Closed-book Question Generation via Contrastive Learning

Xiangjue Dong, Jiaying Lu, Jianling Wang, James Caverlee


Abstract
Question Generation (QG) is a fundamental NLP task for many downstream applications. Recent studies on open-book QG, where supportive answer-context pairs are provided to models, have achieved promising progress. However, generating natural questions under a more practical closed-book setting that lacks these supporting documents still remains a challenge. In this work, we propose a new QG model for this closed-book setting that is designed to better understand the semantics of long-form abstractive answers and store more information in its parameters through contrastive learning and an answer reconstruction module. Through experiments, we validate the proposed QG model on both public datasets and a new WikiCQA dataset. Empirical results show that the proposed QG model outperforms baselines in both automatic evaluation and human evaluation. In addition, we show how to leverage the proposed model to improve existing question-answering systems. These results further indicate the effectiveness of our QG model for enhancing closed-book question-answering tasks.
Anthology ID:
2023.eacl-main.230
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3150–3162
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2023.eacl-main.230/
DOI:
10.18653/v1/2023.eacl-main.230
Bibkey:
Cite (ACL):
Xiangjue Dong, Jiaying Lu, Jianling Wang, and James Caverlee. 2023. Closed-book Question Generation via Contrastive Learning. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3150–3162, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Closed-book Question Generation via Contrastive Learning (Dong et al., EACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2023.eacl-main.230.pdf
Video:
 https://preview.aclanthology.org/build-pipeline-with-new-library/2023.eacl-main.230.mp4