Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.08269 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914866435981312 |
|---|---|
| author | Moisio, Anssi Creutz, Mathias Kurimo, Mikko |
| author_facet | Moisio, Anssi Creutz, Mathias Kurimo, Mikko |
| contents | 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-3.5-turbo struggles and smaller models Llama2-70B and Poro-34B fail nearly completely. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08269 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLMs' morphological analyses of complex FST-generated Finnish words Moisio, Anssi Creutz, Mathias Kurimo, Mikko Computation and Language 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-3.5-turbo struggles and smaller models Llama2-70B and Poro-34B fail nearly completely. |
| title | LLMs' morphological analyses of complex FST-generated Finnish words |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.08269 |