Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.16382 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913442251669504 |
|---|---|
| author | SadraeiJavaheri, MohammadAli Moghaddaszadeh, Ali Molazadeh, Milad Naeiji, Fariba Aghababaloo, Farnaz Rafiee, Hamideh Amirmahani, Zahra Abedini, Tohid Sheikhi, Fatemeh Zahra Salehoof, Amirmohammad |
| author_facet | SadraeiJavaheri, MohammadAli Moghaddaszadeh, Ali Molazadeh, Milad Naeiji, Fariba Aghababaloo, Farnaz Rafiee, Hamideh Amirmahani, Zahra Abedini, Tohid Sheikhi, Fatemeh Zahra Salehoof, Amirmohammad |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16382 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TookaBERT: A Step Forward for Persian NLU SadraeiJavaheri, MohammadAli Moghaddaszadeh, Ali Molazadeh, Milad Naeiji, Fariba Aghababaloo, Farnaz Rafiee, Hamideh Amirmahani, Zahra Abedini, Tohid Sheikhi, Fatemeh Zahra Salehoof, Amirmohammad Computation and Language 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. |
| title | TookaBERT: A Step Forward for Persian NLU |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.16382 |