ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment
Paper • 2305.14463 • Published
RuBERT-base (DeepPavlov/rubert-base-cased) model fine-tuned on the Russian portion of the ReadMe++ corpus for sentence-level readability prediction on a scale of 6-level CEFR scale
Github (Dataset and Python Package): https://github.com/tareknaous/readme
- Downloads last month
- 9