Codabench link for Subtask A: https://www.codabench.org/competitions/17073/

Codabench link for Subtask B: https://www.codabench.org/competitions/17087/

The evaluation scripts can be downloaded from GitHub repository.

The scoring for subtask A uses multiple transformer models and multiple evaluation metrics. The submissions for subtask A will take upto 24 hours to get reflected on the codabench leaderboard. The scoring for subtask B uses the macro F1-score metric and the submissions will be reflected on the codabench leaderboard instantly.

The participants are open to use any model for language identification, fluency, and semantic similarity in subtask A as provided in the evaluation script. For the final results on dev and test in subtask A, we are going to use a fine-tuned model for language identification and appropriate models for fluency and semantic similarity.