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 601–695 of 695
Mao, Y., Ma, W., Lei, D., & Ren, X. (2021) · arXiv (Cornell University)
Automatic Question and Answer Generation from Text Using Neural Networks
Soni, S., Kumar, P., & Saha, A. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-15-9774-9_46
Automated Generation of Assessment Questions from Textbook Models
Dresscher, L. L. J. (2021) · Utrecht University Repository (Utrecht University)
Barradas, N. A. M. (2020) · Repositório do ISCTE-IUL
On Training Instance Selection for Few-Shot Neural Text GenerationPreprint
Chang, E., Shen, X., Yeh, H.-S., & Demberg, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03176
Question Generation with Adaptive Copying Neural Networks
Lu, X. (2019) · doi:10.22215/etd/2019-13754
“[1] in 2017 conducted a supplementary study.”
BackgroundMethodInfluentialSemantic Templates for Generating Long-Form Technical Questions
Pal, S., Singh, A., Datta, S., Patil, S., Bhattacharya, I., & Palshikar, G. K. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-83527-9_20
Meta Sequence Learning for Generating Adequate Question-Answer PairsPreprint
Zhang, C., & Wang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.01620
“Their experiments show that the BLEU-4 (Papineni et al., 2002), METEOR (Banerjee and Lavie, 2005), and ROUGE-L (Lin, 2004) scores on the questions generated are, respectively, 16.2, 19.92, 43.96, which are 3 to 4 points higher than the earlier results on the same dataset (Du et al., 2017).”
BackgroundResultInfluentialHow Well Do You Know Your Audience? Reader-aware Question Generation.Preprint
Stewart, I., & Mihalcea, R. F. (2021) · arXiv (Cornell University)
Contrastive Domain Adaptation for Question Answering using Limited Text CorporaPreprint
Yue, Z., Kratzwald, B., & Feuerriegel, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.13854 · Cited by 9
“Du et al. (2017) propose an endto-end seq2seq encoder-decoder for the generation.”
BackgroundImproving Long Content Question Generation with Multi-level Passage Encoding
Zhu, P. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89363-7_11
Formulating critical questions to the user in the course of decision-making
Galitsky, B. A. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-824521-7.00007-7
Answer-Centric Local and Global Information Fusion for Conversational Question Generation
Lei, P., & Sun, X. N. (2021) · IEEE International Conference on Big Knowledge (ICBK) · doi:10.1109/ickg52313.2021.00067
Data Science Mentoring Support using Neural Networks
Trinidad, M. J. C., Coelho, F. B., Canchumuni, S. W. A., & Pacheco, M. A. C. (2021) · International Conference on Computational Science and Its Applications · doi:10.1109/iccsa54496.2021.00045
Learn to Ask What You Don’t Know
Dahal, B., Choi, S., & Taghva, K. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-1607-6_32
Exploring neural question generation for formal pragmatics: Data set and model evaluation
Kuthy, K. D., Kannan, M., Ponnusamy, H. S., & Meurers, D. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.966013
Dual Machine Reading Comprehension for Event Extraction
Feng, Z., Wang, X., & Fu, D. (2022) · International Conference on Information Science and Technology · doi:10.1109/icist55546.2022.9926951 · Cited by 1
“Due to the limitation of computing power, the batch size set as 16 (from [8, 16, 32]), and the learning rate is 3e-5 (from [1e-5, 3e-5, 4e-5, 5e-5, 3e-6, 4e-6, 5e-6]).”
BackgroundParagraph-level Tibetan Question Generation for Machine Reading Comprehension
Liu, S., Chen, C., & Sun, Y. (2022) · International Conference on Asian Language Processing · doi:10.1109/ialp57159.2022.9961244
“Most of their works are based on the sequence to sequence (Seq2Seq) framework with attention mechanisms [3]–[6] and achieves some successes [7]–[9].”
