The DOI matches its Crossref record; 41 of the 42 references it cites were found in a registry or an index.
Learning to Ask: Neural Question Generation for Reading Comprehension
Open accessAbstract
We study automatic question generation for sentences from text passages in reading comprehension.We introduce an attention-based sequence learning model for the task and investigate the effect of encoding sentence-vs.paragraph-level information.In contrast to all previous work, our model does not rely on hand-crafted rules or a sophisticated NLP pipeline; it is instead trainable end-to-end via sequenceto-sequence learning.Automatic evaluation results show that our system significantly outperforms the state-of-the-art rule-based system.In human evaluations, questions generated by our system are also rated as being more natural (i.e., grammaticality, fluency) and as more difficult to answer (in terms of syntactic and lexical divergence from the original text and reasoning needed to answer).
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The authors performed both automatic evaluations using BLEU, METEOR, and ROUGE as well as human-based evaluation and found that their model outperformed the baseline model in [32] that they considered.”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [32]
In the citing paper
“Other approaches make use of naturalness [32, 35] and difficulty [35].”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [32]
In the citing paper
“However, the questions generated lack to a certain extent in terms of semantics and relevance as reported in most studies through human evaluation [32, 35, 36, 39, 56, 61].”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [32]
In the citing paper
“While ITSs have traditionally been defined and constructed by hand, recent approaches have applied ML techniques such as multi-armed bandit techniques to adaptively personalize sequences of learning activities [135], LSTMs to generate questions to evaluate language comprehension [205], and RL to improve the strategies used within the ITS [365,441].”
From Tackling climate change with machine learning (2023) · cites this paper as [205]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“W s and W t are parameters to be learned. here, LSTM is the Long Short-Term Memory (LSTM) network (Hochreiter and Schmidhuber, 1997).”
BackgroundGlove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 2×
“300d pre-trained embeddings (Pennington et al., 2014) for initialization.”
MethodLearning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 2×
“We model the conditional probability us-ing RNN encoder-decoder architecture (Bahdanau et al., 2015; Cho et al., 2014), and adopt the global attention mechanism (Luong et al., 2015a) to make the model focus on certain elements of the input when generating each word during decoding.”
MethodBLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344 · cited 2×
“The package includes BLEU 1, BLEU 2, BLEU 3, BLEU 4 (Papineni et al., 2002), METEOR (Denkowski and Lavie, 2014) and ROUGE L (Lin, 2004) evaluation scripts.”
MethodSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 4×
“More specifically, inspired by the recent success in neural machine translation (Sutskever et al., 2014; Bahdanau et al., 2015), summarization (Rush et al.”
BackgroundInfluentialNeural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 4×
“We model the conditional probability us-ing RNN encoder-decoder architecture (Bahdanau et al., 2015; Cho et al., 2014), and adopt the global attention mechanism (Luong et al., 2015a) to make the model focus on certain elements of the input when generating each word during decoding.”
BackgroundMethodInfluentialBinary Codes capable of currecting deletions, insertions, and reversals
Levenshtein, V. I. (1965) · Soviet physics. Doklady · Cited by 10,387
(2004) · Cited by 9,718
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382 · cited 3×
“We model the conditional probability us-ing RNN encoder-decoder architecture (Bahdanau et al., 2015; Cho et al., 2014), and adopt the global attention mechanism (Luong et al., 2015a) to make the model focus on certain elements of the input when generating each word during decoding.”
MethodShow, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248 · cited 2×
“, 2016), and image caption generation (Xu et al., 2015), we tackle question generation using a conditional neural language model with a global attention mechanism (Luong et al.”
Method
Research works printed but not linked: 2
- Thang Luong, Hieu Pham, and Christopher D. Manning. 2015a. Effective approaches to attentionbased neural machine translation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing . Association for Computational Linguistics, Lisbon, Portugal, pages 14121421. http://aclweb.org/anthology/D15-1166.
