
KaupunkiBangkok
Ajanjakso15/08/202415/08/2024

Sormenjälki

Sukella tutkimusaiheisiin 'LLMs’ morphological analyses of complex FST-generated Finnish words'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä