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 201–300 of 695
Large-Scale Simple Question Generation by Template-Based Seq2seq Learning
Liu, T., Wei, B., Chang, B., & Sui, Z. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-73618-1_7 · Cited by 21
“Automatic question generation (QG) ([15], [4], [6]) has become a popular task for solving the data insufficient problems in QA systems.”
BackgroundRetrieval-Augmented Generation for Multiple-Choice Questions and Answers Generation
Pradeesh, N., Remya, T., Thushara, M. G., Krishna, K. A., & Pranav, V. S. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.352 · Cited by 23
Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends
Lan, Y., Li, X., Du, H., Lu, X., Gao, M. Z., Qian, W., & Zhou, A. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3621181 · Cited by 43
Rule-Based Automatic Question Generation Using Semantic Role Labeling
Keklik, O., Tuğlular, T., & Tekır, S. (2019) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2018edp7199 · Cited by 18
CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering
Yue, X., Zhang, X. F., Yao, Z., Lin, S. M., & Sun, H. (2021) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm52615.2021.9669300 · Cited by 22
Few-Shot Question Generation for Personalized Feedback in Intelligent Tutoring Systems
Kulshreshtha, D., Shayan, M., Belfer, R., Reddy, S., Serban, I. V., & Kochmar, E. (2022) · Frontiers in Artificial Intelligence and Applications · doi:10.3233/faia220062 · Cited by 18
Gašpar, A., Grubišić, A., & Šarić‐Grgić, I. (2023) · Language Resources and Evaluation · doi:10.1007/s10579-023-09672-1 · Cited by 18
“As for the preliminary comparison to other approaches ( ES5 ), the quality of our machine-generated questions was compared with those obtained by Du et al. (2017), Khullar et al. (2018), who compared their results with Heilman and Smith (2010), and Heilman (2011).”
BackgroundMethodResultInfluentialEdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation
Ge, T., Chen, S., & Wei, F. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.741 · Cited by 21
Towards a Benchmark for Scientific Understanding in Humans and Machines
Barman, K. G., Caron, S., Claassen, T., & de Regt, H. W. (2024) · Minds and Machines · doi:10.1007/s11023-024-09657-1 · Cited by 28
“In some cases, it could be possible to train language models to produce questions as well (Perez et al., 2022 ; Du et al., 2017 ; Rao & Daumé III, 2018 ).”
BackgroundA Question Answering System on Regulatory Documents
Collarana, D., Heuss, T., Lehmann, J., Lytra, I., Gaurav, M., Nedelchev, R., Thorsten, S., & Priyansh, T. (2018) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-61499-935-5-41 · Cited by 18
“We made use of a neural network question generation model proposed by [3].”
MethodChen, G., Yang, J., & Gašević, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-23204-7_6 · Cited by 19
“There have been several studies working on constructing effective question generators [10, 11, 33, 35], most of which assume that the answer to a question (usually a span of text in the input sentence) is determined prior to the generation of the question and use both the sentence and the answer as input for the quest…”
BackgroundMethodInfluentialAsk to Learn: A Study on Curiosity-driven Question Generation
Scialom, T., & Staiano, J. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.202 · Cited by 24
Self-supervised clarification question generation for ambiguous multi-turn conversation
Shao, T., Cai, F., Chen, W., & Chen, H. (2021) · Information Sciences · doi:10.1016/j.ins.2021.12.040 · Cited by 18
Question Generation by TransformersPreprint
Kriangchaivech, K., & Wangperawong, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05017 · Cited by 27
“On the other hand, machine learned models developed recently have used recurrent neural networks (RNNs) to perform sequence transduction, i.e. sequence-to-sequence (Du, Shao, and Cardie 2017; Kim et al. 2019).”
MethodModels in the Loop: Aiding Crowdworkers with Generative Annotation Assistants
Bartolo, M., Thrush, T., Riedel, S., Stenetorp, P., Jia, R., & Kiela, D. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.275 · Cited by 28
Remember the Facts? Investigating Answer-Aware Neural Question Generation for Text Comprehension
Steuer, T., Filighera, A., & Rensing, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-52237-7_41 · Cited by 17
“Looking outside the educational domain, NQGs evolved from relatively simple sequence to sequence models, relying only on the context sentence and the statistical regularities of language to generate questions [9], to sophisticated model with different facets.”
BackgroundMethodDiversify Question Generation with Continuous Content Selectors and Question Type Modeling
Wang, Z., Rao, S., Zhang, J., Qin, Z., Tian, G., & Wang, Y.-X. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.194 · Cited by 16
“In recent years, neural techniques are applied to this task and have achieved significant progress (Zhou et al., 2017; Du et al., 2017).”
BackgroundPathQG: Neural Question Generation from Facts
Wang, S., Wei, Z., Fan, Z., Huang, Z., Sun, W., Zhang, Q., & Huang, X. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.729 · Cited by 17
“Current QG systems mainly follow the sequence-to-sequence structure with an encoder for modeling the textual input and a decoder for text generation (Du et al., 2017).”
BackgroundMethodInfluentialGenerating Diverse Numbers of Diverse Keyphrases.Preprint
Yuan, X., Wang, T., Meng, R., Thaker, K. M., He, D., & Trischler, A. (2018) · arXiv (Cornell University) · Cited by 16
Cai, P.-X., Fan, Y.-C., & Leu, F. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-90072-4_23 · Cited by 16
DATLMedQA: A Data Augmentation and Transfer Learning Based Solution for Medical Question Answering
Zhou, S., & Zhang, Y. (2021) · Applied Sciences · doi:10.3390/app112311251 · Cited by 16
“However, question generation (QG) [13–16] has a large number of potential applications, such as improving the training of QA systems [17,18] and helping create new resources in the field of medical question answering.”