- Ruslan Mitkov and Le An Ha. 2003. Computeraided generation of multiple-choice tests. In Jill Burstein and Claudia Leacock, editors, Proceedings of the HLT-NAACL 03 Workshop on Building Educational Applications Using Natural Language Processing . pages 17-22. http://www.aclweb.org/anthology/W03-0203.pdf.
Cited by
Sorted by citations
Items 401–500 of 695
Steuer, T., Filighera, A., Meuser, T., & Rensing, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.04123 · Cited by 11
PROTEGE: Prompt-based Diverse Question Generation from Web Articles
Puranik, V. S., Majumder, A., & Chaoji, V. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.362 · Cited by 4
“QA extraction models (Alberti et al., 2019; Du et al., 2017; Reddy et al., 2017; Krishna and Iyyer, 2019) are generally pipeline-based which generates the question and the answer in a sequence.”
BackgroundJuan, Y., Chen, C.-C., Huang, H., & Chen, H. (2023) · International Conference on Natural Language Generation · doi:10.18653/v1/2023.inlg-main.35 · Cited by 4
UniPoll: A Unified Social Media Poll Generation Framework via Multiobjective Optimization
Li, Y., Xiang, R., Song, Y., & Li, J. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3512868 · Cited by 6
“According to the QAG definition, QA pairs are neither subjective nor open-ended, with answers serving as ground truth for questions [7], emphasizing explicit QA-context connections.”
Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization
Pagnoni, A., Fabbri, A. R., Kryściński, W., & Wu, C.-S. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.713 · Cited by 8
In-sample Curriculum Learning by Sequence Completion for Natural Language Generation
Jia, Q. F., Liu, Y., Tang, H., & Zhu, K. Q. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.666 · Cited by 8
Towards Data-Effective Educational Question Generation with Prompt-Based Learning
Wu, Y., Nouri, J., Megyesi, B. B., Henriksson, A., Duneld, M., & Li, X. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-37717-4_11 · Cited by 6
Ask To The Point: Open-Domain Entity-Centric Question Generation
Liu, Y., Huang, J., & Chang, K. C. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.178 · Cited by 5
Towards Vietnamese Question and Answer Generation: An Empirical Study
Hùng, P. Q., Le, H.-L., Nhat, M. D., Khang Tran, T., Tran-Tien, M., Dang, V.-H., Vu, H.-T., Nguyen, M.-T., & Phan, X.-H. (2024) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3675781 · Cited by 4
“Since then, QG models using neural networks have shown promising results, enabling the generation of questions in an end-to-end fashion [Du et al. 2017a; Zhou et al. 2017a].”
Tomikawa, Y., & Uto, M. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-64315-6_27 · Cited by 4
Current Trends and Future Prospects of Large-Scale Foundation Model in K-12 Education
Zhu, Q., Wang, M., Zhang, T., & Huang, H. (2025) · Frontiers of digital education. · doi:10.1007/s44366-025-0059-6 · Cited by 5
Question generation based on chat‐response conversion
Zhong, S.-H., Peng, J., & Liu, P. (2019) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5584 · Cited by 4
Harvest shopping advice: Neural Question Generation from multiple information sources in E-commerce
Wang, Y., Song, K., Bing, L., & Liu, X. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.12.013 · Cited by 4
Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism
Ji, T., Lyu, C., Cao, Z., & Cheng, P. (2021) · Entropy · doi:10.3390/e23111449 · Cited by 4
“An attention-based bidirectional long short-term memory (LSTM) model is employed to generate questions given a pair of passage and answer [8].”
MethodLamba, D., & Hsu, W. H. (2021) · 2021 2nd International Conference on Electronics, Communications and Information Technology (CECIT) · doi:10.1109/cecit53797.2021.00052 · Cited by 4
“The earliest work to use a deep-learning approach to generate questions was presented by Du. et al (2017) [25], where a sequence-to-sequence model (Sutskever et al., 2014 [26]) was used with the attention mechanism (Bahdanau et al., 2014) [27].”
