Abstract
Generating high-quality complete question sets (for example, the question, answer and distractors) in reading comprehension tasks is challenging and rewarding. This paper proposes a question-distractor joint generation framework (QDG). The framework can automatically generate both questions and distractors given a background text and the specified answer. Our work makes it possible to combine complete multiple-choice reading comprehension questions that can be better applied to educators’ work. While there have been independent studies of question generation and distractor generation in previous studies, there have been few joint question-distractor generation studies. In a past joint generation, distractors could only be constructed by generating questions first and then by sorting the answers with similar words. It was impossible to generate question-distractor pairs in an end-to-end unified joint generation approach. To the best of our knowledge, we are the first to propose an end-to-end question-distractor joint generation framework on the RACE dataset. This paper finds that distractors are somehow relevant to the background articles, by suppressing those related parts, thus enabling the generated questions to be better focused on the relevant parts of the correct answers. The experimental results show that the model achieves a giant breakthrough in the question-distractor pair generation task. The question generation task achieves better performance than baselines. For further evaluation, we also manually people for evaluation to demonstrate the educational relevance of our model in generating high-quality question-distractor pairs.
Similar content being viewed by others
Data Availability
All data included in this study are available upon request by contact with the corresponding author.
References
Adamson D, Bhartiya D, Gujral B, Kedia R, Singh A, Rosé CP (2013) Automatically generating discussion questions. In: AIED. Lecture notes in computer science, vol 7926. pp 81–90, Springer
Cao ND, Aziz W, Titov I (2019) Question answering by reasoning across documents with graph convolutional networks. In: Association for computational linguistics. NAACL-HLT (1) pp 2306–2317
Cao Y, Fang M, Tao D (2019) BAG: Bi-directional attention entity graph convolutional network for multi-hop reasoning question answering. In: NAACL-HLT, (1) pp 357–362, Association for computational linguistics
Chen Y, Wu L, Zaki MJ (2020) Reinforcement learning based graph-to-sequence model for natural question generation. In: ICLR. Open Review net
Cheng Y, Li S, Liu B, Zhao R, Li S, Lin C, Zheng Y (2021) Guiding the growth: Difficulty-controllable question generation through step-by-step rewriting. In: Association for computational linguistics. ACL/IJCNLP (1) pp 5968–5978
Deepak G, Kumar N, Bharadwaj GVSY, Santhanavijayan A (2019) Ontoquest: an ontological strategy for automatic question generation for e-assessment using static and dynamic knowledge. In: 2019 Fifteenth international conference on information processing (ICINPRO), pp 1–6. IEEE
Dong L, Yang N, Wang W, Wei F, Liu X, Wang Y, Gao J, Zhou M, Hon H (2019) Unified language model pre-training for natural language understanding and generation. In: NeurIPS, pp 13042–13054
Du X, Shao J, Cardie C (2017) Learning to ask: Neural question generation for reading comprehension. In: Association for computational linguistics. ACL (1)pp 1342–1352
Fan A, Gardent C, Braud C, Bordes A (2019) Using local knowledge graph construction to scale seq2seq models to multi-document inputs. In: Association for computational linguistics. EMNLP/IJCNLP (1) pp 4184–4194
Gao Y, Bing L, Chen W, Lyu MR, King I (2019) Difficulty controllable generation of reading comprehension questions. In: IJCAI, pp 4968–4974. http://www.ijcai.org
Gao Y, Bing L, Li P, King I, Lyu MR (2019) Generating distractors for reading comprehension questions from real examinations. In: AAAI, pp 6423–6430. AAAI Press
Guo Q, Kulkarni C, Kittur A, Bigham JP, Brunskill E (2016) Questimator: Generating knowledge assessments for arbitrary topics. In: IJCAI, pp 3726–3732. IJCAI/AAAI press
Heilman M, Smith NA (2010) Good question! statistical ranking for question generation. In: The association for computational linguistics, HLT-NAACL. pp 609–617
Jia X, Zhou W, Sun X, Wu Y (2021) EQG-RACE: Examination-type question generation. In: AAAI, pp 13143–13151. AAAI Press
Kumar G, Banchs RE, D’Haro LF (2015) Revup: Automatic gap-fill question generation from educational texts. In: The association for computer linguistics, BEA@NAACL-HLT. pp 154–161
Kumar V, Hua Y, Ramakrishnan G, Qi G, Gao L, Li Y (2019) Difficulty-controllable multi-hop question generation from knowledge graphs. In: ISWC (1). Lecture Notes in computer science, vol 11778. pp 82–398. Springer
Lai G, Xie Q, Liu H, Yang Y, Hovy EH (2017) RACE: Large-scale reading comprehension dataset from examinations. In: Association for computational linguistics, EMNLP. pp 785–794
