Knesset-DictaBERT: A Hebrew Language Model for Parliamentary Proceedings
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910546143477760 |
|---|---|
| author | Goldin, Gili Wintner, Shuly |
| author_facet | Goldin, Gili Wintner, Shuly |
| contents | We present Knesset-DictaBERT, a large Hebrew language model fine-tuned on the Knesset Corpus, which comprises Israeli parliamentary proceedings. The model is based on the DictaBERT architecture and demonstrates significant improvements in understanding parliamentary language according to the MLM task. We provide a detailed evaluation of the model's performance, showing improvements in perplexity and accuracy over the baseline DictaBERT model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20581 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Knesset-DictaBERT: A Hebrew Language Model for Parliamentary Proceedings Goldin, Gili Wintner, Shuly Computation and Language 68T50 We present Knesset-DictaBERT, a large Hebrew language model fine-tuned on the Knesset Corpus, which comprises Israeli parliamentary proceedings. The model is based on the DictaBERT architecture and demonstrates significant improvements in understanding parliamentary language according to the MLM task. We provide a detailed evaluation of the model's performance, showing improvements in perplexity and accuracy over the baseline DictaBERT model. |
| title | Knesset-DictaBERT: A Hebrew Language Model for Parliamentary Proceedings |
| topic | Computation and Language 68T50 |
| url | https://arxiv.org/abs/2407.20581 |