MethodDeep human answer understanding for natural reverse QA
Yao, R., Hou, L., Yang, L., Gui, J., & Wu, O. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109625 · Cited by 4
AUTOMATIC QUESTION GENERATION THROUGH WORD VECTOR SYNCHRONIZATION USING LAMMA
Khandait, K., Bhura, S. A., & Asole, S. S. (2022) · Indian Journal of Computer Science and Engineering · doi:10.21817/indjcse/2022/v13i4/221304046 · Cited by 5
Neural Question Generation for the Portuguese Language: A Preliminary Study
Leite, B., & Cardoso, H. L. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16474-3_63 · Cited by 4
Zhang, C., Zhang, H., Sun, Y., & Wang, J. (2022) · ACM Symposium on Document Engineering (DocEng) · doi:10.1145/3558100.3563846 · Cited by 6
Обзор существующих методов автоматической генерации задач с условиями на естественном языке
Кручинин, В. В., & Kuzovkin, V. (2022) · Computer Tools in Education · doi:10.32603/2071-2340-2022-1-85-96 · Cited by 4
Zeng, H., Wei, B., Liu, J., & Fu, W. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.500 · Cited by 5
“With the popularity of neural networks, many research works (Du et al., 2017; Zhou et al., 2017; Zhao et al., 2018) adopt the encoder-decoder framework which combines attention (Bahdanau et al., 2015) and pointer (See et al., 2017) mechanisms to deal with the question generation problem in an…”
BackgroundDecoding a Neural Retriever’s Latent Space for Query Suggestion
Adolphs, L., Huebscher, M. C., Buck, C., Girgin, S., Bachem, O., Ciaramita, M., & Hofmann, T. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.601 · Cited by 9
Syntax-guided question generation using prompt learning
Hou, Z., Bi, S., Qi, G., Zheng, Y., Ren, Z., & Li, Y. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09421-7 · Cited by 4
“Du et al. [27] were the first to apply sequence-to-sequence models with attention mechanisms to question generation and achieved standout results.”
Paired Examples as Indirect Supervision in Latent Decision Models
Gupta, N., Singh, S., Gardner, M., & Roth, D. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.466 · Cited by 6
“We show how question generation (QG) models (Du et al., 2017; Krishna and Iyyer, 2019) can be used to generate paired questions.”
Multi-Lingual Question Generation with Language Agnostic Language Model
Wang, B., Yao, T., Chen, W., Xu, J., & Wang, X. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.199 · Cited by 4
“With the development of deep learning and large-scale question answering datasets, motivated by neural machine translation, Du et al. (2017) proposed a sequence to sequence (seq2seq) architecture combined with attention mechanism, achieving a promising result on QA dataset SQuAD.”
MethodImproving Dense FAQ Retrieval with Synthetic Training
Liu, L., Wu, Q., & Chen, G. (2021) · IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) · doi:10.1109/ic-nidc54101.2021.9660603 · Cited by 4
Intelligence Is Asking The Right Question: A Study On Japanese Question Generation
Nio, L., & Murakami, K. (2018) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2018.8639526 · Cited by 4
“Du et al. [15] point out the importance of attention-based sequence learning adaptation to the generation of questions.”
BackgroundMethodGeneration of English Question Answer Exercises from Texts using Transformers based Models
Berger, G., Rischewski, T., Chiruzzo, L., & Rosá, A. (2022) · IEEE Latin American Conference on Computational Intelligence (LA-CCI) · doi:10.1109/la-cci54402.2022.9981171 · Cited by 5
“[10] was one of the first works using this scheme, they evaluate two strategies: taking sentence-level information and taking paragraph-level information.”
MethodMultimodal Differential Network for Visual Question GenerationPreprint
Patro, B. N., Kumar, S., Kurmi, V. K., & Namboodiri, V. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.03986 · Cited by 4
“Recently there have been many deep learning based approaches as well for solving the text-based question generation task such as (Du et al., 2017).”
BackgroundTowards a Better Metric for Evaluating Question Generation SystemsPreprint
Nema, P., & Khapra, M. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.10192 · Cited by 4
“…problem and create even more training data, there is growing interest in developing techniques that can automatically generate questions from a given source, say a document (Du et al., 2017; Du and Cardie, 2017), knowledge base (Reddy et al., 2017; Serban et al., 2016), or image (Li et al., 2017) .”
