A Simple Recipe for Multilingual Grammatical Error Correction
Paper • 2106.03830 • Published
How to use Buntan/gec-t5-v1_1-small with Transformers:
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Buntan/gec-t5-v1_1-small")
model = AutoModelForSeq2SeqLM.from_pretrained("Buntan/gec-t5-v1_1-small")A small T5v1.1 model trained on the cLang-8 dataset following the process described in A Simple Recipe for Multilingual Grammatical Error Correction.
Since it is a single-task T5v1.1 model, there is no need for a task-specific prefix.