TookaBERT: A Step Forward for Persian NLU
This provides improved models for Persian NLP practitioners, though it is incremental as it applies an existing method to a new language.
The authors tackled the problem of Persian natural language understanding by training two new BERT models on Persian data, and their larger model achieved an average improvement of at least +2.8 points over seven existing models across 14 tasks.
The field of natural language processing (NLP) has seen remarkable advancements, thanks to the power of deep learning and foundation models. Language models, and specifically BERT, have been key players in this progress. In this study, we trained and introduced two new BERT models using Persian data. We put our models to the test, comparing them to seven existing models across 14 diverse Persian natural language understanding (NLU) tasks. The results speak for themselves: our larger model outperforms the competition, showing an average improvement of at least +2.8 points. This highlights the effectiveness and potential of our new BERT models for Persian NLU tasks.