BackgroundLet's Ask Again: Refine Network for Automatic Question GenerationPreprint
Nema, P., Mohankumar, A. K., Khapra, M. M., Srinivasan, B. V., & Ravindran, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05355 · Cited by 7
“Current models for AQG are based on the encode-attend-decode paradigm and they either generate questions from the passage alone (Du and Cardie, 2017; Du et al., 2017; Yao et al., 2018) or from the passage and a given answer (in which case the generated question must result in the given answer).”
MethodQuestion Generation from Paragraphs: A Tale of Two Hierarchical ModelsPreprint
Kumar, V., Chaki, R., Talluri, S. T., Ramakrishnan, G., Li, Y.-F., & Haffari, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.03407 · Cited by 4
“…based on recurrent neural networks (RNN), such as bi-directional LSTM. Equipped with different enhancements such as the attention, copy and coverage mechanisms, RNN-based models (Du et al., 2017; Kumar et al., 2018; Song et al., 2018) achieve good results on sentence-level question generation.”
BackgroundMethodInfluentialGenerating Fact Checking BriefsPreprint
Fan, A., Piktus, A., Petroni, F., Wenzek, G., Saeidi, M., Vlachos, A., Bordes, A., & Riedel, S. (2020) · arXiv (Cornell University) · doi:10.17863/cam.78760 · Cited by 4
Improving Controllability of Educational Question Generation by Keyword ProvisionPreprint
Chan, Y.-H., Chung, H.-L., & Fan, Y.-C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.01012 · Cited by 4
“Question generation (QG), taking a passage and an answer phrase as input and generating a context-related question as output, has received tremendous interests in recent years (Zhou et al. 2017; Zhao et al. 2018; Du, Shao, and Cardie 2017; Chan and Fan 2019; Dong et al. 2019; Bao et al. 2020).”
BackgroundMethodKourouklides, I. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/sjrkh · Cited by 4
Neural Question Generation Using Question Type Guidance
Sun, R. F., Zhou, X., & Fang, F. (2021) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis54983.2021.00075 · Cited by 3
Two-Step Question Retrieval for Open-Domain QA
Seonwoo, Y., Son, J., Jin, J., Lee, S., Kim, J., Ha, J.-W., & Oh, A. H. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.117 · Cited by 3
Graph convolutional network for difficulty-controllable visual question generation
Chen, F., Xie, J., Cai, Y., Lin, Z., Li, Q., & Wang, T. (2023) · World Wide Web · doi:10.1007/s11280-023-01202-x · Cited by 3
“[15]firstlyuseanattention-basedsequence-to-sequencemodeltogeneratequestionsfromsentences,achievingbetterperformancethan rule-basedsystemsinbothautomaticandhumanevaluations.”
An end-to-end transformer-based model for Arabic question generation
Lafkiar, S., & En-Nahnahi, N. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19958-3 · Cited by 3
“Alternatively, another pathway for generating questions is to use a machine learning-based system [4–8].”
Question Generation Capabilities of “Small" Large Language Models
Berger, J., Koß, J., Stamatakis, M., Hoppe, A., Ewerth, R., & Wartena, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70242-6_18 · Cited by 4
Shwe, L. L., Matayong, S., & Witosurapot, S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127244 · Cited by 3
Summary-Oriented Question Generation for Informational Queries
Yin, X., Zhou, L., Small, K., & May, J. (2021) · doi:10.18653/v1/2021.dialdoc-1.11 · Cited by 4
“4 questions per sentence on average (Du et al., 2017).”
