English

Closed-book Question Generation via Contrastive Learning

Computation and Language 2023-02-14 v2

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.

Keywords

Cite

@article{arxiv.2210.06781,
  title  = {Closed-book Question Generation via Contrastive Learning},
  author = {Xiangjue Dong and Jiaying Lu and Jianling Wang and James Caverlee},
  journal= {arXiv preprint arXiv:2210.06781},
  year   = {2023}
}

Comments

To appear in EACL 2023

R2 v1 2026-06-28T03:31:13.076Z