Joint Learning of Question Answering and Question Generation

Yibo Sun, Duyu Tang, Nan Duan, Tao Qin, Shujie Liu, Zhao Yan, Ming Zhou, Yuanhua Lv, Wenpeng Yin, Xiaocheng Feng, Bing Qin, Ting Liu

Abstract

Question answering (QA) and question generation (QG) are closely related tasks that could improve each other; however, the connection of these two tasks is not well explored in the literature. In this paper, we present two training algorithms for learning better QA and QG models through leveraging one another. The first algorithm extends Generative Adversarial Network (GAN), which selectively incorporates artificially generated instances as additional QA training data. The second algorithm is an extension of dual learning, which incorporates the probabilistic correlation of QA and QG as additional regularization in training objectives. To test the scalability of our algorithms, we conduct experiments on both document based and table based question answering tasks. Results show that both algorithms improve a QA model in terms of accuracy and QG model in terms of BLEU score. Moreover, we find that the performance of a QG model could be easily improved by a QA model via policy gradient, however, directly applying GAN that regards all the generated questions as negative instances could not improve the accuracy of the QA model. Our algorithm that selectively assigns labels to generated questions would bring a performance boost.
BibTeX
@article{sun2020joint,
  author = {Yibo Sun and Duyu Tang and Nan Duan and Tao Qin and Shujie Liu and Zhao Yan and Ming Zhou and Yuanhua Lv and Wenpeng Yin and Xiaocheng Feng and Bing Qin and Ting Liu},
  title = {{Joint Learning of Question Answering and Question Generation}},
  journal = {IEEE Trans. Knowl. Data Eng.},
  year = {2020},
  url = {https://openreview.net/forum?id=_k01BW-qFW5},
}

Loading related content...

Figure