BackgroundMethodBinary-perspective Asymmetrical Twin Gain: a Novel Evaluation Method for Question Generation
Su, Y., Hong, Y., Zhu, H., Xu, M., Fan, Y., & Zhang, M. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892106
“Since Du et al. [9] did not use the answer information, this kind of research is also be called Answer-Agnostic Question Generation.”
BackgroundMethodYang, H., Lan, K., You, J., & Shen, L. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9891960
A primary study on diversity of question generation
Xu, L., Chen, X., Wang, B., & Jin, P. (2022) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis58238.2022.00042
“The SQuAD data set used in our paper is divided according to the paper [16], there are about 70k training samples, 10k test and valid samples, each passage contains many question-answer pairs, different questions may have the same answer, and each question has 10 tokens on average.”
MethodEntity Level QA Pairs Dataset for Sentiment Analysis
Lahiri, A. K., & Hu, Q. (2022) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat55865.2022.00046
Multi-hop Question Generation without Supporting Fact Information
Emerson, J., & Chali, Y. (2023) · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference · doi:10.32473/flairs.36.133320
“Although question generation has been extensively researched in recent years, most of the previous work has focused on generating questions from input contexts of limited sizes, usually consisting of a single sentence or small paragraph (Du, Shao, and Cardie 2017), (Zhao et al. 2018).”
BackgroundExploring Social Sciences Archives with Explainable Document Linkage through Question Generation
Antoine, E., Kang, H. J., Rousseau, I., Azémard, G., Béchet, F., & Damnati, G. (2023) · Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (LaTeCH-CLfL) · doi:10.18653/v1/2023.latechclfl-1.16
“The Question-Generation (QG) task is a classical NLP task that has been revisited thanks to the development of efficient deep learning sequence-to-sequence models (Du et al., 2017; Shakeri et al., 2020; Murakhovs’ka et al., 2022) and Large Language Models (Agrawal et al., 2022).”
MethodA Research on Attraction Details Question-answer Pair Generation based on Gate Attention Unit
Huang, W., Jin, F., & Chang, Q. (2023) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/icecai58670.2023.10176653
“The existing pipeline approach works by [6, 7, 8, 9, 10, 11] (1) first generating or extracting the selected answer range based on the textual information, (2”
MethodEBAMQ: Exposure Bias Alleviation via Moment Matching for Question Generation
Liu, D., Hong, Y., Ding, C., Yao, J., & Zhou, G. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191278
Generating News-Centric Crossword Puzzles As A Constraint Satisfaction and Optimization Problem
Majima, K., & Ishihara, S. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3615151
“A rapidly evolving text generation approach, using pre-trained language models, is expected to improve clue quality [13].”
MethodLow-Resource Language Question Generation Based on Key Sentence and Knowledge GraphPreprint
Sun, Y., Zhuang, Y., Liu, S., & Zhao, X. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4560896 · Cited by 1
วิวัฒน์บุตรสิริ, ณ. (2021) · doi:10.58837/chula.the.2021.850
Keyword Provision Question Generation for Facilitating Educational Reading Comprehension Preparation
Chan, Y.-H., Chung, H.-L., & Fan, Y.-C. (2022) · International Conference on Natural Language Generation · doi:10.18653/v1/2022.inlg-main.15
“Question generation (QG), taking a passage and an answer phrase as input and generating a context-related question as output, has received interest in recent years (Zhou et al., 2017; Zhao et al., 2018; Du et al., 2017; Chan and Fan, 2019; Dong et al., 2019; Bao et al., 2020).”
BackgroundSCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples
Fu, D., Godbole, A., & Jia, R. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.485 · Cited by 3
Geometry Arithmetic Problem Recommendation Based on Scene-Enhanced BERT
Min, Y., Peng, R., Huang, L., Lyu, X., & Yu, X. (2023) · International Conference on Intelligent Education and Intelligent Research (IEIR) · doi:10.1109/ieir59294.2023.10391228
“This approach allows the recommendation system to better understand user intent and offer more flexible generation of personalized recommendations [14].”
