Binary and multi-class grammatical error detection models.
The experiment was performed according to Yuan+ 21.

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

Trained models are distributed for research and educational purposes only.

Downloads last month
7
Safetensors
Model size
334M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Collection including gotutiyan/token-ged-electra-large-4cls