Enhancing Question Generation in Bahasa Using Pretrained Language Models
Renaldy Fredyan, Ivan Satrio Wiyono, Derwin Suhartono, Muhammad Rizki Nur Majiid, Fredy Purnomo · Revue d intelligence artificielle · 2024
Automatic Question Generation (AQG) from text is difficult, especially in Indonesia, where research is scarce.Current research focuses on factual questions, leaving room for improvement.Previous studies used sequence-to-sequence models, which are effective for rule-based and cloze testing but rely on pre-existing rules.This article evaluates state-ofthe-art pre-trained models such as IndoBERT, IndoGPT, and IndoBART as well as classical models such as BiGRU, BiLSTM, and Transformer to fill this gap.This paper tests model question generation using SQuAD-ID, IDK-MRC, and TyDi-QA, three popular questionand-answer datasets.This study uses BLEU and ROUGE-L to evaluate each model's ability to generate meaningful queries from the provided settings.This research aims to understand AQG in Indonesian and evaluate model performance.Discusses the background of AQG research, model limitations, as well as research topics and hypotheses.The paper also analyzes the expected contributions, such as the effectiveness of the trained model and the architectural effects on the AQG process.This research improves natural language processing and question generation systems, especially for Indonesian.