Reinforced Multi-task Approach for Multi-hop Question Generation

Deepak Gupta, Hardik Chauhan, Ravi Tej Akella, Asif Ekbal, Pushpak Bhattacharyya


Abstract
Question generation (QG) attempts to solve the inverse of question answering (QA) problem by generating a natural language question given a document and an answer. While sequence to sequence neural models surpass rule-based systems for QG, they are limited in their capacity to focus on more than one supporting fact. For QG, we often require multiple supporting facts to generate high-quality questions. Inspired by recent works on multi-hop reasoning in QA, we take up Multi-hop question generation, which aims at generating relevant questions based on supporting facts in the context. We employ multitask learning with the auxiliary task of answer-aware supporting fact prediction to guide the question generator. In addition, we also proposed a question-aware reward function in a Reinforcement Learning (RL) framework to maximize the utilization of the supporting facts. We demonstrate the effectiveness of our approach through experiments on the multi-hop question answering dataset, HotPotQA. Empirical evaluation shows our model to outperform the single-hop neural question generation models on both automatic evaluation metrics such as BLEU, METEOR, and ROUGE and human evaluation metrics for quality and coverage of the generated questions.
Anthology ID:
2020.coling-main.249
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2760–2775
Language:
URL:
https://aclanthology.org/2020.coling-main.249
DOI:
10.18653/v1/2020.coling-main.249
Bibkey:
Cite (ACL):
Deepak Gupta, Hardik Chauhan, Ravi Tej Akella, Asif Ekbal, and Pushpak Bhattacharyya. 2020. Reinforced Multi-task Approach for Multi-hop Question Generation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2760–2775, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Reinforced Multi-task Approach for Multi-hop Question Generation (Gupta et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2020.coling-main.249.pdf
Data
HotpotQASQuAD