BackgroundDiversity question generation based on contrastive search algorithmPreprint
Zhou, M., Zhou, J., Gan, J., Wang, J., & Wang, M. (2024) · Research Square · doi:10.21203/rs.3.rs-3887342/v1
Text-based Q&A: Automated Question Generation and Answering for Enhanced Data Processing
(2023) · Computer Applications & Technological Solutions (CATS) · doi:10.1109/cats58046.2023.10424347
KICHIK BIZNES SUBYEKTLARINING ISHLAB CHIQARISHINI SAMARALI AMALGA OSHIRISH KO'RSATKICHLARI
Yaqubova, Y. (2024) · Ижтимоий-гуманитар фанларнинг долзарб муаммолари / Актуальные проблемы социально-гуманитарных наук / Actual Problems of Humanities and Social Sciences · doi:10.47390/spr1342v4i1y2024n19
Chinese Question Generation for Children Stories Based on Deep Learning
Tong, Z. (2023) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1145/3652628.3652714
“Du et al [5] firstly used the Seq2Seq neural network model for the question generation task, and by using a global attention mechanism during the decoding process, they were able to capture closely related contextual semantic information, which led to automatic evaluation results that were…”
BackgroundMethodLiquin, E. G., Rhodes, M., & Gureckis, T. M. (2024) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/4gtrz
Deep question generation model based on dual attention guidance
Li, J., Zhang, X., Wang, J., & Zhou, X. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02249-6
Learning to generate text with auxiliary tasks
Hùng, P. Q., Nguyen, M.-T., Inoue, S., Tran-Tien, M., & Phan, X.-H. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112570
An Analysis of Automatic Question Generation Research Progress and Challenges
Dey, D., & Rudrapal, D. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-97-8336-6_19
Automatic Question Generation from Postpositional Phrases of Marathi
Patil, P. M., Bhavsar, R. P., & Pawar, B. V. (2025) · SN Computer Science · doi:10.1007/s42979-025-03682-2
“A neural network-based sequence-to-sequence learning approach has been proposed for AQG [5].”
ViQAG: A System for Vietnamese Questions and Answers Generation
Le, H.-L., Hùng, P. Q., Ha, N. T., Vu, H.-T., Nguyen, M.-T., & Phan, X.-H. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-80943-9_82
Dual Decoder for Fast Inference in Natural Language Generation
Wang, W., Wang, H., Wang, Z., Li, S., & Yu, W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889713
“Following [26], we split the original 98K training set into training and test sets, and keep the original development set.”
KPQDG: a key sentence prompt-tuning for automatic question-distractor pairs generation
Yin, Z., & Li, L. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11149-x · Cited by 2
Liquin, E. G., Rhodes, M., & Gureckis, T. M. (2025) · Open Mind · doi:10.1162/opmi.a.12 · Cited by 1
“There has also been increasing interest in developing artificial intelligence systems with human-like question asking abilities (e.g., Du et al., 2017; Grand et al., 2024; Jain et al., 2017; Rao & Daumé, 2018; Wang & Lake, 2021).”
Transformers in Bangla Text: Advancing MCQ and Answer Generation Methods
Mamun, M., Sunny, S. N., & Rahman, M. S. (2024) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit64611.2024.11021706
“In the field of machine learning, Du et al. [10] introduced an encoder-decoder model [11] that leveraged the attention mechanism for question generation.”
Improve Question Generation via Dual Perspective Key Phrase Selection
Wu, Y., Du, X., & Wang, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0020-8_24
Self-citationSaravanan, K. S., & Velammal, B. L. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-78925-0_12
Bernard, J., & Sabine Graf, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98281-1_11 · Cited by 1
Generative Adversarial Quest: Enhancing Question and Answer Generation Through GAN
Yellu, S., Satyamurty, C. V. S., Appe, S. N., & Afroz, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-1264-2_21
Enhancing Vietnamese Automatic Question Generation with Synthetic Data and Preference Optimization
Nguyen, D. H., Tran, C., & Tran, H. T. (2025) · doi:10.1109/icnlp65360.2025.11108542 · Cited by 1
“An Automatic Question Generation (AQG) system has long been an intriguing problem, involving the system that generate relevant questions based on provided contexts and answers [1], [29].”