BackgroundMethodResultInfluentialVirtual Assistant for Enhancing English Speaking Skills
Desai, A., Gandhi, Y., Gaglani, J., & Mulla, N. (2021) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca51532.2021.9544877 · Cited by 3
Zhou, X., Wu, O., & Jiang, C. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108485 · Cited by 3
Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data
Li, X., & Liu, M. (2023) · Workshop on Trustworthy Natural Language Processing (TrustNLP) · doi:10.18653/v1/2023.trustnlp-1.22 · Cited by 4
QGAE: an end-to-end answer-agnostic question generation model for generating question-answer pairs
Li, L., Zhang, L., Zhu, C., & Mao, Z. (2023) · JUSTC · doi:10.52396/justc-2023-0002 · Cited by 3
Afzaal, M., Nouri, J., & Aayesha, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42682-7_2 · Cited by 4
Efficient Multi-hop Question Generation
Emerson, J., & Chali, Y. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2023.08.159 · Cited by 3
Question Generation: An Experimental Study for Vietnamese Text
Hùng, P. Q., Le, H.-L., Minh, D. N., Khang Tran, T., Vu, H.-T., Nguyen, M.-T., & Phan, X.-H. (2023) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf60135.2023.10471875 · Cited by 3
“The human evaluation followed the work [36] to use two metrics.”
MethodRen, T., Wang, H., & Rafferty, K. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i23.34693 · Cited by 5
“Due to the in-accessibility of SQuAD 1.1’s test set, we use two popular splits of it from (Zhou et al. 2017) and (Du, Shao, and Cardie 2017), which we will further refer to SQuAD 1.1 / 1 and SQuAD 1.1 / 2 respectively.”
InfluentialEnhancing Question Generation with Commonsense Knowledge
Jia, X., Wang, H. E., Yin, D., & Wu, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-84186-7_10 · Cited by 6
Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
Kaffee, L.-A., Elsahar, H., Vougiouklis, P., Gravier, C., Laforest, F., Hare, J. S., & Simperl, E. P. B. (2018) · ePrints Soton (University of Southampton) · doi:10.48550/arxiv.1803.07116 · Cited by 3
“IR is an Information Retrieval (IR) baseline similar to those that have been used in other text generative tasks (Rush et al., 2015; Du et al., 2017).”
MethodBuilding an Agent for Factual Question Generation Task
Blšták, M., & Rozinajová, V. (2018) · World Symposium on Digital Intelligence for Systems and Machines (DISA) · doi:10.1109/disa.2018.8490637 · Cited by 3
“There are just few datasets consisting of pairs of triplets and questions which can be used for question generation from structured data ([5][15]).”
BackgroundShan, J., Nishihara, Y., Yamanishi, R., & Maeda, A. (2019) · Conference on Technologies and Applications of Artificial Intelligence (TAAI) · doi:10.1109/taai48200.2019.8959903 · Cited by 3
“In 2017, Du et al. proposed a method to treat the QG as a seq2seq (sequence to sequence) task [7].”
MethodControllable Question Generation via Sequence-to-Sequence Neural Model with Auxiliary Information
Cao, Z., Tatinati, S., & Khong, A. W. H. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207643 · Cited by 3
“A technique that learns factual embedding for logic triples before generating question via an attentive gated recurrent unit (GRU) decoder has been proposed [1], while the algorithm presented in [7] generates questions from passages by learning passageto-question mapping via a seq2seq model with attention mechanism.”
BackgroundMethodInfluentialConversational Question Generation in Russian
Makhnytkina, O. V., Matveev, A., Svischev, A., Korobova, P., Zubok, D. A., Mamaev, N., & Tchirkovskii, A. (2020) · Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct49677.2020.9211056 · Cited by 3
“Du et al. [25] and Zhao et al. [26] use a seq2seq architecture with copying to generate factual questions in an end-to-end approach.”
BackgroundChinese Neural Question Generation: Augmenting Knowledge into Multiple Neural Encoders
Liu, M., & Zhang, J. (2022) · Applied Sciences · doi:10.3390/app12031032 · Cited by 6
“[12] observed that 20% of questions in the SQuAD dataset require paragraph-level information to be answered.”
