Multi-task fine-tuning using prefix-prepend format in text-to-text transfer transformer for automatic question generation in Bahasa Indonesia
A prefix-prepend format for fine-tuning with the idT5-base model on the Indonesian Stanford Question Answering Dataset (SQuAD) and the Typologically Diverse Question Answering (TyDiQA) dataset is proposed and shows that prefix-prepend fine-tuning improved the performance of the baseline model.