Abstract
In the field of education, framing right questions is an important way of measuring the knowledge of an individual, and automation of the generation of questions would reduce the strain on educators and thus increase efficiency in learning. Literature survey reveals that while there are several promising methods for testing comprehension generating questions, but none of them can be used reliably for generating meaningful questions all the time, and thus, further research is required. A novel method of generating questions is presented in this paper from input text, by encoding the answers into the model and using attention that learns the dependencies between both input text and answers and between input text and questions, thus generating questions which are relevant to the answer given. The dataset used is the SQuAD dataset, and the model produces fluent questions which have been evaluated with the required metrics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
P. Rajpurkar, J. Zhang, K. Lopyrev, P. Liang, SQuAD: 100,000+ Questions for machine comprehension of text, in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)Association for Computational Linguistics (2016), pp. 2383–2392
I. Sutskever, O. Vinyals, Q.V. Le, Sequence to sequence learning with neural networks. Adv. Neural Inf. 3104–3112 (2014)
S. Xingwu, L. Jing, L. Yajuan, H. Wei, M. Yanjun, W. Shi, Answer-focused and position-aware neural question generation, in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018), pp. 3930–3939
X. Ma, Q. Zhu, Y. Zhou, X. Li, Improving question generation with sentence-level semantic matching and answer position inferring, in Proceedings of the AAAI Conference on Artificial Intelligence (2020), 8464–8471
K. Yanghoon, L. Hwanhee, S. Joongbo, J. Kyomin, Improving Neural Question Generation using Answer Separation (2018). arXiv preprint arXiv:1809.02393
H. Vrindavan, W., Marilyn, Neural generation of diverse questions using answer focus, contextual and linguistic features, in International Conference on Natural Language Generation (INLG) (2018), pp. 296–306
Z. Qingyu, Y. Nan, W. Furu, T. Chuanqi, B. Hangbo, Z. Ming, Neural question generation from text: a preliminary study. CoRR, abs/1704.01792, 2017. http://arxiv.org/abs/1704.01792
D. Xinya, S., Junru, C. Claire, Learning to ask: neural question generation for reading comprehension, in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 (1: Long Papers), pp. 1342–1352
J. Weston, B. Antoine, C. Sumit, R. Alexander, M. Bart, J. Armand, M. Tomas, Towards AI-complete question answering: a set of prerequisite toy tasks (2016)
M. Hermann, K. Tomas, G. Edward, E. Lasse, K. Will, S. Mustafa, B. Phil, Teaching machines to read and comprehend, in Advances in Neural Information Processing Systems (NIPS) (2015), pp. 1693–1701
D. Chen, D., B. Jason, M. Christopher, A thorough examination of the cnn/daily mail reading comprehension task, in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (vol 1: Long Papers). Association for Computational Linguistics (2016), pp. 2358–2367. http://www.aclweb.org/anthology/P16-1223
I. Goodfellow, D. Warde-Farley, M. Mirza, A. Courville, Y. Bengio, Maxout networks, in Proceedings of The 30th International Conference on Machine Learning (2013), pp. 1319–1327
Ç.S. Gülçehre, S. Ahn, R. Nallapati, B. Zhou, Y. Bengio, Pointing the unknown words. CoRR abs/1603.08148 (2016)
W. Zich, A. Lan, W. Nie, A. Waters, P. Grimaldi, R. Baraniuk, QG-Net: a data-driven question generation model for educational content, inProceedings of the Fifth Annual ACM Conference on Learning at Scale (2018), pp 1–10. https://doi.org/10.1145/3231644.3231654
W. Zaremba, I. Sutskever, O. Vinyals, Recurrent neural network regularization (September 2014). arXiv preprint arXiv:1409.2329
K. Papineni, R. Salim, W. Todd, W. Wei-Jing and Z.: Bleu: a method for automatic evaluation of machine translation, in Proceedings of 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (2002), pp. 311–318. https://doi.org/10.3115/1073083.1073135
M. Denkowski, L. Alon, Meteor universal: language specific translation evaluation for any target language, in Proceedings of the Ninth Workshop on Statistical Machine Translation. Association for Computational Linguistics (2014), pp. 376–380. http://www.aclweb.org/anthology/W14-3348
C. Lin, Rouge: a package for automatic evaluation of summaries, in ed. by S. Szpakowicz, M.-F. Moens, Text Summarization Branches Out: Proceedings of the ACL-04 Workshop. Association for Computational Linguistics (2004), pp. 74–81. http://aclweb.org/anthology/W/W04/W04-1013.pdf
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kumar, A.P., Sridhar, G., Nayak, A., Shenoy, M.K. (2022). A Neural Attention Model for Automatic Question Generation Using Dual Encoders. In: Shetty D., P., Shetty, S. (eds) Recent Advances in Artificial Intelligence and Data Engineering. Advances in Intelligent Systems and Computing, vol 1386. Springer, Singapore. https://doi.org/10.1007/978-981-16-3342-3_34
Download citation
DOI: https://doi.org/10.1007/978-981-16-3342-3_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3341-6
Online ISBN: 978-981-16-3342-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)