We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Estonian Language Understanding: a Case Study on the COPA Task.
- Authors
KUULMETS, Hele-Andra; TÄTTAR, Andre; FISHEL, Mark
- Abstract
The lack of Estonian NLU datasets severely affects advancing Estonian-specific NLP research. With this paper we aim to relieve the issue by publishing a new Estonian NLU dataset EstCOPA. We benchmark the task on several Estonian and multilingual transformer based language models, including a novel Estonian-centric GPT (GPT4Est). Moreover, we evaluate different low-cost alternatives for creating training and test datasets and outline strategies for future Estonian language understanding research.
- Subjects
ESTONIAN language; LANGUAGE research; NATURAL languages; TASKS
- Publication
Baltic Journal of Modern Computing, 2022, Vol 10, Issue 3, p470
- ISSN
2255-8942
- Publication type
Article
- DOI
10.22364/bjmc.2022.10.3.19