Edit model card

A reproduction of training T5 on cLang-8 (corresponding to Table 4) in the following paper: A Simple Recipe for Multilingual Grammatical Error Correction.

The code and the performance on GEC benchmarks are avaliable from https://github.com/gotutiyan/gec-t5.

The same as cLang-8 corpus and the original Lang-8 corpus, the pre-trained models are distributed for research and educational purposes only.

Downloads last month
13
Safetensors
Model size
248M params
Tensor type
F32
·

Collection including gotutiyan/gec-t5-base-clang8