no code implementations • 2 Dec 2021 • Ying-Hong Chan, Ho-Lam Chung, Yao-Chung Fan
While the significant advancement of QG techniques was reported, current QG results are not ideal for educational reading practice assessment in terms of \textit{controllability} and \textit{question difficulty}.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ho-Lam Chung, Ying-Hong Chan, Yao-Chung Fan
In this paper, we investigate the following two limitations for the existing distractor generation (DG) methods.
1 code implementation • 12 Oct 2020 • Ho-Lam Chung, Ying-Hong Chan, Yao-Chung Fan
In this paper, we investigate the following two limitations for the existing distractor generation (DG) methods.
Ranked #1 on Distractor Generation on RACE
1 code implementation • WS 2019 • Ying-Hong Chan, Yao-Chung Fan
In this study, we investigate the employment of the pre-trained BERT language model to tackle question generation tasks.
Ranked #9 on Question Generation on SQuAD1.1 (using extra training data)
no code implementations • WS 2019 • Ying-Hong Chan, Yao-Chung Fan
In this study, we investigate the employment of the pre-trained BERT language model to tackle question generation tasks.