Gec T5 Small

🚀 Grammatical Error Correction Model

This model is designed for grammatical error correction, implementing a method from Google to achieve state - of - the - art results in the Grammatical Error Correction (GEC) task.

🚀 Quick Start

This model is an implementation of the paper A Simple Recipe for Multilingual Grammatical Error Correction from Google, which reports the state - of - the - art score in the task of Grammatical Error Correction (GEC). We implement the version with T5 - small and achieve the reported F_0.5 score (60.70) in the paper.

To effectively use the "Hosted inference API", simply write "gec: [YOUR SENTENCE HERE]".

💻 Usage Examples

Basic Usage

from transformers import T5ForConditionalGeneration, T5Tokenizer

model = T5ForConditionalGeneration.from_pretrained("Unbabel/gec-t5_small")
tokenizer = T5Tokenizer.from_pretrained('t5-small')

sentence = "I like to swimming"
tokenized_sentence = tokenizer('gec: ' + sentence, max_length=128, truncation=True, padding='max_length', return_tensors='pt')
corrected_sentence = tokenizer.decode(
    model.generate(
        input_ids = tokenized_sentence.input_ids,
        attention_mask = tokenized_sentence.attention_mask, 
        max_length=128,
        num_beams=5,
        early_stopping=True,
    )[0],
    skip_special_tokens=True, 
    clean_up_tokenization_spaces=True
)
print(corrected_sentence) # -> I like swimming.

📄 License

The model is released under the apache - 2.0 license.