xlxwalex
commented
2 months ago Hi,
The main code in our repository is for Error Correction task. Since for the two sub-tasks of error detection and error type identification, we only utilized the simplest pre-trained model with the fully connected layers for fine-tuning, we did not provide the code for this part directly in the repository.
However, you can refer to the code for type identification in the TaggerModelTTI class of the tagger_model.py file.
Hello, I have finished the error correction according to the steps you provided, but now I want to predict the error type identification for every text at the same time. Can I use FCGEC-Joint and get the desired result by changing some params? If so could you please give me an example?Thank you very much.