BERT for Question Generation

• Main Authors: Ying-Hong Chan, 詹英鴻
• Other Authors: Yao-Chung Fan
• Format: Others
• Language: en_US
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22107NCHU5394056%22.&searchmode=basic

碩士 === 國立中興大學 === 資訊科學與工程學系所 === 107 === In this study, we investigate the employment of the pre-trained BERT language model to tackle question generation tasks. We introduce three neural architectures built on top of BERT for question generation tasks. The first one is a straightforward BERT employment, which reveals the defects of directly using BERT for text generation. And, the second one remedies the first one by restructuring the architecture into a sequential manner for taking information from previous decoded result. In addition, we further propose third model which improves the performance through different BERT input representation formulation. Our models are trained and evaluated on the recent question-answering dataset SQuAD. Experiment results show that our best model yields state-of-the-art performance which advances the BLEU 4 score of the existing best models from 16.85 to 22.17.