Integrated Framework for Bloom’s based Question and Short Answer Generation using Transformer
Jadhav, P., Harnekar, M., Jalgaonkar, A., More, S., Khandekar, S., & Bhingarde, K. (2025) · International Conference on Soft Computing for Security Applications (ICSCSA) · doi:10.1109/icscsa66339.2025.11170844
Leveraging Generative AI for Enhanced Question Generation in Reading Comprehension
Vedantham, U., Chouti, N., Kumar, V., Mahatme, G., Kundu, D., & Ghosh, K. (2025) · International Conference on Computing, Intelligence, and Application (CIACON) · doi:10.1109/ciacon65473.2025.11189701
“A significant milestone in question generation (QG) research was achieved by Du et al. , who proposed a neural network-based approach to generate questions from reading comprehension passages automatically [1].”
AI-enhanced learning: Converting educational data into tailored question papers and responses
Lingamallu, R. K., Nalla, A. R., Regati, S., Nalam, R., Vargese, M. G., Mouli, K. C., Vamshi, B. N., & Mohmedmhdi, H. (2025) · AIP conference proceedings · doi:10.1063/5.0298249
Knowledge-Enhanced Question Generation Guided by Interrogative Words
Li, J., Zhang, X., Wang, J., & Zhou, X. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227373
“With natural language processing (NLP) advancements, Du et al. [16] pioneered an automatic question generation approach using a neural sequence-to-sequence (Seq2Seq) model, which utilizes an encoder to transform input sentences into hidden representations that are then converted into questions by a…”
Syntax-aware question generation through dependency relations-guided attention
Li, J., Zhang, X., Wang, J., & Zhou, X. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113575
Questionnaire Generator Using Tinyllama Sentence Transformer and LangChain
K, B. A. N., Devesh, M., Punith Kumar, B., Khandal, H., & Poongodi, T. (2025) · International Conference on Electrical, Electronics, and Computer Science with Advance Power Technologies - A Future Trends (ICE2CPT) · doi:10.1109/ice2cpt66440.2025.11340279
“Similarly, Du et al. [2] demonstrated how sequence-to-sequence models with attention can generate questions directly from text, without requiring handcrafted templates.”
ReviseSmart: An AI-Powered Personalized Revision Platform
Shah, K., Singh, V., Sonekar, S., & Ambawade, D. D. (2025) · IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies (INSPECT) · doi:10.1109/inspect67393.2025.11350596
Liu, H. T., Zhang, Y., Meng, Q., & Zhang, X. (2025) · International Conference on Big Data Analytics and Artificial Intelligence Application · doi:10.1145/3788108.3788109
“Training with datasets from various domains and subsequently testing with corresponding domain-specific test sets enables us to evaluate the effectiveness of our training methodologies[22][23].”
Bridging Dependency Enhanced Counterfactual Supporting for Multi-hop Question Generation
Hu, K., Li, L., Zhang, H., Zhang, J., & Tao, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7138-3_12
Enabling Dynamic Interactions between Natural Language and Structured Knowledg Bases
Elsahar, H. (2019) · theses.fr (ABES) · doi:10.70675/4944f792z8529z4f8azb2cdzac4385d2705d
Deep Multimodal Learning for Joint Textual and Visual Reasoning
Bordes, P. (2020) · theses.fr (ABES) · doi:10.70675/8bd1beefz5760z4f96z8d8cz87e025608c32
Text Generation with and without Retrieval
Fan, H. (2021) · theses.fr (ABES) · doi:10.70675/87ca97d1z017cz478azac26z38a64f0a75e0
Vers la mitigation des biais en traitement neuronal des langues
Berre, G. L. (2023) · theses.fr (ABES) · doi:10.70675/f37c3802z821az4a6dzb877zf631994cacd5
Singh, V., Pradhan, T. K., Shreya, S. S., Upadhayay, K., & Kumar, S. S. (2026) · IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi68868.2026.11466032
“Automated Question Generation (AQG) converts educational content into questions to support active recall [8], [9].”