BackgroundMethodInfluentialLearning Enhancement Using Question-Answer Generation for e-Book Using Contrastive Fine-Tuned T5
Kumar, S., Chauhan, A., & Kumar, C. P. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-24094-2_5 · Cited by 3
WikiOmnia: filtration and evaluation of the generated QA corpus on the whole Russian Wikipedia
Pisarevskaya, D., & Shavrina, T. (2022) · Workshop on Generation, Evaluation and Metrics (GEM) · doi:10.18653/v1/2022.gem-1.10 · Cited by 3
“Classical QA pair generation pipeline lets firstly choose among text points that should be asked, then ask a question based on these points, and after that find the most likely candidate from the answer spans in text (Reddy et al., 2017; Du et al., 2017; Al-berti et al., 2019; Lee et al., 2020).”
BackgroundGenerating Highly Relevant QuestionsPreprint
Qiu, J., & Xiong, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.03401 · Cited by 3
“Specifically, the encoder-decoder seq2seq model (Du et al., 2017; Zhou et al., 2017; Song et al., 2018) is used to encode a passage and generate a question corresponding to the answer.”
InfluentialUnsupervised Question Answering for Fact-CheckingPreprint
Jobanputra, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.07154 · Cited by 3
“Du et al. (2017) introduced a sequence-to-sequence model with an attention mechanism, out-performing rule-base question generation systems.”
Deep Exemplar Networks for VQA and VQGPreprint
Patro, B. N., & Namboodiri, V. P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.09551 · Cited by 3
“Recently there have been many deep learning based approaches as well for solving the text-based question generation task such as as [46].”
BackgroundShinoda, K., Sugawara, S., & Aizawa, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.03238 · Cited by 3
“Since the SQuAD test set has not been released, we use the split of the dataset, SQuAD-Du (Du et al., 2017”
MethodEnhancing Question Generation with Commonsense KnowledgePreprint
Jia, X., Wang, H. E., Yin, D., & Wu, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10454 · Cited by 3
“Different from these, neural network-based methods are completely data-driven and trainable in an end-to-end fashion (Du et al., 2017; Zhou et al., 2017; Zhao et al., 2018; Song et al., 2018; Kim et al., 2018; Nema et al., 2019; Zhou et al., 2019a; Zhou et al., 2019b; Jia et al., 2020b; Ko et al., 2020).”
Akyön, F. Ç., Çavuşoğlu, D., Cengiz, C., Altinuc, S. O., & Temizel, A. (2021) · arXiv (Cornell University) · doi:10.3906/elk-2111-63 · Cited by 3
An AI-based Solution for Enhancing Delivery of Digital Learning for Future TeachersPreprint
Kang, Y., Forkan, A. R. M., Jayaraman, P. P., Wieland, N., Kollias, E., Du, H., Thomson, S., & Li, Y.-F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.01229 · Cited by 3
“Various NLP methods are developed in the literature for natural question generation such as the sequence-to-sequence (Seq2Seq), [20], encoder-decoder[21], and QG-Net [22].”
Kang, Y., Forkan, A. R. M., Banerjee, A., Jayaraman, P. P., McCosker, A., Kim, S.-S., Wieland, N., & Kollias, L. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3620274 · Cited by 2
“Another study developed an attention-based sequence learning model, which investigated the impact of encoding sentence-vs-paragraph-level information [20].”
Generating Instructive Questions from Multiple Articles to Guide Reading in E-Bibliotherapy
Xin, Y., Cao, L., Wang, X., He, X., & Feng, L. (2021) · Sensors · doi:10.3390/s21093223 · Cited by 2
“nqg [10] is the state-of-the-art model for question generation on SQuAD dataset, both its encoder and decoder are 2-layer LSTMs with 600 hidden units while the LSTM of the encoder is bidirectional.”
BackgroundMethodInfluentialA Study on Text Rank Algorithm for Automatic Text Summarization and Question Generation
Deena, G. (2021) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-2302 · Cited by 2
Question Generation in the Thai Language Using MT5
Wiwatbutsiri, N., Suchato, A., Punyabukkana, P., & Tuaycharoen, N. (2022) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse54890.2022.9836271 · Cited by 2
Refined-Para Forming Question Generation System Using Lamma
Khandait, K., Bhura, S. A., & Asole, S. S. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-24352-3_6 · Cited by 3
EQGTL: An Ensemble Model for Relevant Question Generation using Transfer Learning
Godslove, J. F., & Nayak, A. K. (2022) · International Conference on Machine Learning, Computer Systems and Security (MLCSS) · doi:10.1109/mlcss57186.2022.00054 · Cited by 2
Bullshit, Pragmatic Deception, and Natural Language Processing
Deck, O. (2023) · Dialogue & Discourse · doi:10.5210/dad.2023.103 · Cited by 2
“(2020), but also on a large amount of literature on question generation for a variety of purposes (Heilman and Smith, 2010; Du et al., 2017; Duan et al., 2017; Zhou et al., 2018; Kurdi et al., 2020).”
