A Comparison of OpenNMT Sequence Model for Indonesian Automatic Question Generation

Indrihapsari, Yuniar
Jati, Handaru
Nurkhamid, N.
Wardani, Ratna
Setialana, Pradana
Mahali, Muhamad Izzudin
Wijaya, Danang
Ardiansyah, Dhista Dwi Nur
Ardy, Satya Adhiyaksa
Tiala, Maria Bernadetha Charlotta Wonda
Al-khawarizmi, Andi Hakim
Ardiyanto, Widya

ELINVO (Electronics, Informatics, and Vocational Education)
Vol. 8 No. 1 (2023): Mei 2023

Evaluation of learners is a crucial aspect of the educational system. However, creating evaluation instruments is a process that demands teachers' time and energy. The researcher developed the Indonesia Automatic Question Generator in this study using an architecture modified from past studies. The primary goals of this project are (1) to construct an AQG tool utilizing the OpenNMT series and (2) to analyze and compare the model's performance. As a data source, this study employs the SQuAD 2.0 dataset and numerous sequence techniques, including BiGRU, BiLSTM, and Transformer. The researcher trained the models using OpenNMT-py and Google Collaboratory. This approach generates questions that are relevant to the context of the source. This study found that the model was acceptable.