Question Generation With Doubly Adversarial Nets

Junwei Bao

doi:10.1109/TASLP.2018.2859777

Question Generation With Doubly Adversarial Nets

2018-11-01

12

PRE

AI

DOI：10.1109/TASLP.2018.2859777

Original

Original request for help

Save

Abstract

En 中文

We study the problem of question generation on a specific domain, where there are no labeled data. To address this problem, we propose a novel neural question generation approach called DoubAN, or doubly adversarial nets, which fully utilizes labeled data from other domains (source domains) and unlabeled data from the target domain. Learning a DoubAN involves two adversarial procedures between a question generator and two adversaries. One adversary is a domain-classification discriminator (DC-Dis), which is designed to help the generator learn domain-general representations of the input text. The other is a questionans-wering discriminator (QA-Dis), which provides more training data with estimated reward scores for generated text-question pairs. We conduct experiments on the SQuAD dataset as target-domain unlabeled data and the NewsQA dataset as source-domain labeled data. Experiment results show that our DoubAN achieves better results than baselines. Compared to model variants, which adopt only DC-Dis or QA-Dis, we find that the DC-Dis and QA-Dis indirectly interact with each other and jointly improve the quality of generated questions on the target domain. Moreover, extensive analysis and discussion prove the reasonableness and effectiveness of our proposed approach.

Keywords:

Question generation

doubly-adversarial net

sequence-to-sequence learning

neural networks

natural language processing

artificial intelligence

Question Generation With Doubly Adversarial Nets

Abstract

AI Summary

Journal

Organization