Generating and answering questions across text and knowledge graphs
Han, K. (2024) · theses.fr (ABES) · doi:10.70675/605774e1z4ab3z4bc8z9628ze56d226162f9
Data-Based Natural Language Generation : Evaluation and Explainability
Faille, J. (2023) · theses.fr (ABES) · doi:10.70675/3e73dd43z7aa6z4405za5cez27c78b408a3c
Knowledge Graph Augmented Generation for Examination Questions
Li, Q., Zhao, Z., Liu, Y., Liu, N., & Cui, L. (2026) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2026.3682325
Amirkumar, M., Meraliyev, M., Orynbekova, K., Talasbek, A., & Bogdanchikov, A. (2026) · International Conference on Electronics, Computer and Computation · doi:10.1109/icecco67619.2026.11488827
“A paradigm change was brought about by the development of sequence-to-sequence models [6], which made it possible to generate end-to-end neural questions from text passages.”
Tugambayeva, A., & Сахипов, А. (2026) · Scientific Journal of Astana IT University · doi:10.37943/25vynz9998
Tan, J., Zhao, R., Tang, J., & He, L. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-19096-3_22
Li, M., Zhu, J., Zhang, W., Pan, C., Li, Z., & Guan, J. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11521992
“These models demonstrated an improved ability to generate complex and contextually appropriate questions [8].”
Reinforcement Learning-Supervised LLM Question Generation from Educational Textbooks
Damastuti, F. A., Gumelar, A. B., & Firmansyah, K. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.17900
“Authors in [3] studied 93 different AQG systems and reported that most of them only work with English text.”
Supporting Data-Driven Mastery Learning at Scale
Wei, Y. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-29794-5_58
Automatic Generation of Factual and Inferential Questions from Uzbek Popular Science Texts
Qizi, N. I. S., & Manopovna, U. K. (2026) · Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) · doi:10.1109/usbereit70063.2026.11580644
Awalurahman, H. W., & Budi, I. D. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3987
Han, B. G. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.116067
Design and Implementation of Online Learning and Evaluation System for Competitive Examinations
Balamurugan, R., Gowtham, S., Abishek, V., & Abishek Kumar, B. (2026) · International conference Computer Networks and Inventive Communication Technologies · doi:10.1109/iccnct68477.2026.11590170
“Heilman and Smith [9] have proposed the use of statistical ranking for question generation, and Du et al. [10] have proposed the use of neural sequence-to-sequence models for question generation from reading comprehension tasks.”
Sihotang, T. Y. R., & Kusuma, G. P. (2026) · International Conference on Applying New Technology in Green Buildings (ATiGB) · doi:10.1109/atigb70203.2026.11628300
“Automatic Question Generation Systems (AQGS) were introduced to generate questions automatically from given texts or learning materials [1], [4], [5].”
Marathe, V., Thomas, R. K., Sharma, P., Katenahalli, S. K., & Manju (2026) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet65726.2026.11632627
“Existing automated question generation (AQG) research has explored template-based methods, syntax-driven transformations, and neural sequence-to-sequence models [13], [14].”
A Review of Deep Learning-Based Question Generation: Challenges, Methods, and Future Directions
Yehia, M. F., Helmi, Y. M., & Bahloul, M. M. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01497-4
AEQAG: An Association-Enhanced Question Answering Generation Framework and its Application
Li, H., Yin, R., He, R., Yang, J., Wang, S., & Gao, J. (2026) · International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) · doi:10.1109/aiea70743.2026.11632308
“Its advantages are that the consistency of the questions and answers is high, the generated results are relatively stable, and it is easy to carry out automatic evaluation and verification [1], [6].”
