[go: up one dir, main page]

Simple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Model

Sheng Bi, Xiya Cheng, Yuan-Fang Li, Lizhen Qu, Shirong Shen, Guilin Qi, Lu Pan, Yinlin Jiang


Abstract
The ability to generate natural-language questions with controlled complexity levels is highly desirable as it further expands the applicability of question generation. In this paper, we propose an end-to-end neural complexity-controllable question generation model, which incorporates a mixture of experts (MoE) as the selector of soft templates to improve the accuracy of complexity control and the quality of generated questions. The soft templates capture question similarity while avoiding the expensive construction of actual templates. Our method introduces a novel, cross-domain complexity estimator to assess the complexity of a question, taking into account the passage, the question, the answer and their interactions. The experimental results on two benchmark QA datasets demonstrate that our QG model is superior to state-of-the-art methods in both automatic and manual evaluation. Moreover, our complexity estimator is significantly more accurate than the baselines in both in-domain and out-domain settings.
Anthology ID:
2021.findings-emnlp.397
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4645–4654
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.397
DOI:
10.18653/v1/2021.findings-emnlp.397
Bibkey:
Cite (ACL):
Sheng Bi, Xiya Cheng, Yuan-Fang Li, Lizhen Qu, Shirong Shen, Guilin Qi, Lu Pan, and Yinlin Jiang. 2021. Simple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Model. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4645–4654, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Simple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Model (Bi et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.397.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.397.mp4
Data
HotpotQASQuAD