Skip to main content

Research Repository

Advanced Search

Teaching machines to ask questions

Yao, Kaichun; Zhang, Libo; Luo, Tiejian; Tao, Lili; Wu, Yanjun

Authors

Kaichun Yao

Libo Zhang

Tiejian Luo

Lili Tao

Yanjun Wu



Abstract

We propose a novel neural network model that aims to generate diverse and human-like natural language questions. Our model not only directly captures the variability in possible questions by using a latent variable, but also generates certain types of questions by introducing an additional observed variable. We deploy our model in the generative adversarial network (GAN) framework and modify the discriminator which not only allows evaluating the question authenticity, but predicts the question type. Our model is trained and evaluated on a question-answering dataset SQuAD, and the experimental results shown the proposed model is able to generate diverse and readable questions with the specific attribute.

Citation

Yao, K., Zhang, L., Luo, T., Tao, L., & Wu, Y. (2018, July). Teaching machines to ask questions. Paper presented at International Joint Conferences on Artificial Intelligence Organization, Stockholm, Sweden

Presentation Conference Type Conference Paper (unpublished)
Conference Name International Joint Conferences on Artificial Intelligence Organization
Conference Location Stockholm, Sweden
Start Date Jul 13, 2018
End Date Jul 19, 2018
Acceptance Date Apr 16, 2018
Publication Date Jul 1, 2018
Deposit Date Jul 17, 2018
Peer Reviewed Peer Reviewed
Pages 4546-4552
Book Title Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
ISBN 9780999241127
Public URL https://uwe-repository.worktribe.com/output/865419
Publisher URL https://doi.org/10.24963/ijcai.2018/632
Additional Information Title of Conference or Conference Proceedings : Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence




Downloadable Citations