Sharma, D., Singh, R., Sharma, S., Suman, S., & Chaudhary, G. (2026) · VEETHIKA-An International Interdisciplinary Research Journal · doi:10.48001/veethika.spl.mar26.10
“In parallel, Heilman and Smith (2010) explored rule-based question generation, while Du, Shao, and Cardie (2017) demonstrated neural question generation using BERT-based models.”
Hassan, A. N. A. A., Zhao, Z., Farea, I. K. Q., & Hassan, Q. N. A. (2026) · International Conference on Emerging Smart Technologies and Applications (eSmarTA) · doi:10.1109/esmarta70636.2026.11652148
“Neural sequence-to-sequence models subsequently improved fluency and coverage; Du et al. [12] demonstrated that LSTM-based encoder–decoders could generate questions directly from reading-comprehension passages, and transformer variants further raised quality by leveraging large-scale pre-training.”
Li, X., Xie, Z., Long, Y., Gao, J., Xie, X., Pan, J., & Liang, D. (2026) · International Conference on Educational Digitalization and Computer Science in the Guangdong-Hong Kong-Macao Greater Bay Area · doi:10.1145/3828183.3828357
“Sequence-to-sequence models substantially improved fluency and diversity, while answer-aware designs further strengthened the alignment between the generated question and the target answer span [4, 6].”
., J. S. (2026) · International Journal of Scientia · doi:10.66194/gvncijsv1i1-006
Temperoni, A., & Turano, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-40774-0_48
Senthilkumar, P., & Nandhini, K. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.21127
“While the comparison with the models in [20] and [21] is only approximate because of differences in the evaluation data, all of the models have been trained mainly on SQuAD, thus serving as appropriate baselines.”
Xu, J., Cheng, M. T., Li, C., Su, Z., Zhao, J., & Ma, W. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7644108
Quizzi: Automatic Quiz Generation via Iterative BERT Fine-Tuning
Diculescu, D.-R., Popescu, P. Ș., & Mihăescu, M. C. (2026) · IEEE International Conference on Intelligent Systems · doi:10.1109/is71416.2026.11727212
“Neural sequence-to-sequence models marked a turning point: Du et al. [4] were among the first to cast question generation as an end-to-end learning problem and outperformed rule-based baselines on reading-comprehension data.”
Unlocking deeper understanding: A type-specific contextualized question generation approach
Dey, D., Rudrapal, D., Jamatia, A., & Chakma, K. (2026) · Sadhana · doi:10.1007/s12046-026-03398-w
“The approach presented in [14] employed bidirectional LSTMs coupled with an attention mechanism, where the input sentences were encoded to capture complex syntactic structures and enhance contextual comprehension.”
Evaluation of Text Generation: A Survey
Celikyilmaz, A., Clark, E., & Gao, J. (2020) · arXiv · doi:10.48550/arxiv.2006.14799 · Cited by 207
“…the issues found in BLEU and has been widely used for evaluating machine translation models and other models, such as image captioning (Kilickaya et al., 2017), question generation (Nema & Khapra, 2018; Du et al., 2017), and summarization (See et al., 2017; Chen & Bansal, 2018; Yan et al., 2020).”
BackgroundMethodInfluentialThe GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
Gehrmann, S., Adewumi, T., Aggarwal, K., Ammanamanchi, P. S., Anuoluwapo, A., Bosselut, A., Chandu, K. R., Clinciu, M., Das, D., Dhole, K. D., et al. (2021) · arXiv · doi:10.48550/arxiv.2102.01672 · Cited by 49
“Visual Question Generation (Shukla et al., 2019; Li et al., 2018) 28.”
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
