Multi-Task Learning with Language Modeling for Question Generation

Wenjie Zhou, Minghua Zhang, Yunfang Wu


Abstract
This paper explores the task of answer-aware questions generation. Based on the attention-based pointer generator model, we propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical multi-task learning structure. Our joint-learning model enables the encoder to learn a better representation of the input sequence, which will guide the decoder to generate more coherent and fluent questions. On both SQuAD and MARCO datasets, our multi-task learning model boosts the performance, achieving state-of-the-art results. Moreover, human evaluation further proves the high quality of our generated questions.
Anthology ID:
D19-1337
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3394–3399
Language:
URL:
https://aclanthology.org/D19-1337
DOI:
10.18653/v1/D19-1337
Bibkey:
Cite (ACL):
Wenjie Zhou, Minghua Zhang, and Yunfang Wu. 2019. Multi-Task Learning with Language Modeling for Question Generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3394–3399, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Multi-Task Learning with Language Modeling for Question Generation (Zhou et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1337.pdf