Automated question generation and question answering from Turkish texts
This addresses the need for efficient educational tools in Turkish language processing, though it is incremental as it applies existing methods to a new language.
The authors tackled automated question generation and answering for Turkish texts by fine-tuning a multilingual T5 transformer in a multi-task setting, achieving state-of-the-art performance on Turkish QA and QG datasets such as TQuADv1, TQuADv2, and XQuAD Turkish split.
While exam-style questions are a fundamental educational tool serving a variety of purposes, manual construction of questions is a complex process that requires training, experience and resources. Automatic question generation (QG) techniques can be utilized to satisfy the need for a continuous supply of new questions by streamlining their generation. However, compared to automatic question answering (QA), QG is a more challenging task. In this work, we fine-tune a multilingual T5 (mT5) transformer in a multi-task setting for QA, QG and answer extraction tasks using Turkish QA datasets. To the best of our knowledge, this is the first academic work that performs automated text-to-text question generation from Turkish texts. Experimental evaluations show that the proposed multi-task setting achieves state-of-the-art Turkish question answering and question generation performance on TQuADv1, TQuADv2 datasets and XQuAD Turkish split. The source code and the pre-trained models are available at https://github.com/obss/turkish-question-generation.