Lelkes ÁD, Tran VQ, Yu C (2021) Quiz-style question generation for news stories. In: WWW. pp 2501–2511, ACM /IW3c2
Li J, Luong M, Jurafsky D (2015) A hierarchical neural autoencoder for paragraphs and documents. In: ACL (1). pp 1106–1115, The association for computer linguistics
Liang C, Yang X, Dave N, Wham D, Pursel B, Giles CL (2018) Distractor generation for multiple choice questions using learning to rank. In: BEA@NAACL-HLT. pp 284–290. Association for computational linguistics
Liu B, Wei H, Niu D, Chen H, He Y (2020) Asking questions the human way: Scalable question-answer generation from text corpus. In: WWW, pp 2032–2043, ACM/IW3c2
Liu B, Zhao M, Niu D, Lai K, He Y, Wei H, Xu Y (2019) Learning to generate questions by learningwhat not to generate. In: WWW, pp 1106–1118, ACM
Luong T, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. In: EMNLP, pp 1412–1421, The association for computational linguistics
Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: EMNLP, pp 532–1543, ACL
Peters ME, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (2018) Deep contextualized word representations. In: NAACL-HLT, pp 2227–2237, Association for computational linguistics
Qi W, Yan Y, Gong Y, Liu D, Duan N, Chen J, Zhang R, Zhou M (2020) Prophetnet: Predicting future n-gram for sequence-to-sequence pre-training. In: EMNLP (Findings). findings of ACL, vol. EMNLP 2020, pp 2401–2410, Association for Computational Linguistics
Qiu Z, Wu X, Fan W (2020) Automatic distractor generation for multiple choice questions in standard tests. In: COLING, pp 2096–2106, International committee on computational linguistics
Qu F, Jia X, Wu Y (2021) Asking questions like educational experts: Automatically generating question-answer pairs on real-world examination data. In: EMNLP (1). pp 2583–2593. Association for computational linguistics
Ren S, Zhu KQ (2021) Knowledge-driven distractor generation for cloze-style multiple choice questions. In: AAAI pp 4339–4347, AAAI Press
Sakaguchi K, Arase Y, Komachi M (2013) Discriminative approach to fill-in-the-blank quiz generation for language learners. In: ACL (2). pp 238–242, The association for computer linguistics
Seo MJ, Kembhavi A, Farhadi A, Hajishirzi H (2017) Bidirectional attention flow for machine comprehension. In: ICLR, (Poster). Open Review Net
Shah R, Shah D, Kurup L (2017) Automatic question generation for intelligent tutoring systems. In: 2017 2Nd international conference on communication systems, computing and IT applications (CSCITA). pp 127–132, IEEE
Shuai P, Wei Z, Liu S, Xu X, Li L (2021) Topic enhanced multi-head co-attention: Generating distractors for reading comprehension. In: IJCNN, pp 1–8. IEEE
Stasaski K, Hearst MA (2017) Multiple choice question generation utilizing an ontology. In: BEA@EMNLP pp 303–312, Association for computational linguistics
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: NIPS. pp. 3104–3112
Tan J, Wan X, Xiao J (2017) From neural sentence summarization to headline generation: a coarse-to-fine approach. In: IJCAI pp 4109–4115 https://www.ijcai.org
Tang D, Duan N, Qin T, Zhou M (2017) Question answering and question generation as dual tasks. CoRR. arXiv:1706.02027
Wagner C, Bolloju N (2005) Supporting knowledge management in organizations with conversational technologies: Discussion forums, weblogs, and wikis. J Database Manag 16(2):I
Wang W, Hao T, Liu W (2007) Automatic question generation for learning evaluation in medicine. In: ICWL, Lecture Notes in computer science, vol 4823. pp 242–251. Springer
Xie J, Peng N, Cai Y, Wang T, Huang Q (2022) Diverse distractor generation for constructing high-quality multiple choice questions. IEEE ACM Trans Audio Speech Lang Process 30:280–291
Yuan W, Yin H, He T, Chen T, Wang Q, Cui L (2022) Unified question generation with continual lifelong learning. In: WWW, pp 871–881, ACM
Zhao Y, Ni X, Ding Y, Ke Q (2018) Paragraph-level neural question generation with maxout pointer and gated self-attention networks. In: EMNLP, pp 3901–3910, Association for computational linguistics
Zhou Q, Yang N, Wei F, Tan C, Bao H, Zhou M (2017) Neural question generation from text: a preliminary study. In: NLPCC, Lecture Notes in computer science, vol 10619. pp 662–671. Springer
Zhou X, Luo S, Wu Y (2020) Co-attention hierarchical network: Generating coherent long distractors for reading comprehension. In: AAAI, pp 9725–9732, AAAI Press
Acknowledgements
This work was supported by NSFC (grant No. 61877051). Li Li is the correspongding author for the paper.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Shuai, P., Li, L., Liu, S. et al. QDG: A unified model for automatic question-distractor pairs generation. Appl Intell 53, 8275–8285 (2023). https://doi.org/10.1007/s10489-022-03894-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03894-6