A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators

Zhihao Fan, Zhongyu Wei, Siyuan Wang, Yang Liu, Xuanjing Huang


Abstract
Visual Question Generation (VQG) aims to ask natural questions about an image automatically. Existing research focus on training model to fit the annotated data set that makes it indifferent from other language generation tasks. We argue that natural questions need to have two specific attributes from the perspectives of content and linguistic respectively, namely, natural and human-written. Inspired by the setting of discriminator in adversarial learning, we propose two discriminators, one for each attribute, to enhance the training. We then use the reinforcement learning framework to incorporate scores from the two discriminators as the reward to guide the training of the question generator. Experimental results on a benchmark VQG dataset show the effectiveness and robustness of our model compared to some state-of-the-art models in terms of both automatic and human evaluation metrics.
Anthology ID:
C18-1150
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1763–1774
Language:
URL:
https://aclanthology.org/C18-1150
DOI:
Bibkey:
Cite (ACL):
Zhihao Fan, Zhongyu Wei, Siyuan Wang, Yang Liu, and Xuanjing Huang. 2018. A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1763–1774, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators (Fan et al., COLING 2018)
Copy Citation:
PDF:
https://aclanthology.org/C18-1150.pdf
Data
MS COCOVQGVisual Question Answering