Post-training with Data Augmentation for Improving T5-Based Question Generator
Park, G.-M., Hong, S.-E., Hong, C. S., & Park, S.-B. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-1252-0_94 · Cited by 2
Attentive Neural Seq2Seq for Arabic Question Generation
Lafkiar, S., Alami, H., Zouitni, M., Burmani, N., Badir, H., & En-Nahnahi, N. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-26384-2_71 · Cited by 2
Defending Machine Reading Comprehension against Question-Targeted Attacks
Fang, X., & Wang, W. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191697 · Cited by 2
“We apply a regular split for training victim models, in which the original dev set is used as test set, and the original training set is randomly divided into training set and dev set at a 9: 1 ratio [42].”
MethodA Framework for Automatic Generation of Spoken Question-Answering Data
Menevşe, M. Ü., Manav, Y., Arısoy, E., & Özgür, A. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.342 · Cited by 2
“Research in question generation has shifted from RNN or LSTM based models (Du et al., 2017; Song et al., 2018; Duan et al., 2017; Du and Cardie, 2018) to transformer encoder-decoders.”
BackgroundGenerating Question-Answer Pairs for Few-Shot Learning
Wang, Y., & Li, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44213-1_35 · Cited by 2
Multi-perspective thought navigation for source-free entity linking
Peng, B., He, W. P., Chen, B., Villavicencio, A., & Wu, C. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2023.12.020 · Cited by 2
Quizmaster GPT: CustomGPT for Education
(2024) · Engineering Open Access · doi:10.33140/eoa.02.01.01 · Cited by 2
Enhancing Question Generation with Syntactic Details and Multi-Level Attention Mechanism
Zhou, C., Zhu, J., Wang, Q., Meng, C., Pan, C., & Shi, J. (2023) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait60137.2023.10528429 · Cited by 2
“Among these approaches is the sequence-to-sequence model suggested by Du et al. [6], which has proven effective.”
MethodTriKF: Triple-Perspective Knowledge Fusion Network for Empathetic Question Generation
Chen, T., Shen, Y., Chen, X., Zhang, L., & Zhao, S. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3418820 · Cited by 2
“For example, QG can serve as a data augmentation technique in the reading comprehension and question– answering (QA) fields by generating abundant testing questions or QA pairs, reducing the manpower of manually making up these questions [37], [38], [39], [40], [41].”
EQGG: Automatic Question Group Generation
Huang, P., Chan, Y.-H., Yang, C.-Y. H., Chen, H.-Y., & Fan, Y.-C. (2024) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2024.3430225 · Cited by 2
Automatic Question Generation: A Comparative Analysis of Rule-Based and Neural Network-Based Models
Velmurugan, H., Pandiarajan, N., Ravi, L., Voleti, S., Sheik, R., & Nirmala, S. J. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-1724-8_21 · Cited by 2
Obionwu, C. V., Mukherjee, D., Devadas, V., Mittal, S., Ghumman, A. N., John, A. K., Buch, A., Nuernberger, A., & Saake, G. (2024) · Lecture notes in educational technology · doi:10.1007/978-981-97-3883-0_3 · Cited by 2
Knowledge Base Question Generation via Data Augmentation with Dynamic-Prompt
Zhao, L., Yin, X., Wang, Y., & Li, F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72350-6_17 · Cited by 2
Lin, R., Xu, D., Wang, H., Chen, Z., Wang, Y., & Liu, S. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831835 · Cited by 2
“Concurrently, other works explore applying neural network-based methods in selecting distractors [9]–[12].”
