Abstract
BART is a powerful pre-trained model that has excelled in generative tasks such as text summarization, question answering, and machine translation. In previous studies, the BART model has often been used for multi-hop question generation(MQG) task, and it significantly improved the quality of generated questions compared to recurrent neural network-based models. However, due to the differences between downstream tasks and pre-training tasks, BART still generates some nonsensical and grammatically incorrect questions in multi-hop question generation tasks. These types of questions can have a negative impact on the user’s reading experience. To address this challenge, we propose a BART-based retouching framework(BRQG), which builds upon BART. Specifically, BRQG uses BART-generated questions as a starting point, and introduces a Retouching Network module to reattend to the questions and context. The Retouching Gate layer then fuses this attention in an appropriate proportion to generate second-round questions that are more complete and readable. In addition, we propose a Entity Awareness Enhancement module, which construct graph structures from input documents to improve the correctness of entity generation. We conducted experiments on the HotpotQA dataset, and the results show that our model outperforms the currently proposed model on BLEU4, demonstrating the advantages and feasibility of BRQG in multi-hop question generation.
Funding provided by The Fundamental Research Funds for the Central Universities(N2116019), the National Natural Science Foundation of China (62137001,72271048), the Liaoning Natural Science Foundation (2022-MS-119), the Liaoning Province Discipline Inspection Supervision Big Data Key Laboratory (ZX20220460) and China University Industry-University-Research Innovation Fund(2022MU017).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Heilman, M., Smith, N.A.: Good question! statistical ranking for question generation. In: Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 609–617 (2010)
Danon, G., Last, M.: A syntactic approach to domain-specific automatic question generation. arXiv preprint: arXiv:1712.09827 (2017)
Duan, N., Tang, D., Chen, P., Zhou, M.: Question generation for question answering. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 866–874 (2017)
Tang, D., Duan, N., Qin, T., Yan, Z., Zhou, M.: Question answering and question generation as dual tasks. arXiv preprint: arXiv:1706.02027 (2017)
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. arXiv preprint: arXiv:1606.05250 (2016)
Min, S., Zhong, V., Socher, R., Xiong, C.: Efficient and robust question answering from minimal context over documents. arXiv preprint: arXiv:1805.08092 (2018)
KMazidi, K., Nielsen, R.: Linguistic considerations in automatic question generation. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 321–326 (2014)
Du, X., Shao, J., Cardie, C.: Learning to ask: neural question generation for reading comprehension. arXiv preprint: arXiv:1705.00106 (2017)
Zhou, Q., Yang, N., Wei, F., Tan, C., Bao, H., Zhou, M.: Neural question generation from text: a preliminary study. In: Huang, X., Jiang, J., Zhao, D., Feng, Y., Hong, Yu. (eds.) NLPCC 2017. LNCS (LNAI), vol. 10619, pp. 662–671. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-73618-1_56
Kim, Y., Lee, H., Shin, J., Jung, K.: Improving neural question generation using answer separation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6602–6609 (2019)
Zhao, Y., Ni, X., Ding, Y., Ke, Q.: Paragraph-level neural question generation with maxout pointer and gated self-attention networks. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3901–3910 (2018)
Nema, P., Mohankumar, A.K., Khapra, M.M., Srinivasan, B.V., Ravindran, B.: Let’s ask again: refine network for automatic question generation. arXiv preprint: arXiv:1909.05355 (2019)
Pan, L., Xie, Y., Feng, Y., Chua, T.S., Kan, M.Y.: Semantic graphs for generating deep questions. arXiv preprint: arXiv:2004.12704 (2020)
Su, D., Xu, P., Fung, P.: QA4QG: using question answering to constrain multi-hop question generation. In: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8232–8236. IEEE (2022)
Wang, L., Xu, Z., Lin, Z., Zheng, H., Shen, Y.: Answer-driven deep question generation based on reinforcement learning. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 5159–5170 (2020)
Fei, Z., Zhang, Q., Gui, T., Liang, D., Wang, S., Wu, W., Huang, X.J.: CQG: a simple and effective controlled generation framework for multi-hop question generation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 6896–6906 (2022)
Qiu, L., et al.: Dynamically fused graph network for multi-hop reasoning. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6140–6150 (2019)
Velickovic, P., et al.: Graph attention networks. Stat 1050(20), 10–48550 (2017)
Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint: arXiv:1508.04025 (2015)
Papineni, K., Roukos, S., Ward, T., Zhu, W. J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318 (2002)
Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pp. 65–72 (2005)
Lin, C.-Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74–81 (2004)
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint: arXiv:1910.13461 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liao, T., Xu, B., Han, Y., Li, S., Zhang, S. (2023). BRQG: A BART-Based Retouching Framework for Multi-hop Question Generation. In: Yang, X., et al. Advanced Data Mining and Applications. ADMA 2023. Lecture Notes in Computer Science(), vol 14180. Springer, Cham. https://doi.org/10.1007/978-3-031-46677-9_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-46677-9_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46676-2
Online ISBN: 978-3-031-46677-9
eBook Packages: Computer ScienceComputer Science (R0)