BackgroundTAGNet: a tiny answer-guided network for conversational question generation
Wang, Z., Zhu, H., Liu, M. Z., & Qin, B. (2022) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-022-01737-x · Cited by 2
“[23] and [24] apply neural-based models for QG and achieve more promising results using the large-scale questionanswering dataset SQuAD [25].”
BackgroundMethodFactoid Question Answering with Distant Supervision
Zhang, H., Liang, X., Xu, G.-L., Fu, K., Li, F., & Huang, T.-L. (2018) · Entropy · doi:10.3390/e20060439 · Cited by 1
“[14] introduce a supervised neural network for question generation.”
BackgroundDORB: Dynamically Optimizing Multiple Rewards with Bandits
Pasunuru, R., Guo, H., & Bansal, M. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.625 · Cited by 2
Paragraph Level Multi-Perspective Context Modeling for Question Generation
Bai, J., Rong, W., Xia, F., Wang, Y., Ouyang, Y., & Xiong, Z. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414933 · Cited by 2
“To improve the ability of utilizing paragraph-level context, Du et al. [9] proposed to concatenate sentence and paragraph hidden states obtained by RNN encoders.”
BackgroundMethodThe SelectGen Challenge: Finding the Best Training Samples for Few-Shot Neural Text Generation
Chang, E., Shen, X., Marin, A., & Demberg, V. (2021) · International Conference on Natural Language Generation · doi:10.18653/v1/2021.inlg-1.36 · Cited by 2
Mao, Y., Ma, W., Lei, D., Han, J., & Ren, X. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.413 · Cited by 2
“We use the SQuAD 1.1 dataset (Rajpurkar et al., 2016), which is repurposed by Du et al. (2017) for question generation.”
MethodInfluentialAn Answer Driven Model For Paragraph-level Question Generation
Xu, C., & Xu, J. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534455 · Cited by 2
“Reference [4] first proposed using the SQuAD v1.”
BackgroundMethodInfluentialQuestion type and answer related keywords aware question generation
Zhang, J., Rong, W., Chen, D., & Xiong, Z. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-219249 · Cited by 2
“To solve this problem, Bahdanau et al. [25] and Luong et al. [26] proposed attention mechanism to dynamically focus on a subset of the encoded input sequence, instead of completely relying on the fixed-size vector, which is widely adopted in NQG [27–29].”
Speaker Diarization and BERT-Based Model for Question Set Generation from Video Lectures
Nittala, S., Agarwal, P. R., Vishnu, R., & Shanbhag, S. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-0095-2_42 · Cited by 2
Extractive text summarisation using Bayesian state estimation of sentences: A Markovian framework
Haez, S. G., & Shamsfakhr, F. (2022) · Journal of Information Science · doi:10.1177/01655515221112842 · Cited by 2
“Automatic question generation [19–21] and event extraction [22] are other machine reading comprehension practices that can also yield a good text summarisation system.”
Bitew, S. K., Deleu, J., Doğruöz, A. S., Develder, C., & Demeester, T. (2023) · Workshop on Innovative Use of NLP for Building Educational Applications · doi:10.18653/v1/2023.bea-1.51 · Cited by 2
Discord Questions: A Computational Approach To Diversity Analysis in News Coverage
Laban, P., Wu, C.-S., Murakhovs’ka, L., Chen, X., & Xiong, C. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.380 · Cited by 7
Metadata
- Authors
- Du, X., Shao, J., & Cardie, C.
- Affiliations
- Cornell University (US)
- Shanghai Jiao Tong University (CN)
- Corresponding author
- Cardie, Claire
- Venue
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2017
- Pages
- 1342-1352
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2962717047
- Cited by
- 696
- References
- 42
- Citations by year
- 2026: 25 · 2025: 36 · 2024: 54 · 2023: 95 · 2022: 101 · 2021: 120 · 2020: 111 · 2019: 90 · 2018: 56 · 2017: 8
- FWCI
- 33.06
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- automatic question generation, reading comprehension, end-to-end learning, question difficulty
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