BackgroundAutomated question generation and question answering from Turkish texts
Akyön, F. Ç., ÇAVUŞOĞLU, A. D. E., Cengiz, C., Altinuc, S. O., & Temizel, A. (2022) · TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES · doi:10.55730/1300-0632.3914 · Cited by 29
“An encoder-decoder architecture of an LSTM based seq2seq model is adopted in [5].”
MethodLet Me Know What to Ask: Interrogative-Word-Aware Question Generation
Kang, J., Roman, H. P. S., & Myaeng, S.-H. (2019) · Workshop on Machine Reading for Question Answering (MRQA) · doi:10.18653/v1/d19-5822 · Cited by 16
“Du et al. (2017) is the first one to propose an sequence-to-sequence model to tackle the QG problem and outperformed the previous state-of-the-art model using human and automatic evaluations.”
MethodChan, Y.-H., & Fan, Y.-C. (2019) · International Conference on Natural Language Generation · doi:10.18653/v1/w19-8624 · Cited by 18
“The compared models in the experiment are: • NQG-RC (Du et al., 2017): A seq2seq question generation model based on bidirectional LSTM. • PLQG (Zhao et al., 2018): A seq2seq network which contains a gated self-attention encoder and a maxout pointer decoder to enable the capability of handling long…”
BackgroundMethodInfluentialShakeri, S., Constant, N., Kale, M., & Xue, L. (2021) · International Conference on Natural Language Generation · doi:10.18653/v1/2021.inlg-1.4 · Cited by 22
“Recently, there have been numerous efforts around question generation (Du et al., 2017; Song et al., 2018; Klein and Nabi, 2019; Wang et al., 2020; Ma et al., 2020; Chen et al., 2020; Tuan et al., 2019).”
BackgroundQuiz Design Task: Helping Teachers Create Quizzes with Automated Question Generation
Laban, P., Wu, C.-S., Murakhovs’ka, L., Liu, W., & Xiong, C. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.9 · Cited by 20
Multi-Hop Question Generation with Knowledge Graph-Enhanced Language Model
Li, Z., Cao, Z., Li, P., Zhong, Y., & Li, S. (2023) · Applied Sciences · doi:10.3390/app13095765 · Cited by 16
“This stage was primarily focused on single-hop QG, with works such as [3] designing the first neural encoder– decoder model for QG without considering answer information.”
MethodZheng, H.-T., Han, J., Chen, J., & Sangaiah, A. K. (2018) · Computer Science and Information Systems · doi:10.2298/csis171121018z · Cited by 15
“al [5] built a bigger dataset for text&question based on SQuAD 3, and trained a sequence to sequence network to generate questions on level on word and paragraph.”
BackgroundMethodInfluentialRNN based question answer generation and ranking for financial documents using financial NER
Jayakumar, H., Krishnakumar, M. S., Peddagopu, V. V. V., & Sridhar, R. (2020) · Sadhana · doi:10.1007/s12046-020-01501-3 · Cited by 15
“Du et al [17] highlight the method to generate questions using Recurrent Neural Networks (RNN).”
MethodQuestion Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices
Pandya, H. A., & Bhatt, B. (2021) · Journal of Xidian University · doi:10.37896/jxu15.4/014 · Cited by 42
“posed challenges for sequence to sequence neural models in question generation – worse performances were reported if using the whole paragraph (with multiple sentences) as the input [26].”
Learning visual language models for video understanding
Yang, A. (2023) · theses.fr (ABES) · doi:10.70675/802872a7z8092z4556za1fdz2c7af45f0e72 · Cited by 26
Question Generation With Doubly Adversarial Nets
Bao, J., Gong, Y., Duan, N., Zhou, M., & Zhao, T. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2018.2859777 · Cited by 14
“According to [2], we implement a learning-to-ask (L2Ask) baseline in a neural encoder-decoder framework with attention and copying mechanisms.”
BackgroundMethodInfluentialLeveraging Context for Neural Question Generation in Open-domain Dialogue Systems
Ling, Y., Cai, F., Chen, H., & de Rijke, M. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3379996 · Cited by 14
“Following [4, 5, 17, 20, 26], we adopt five metrics to evaluate the performance of CNQG and the baselines, i.”
BackgroundMethodInfluentialMulti-hop Reasoning Question Generation and Its Application
Yu, J., Su, Q., Quan, X., & Yin, J. P. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3073227 · Cited by 14
Suissa, O., Zhitomirsky‐Geffet, M., & Elmalech, A. (2022) · Semantic Web · doi:10.3233/sw-222925 · Cited by 14
“, Where, Who, What, When, Why) rule-based approach [80], knowledge graph-based question generation [16, 50], and DNN-based models for generating additional types of questions [25, 49, 117, 135].”
BackgroundMethodVLSP 2021-ViMRC Challenge: Vietnamese Machine Reading Comprehension
Nguyen, K. V., Tran, S. Q., Nguyen, L. T., Huynh, T. V., Luu, S. T., & Nguyen, N. L.-T. (2022) · VNU Journal of Science Computer Science and Communication Engineering · doi:10.25073/2588-1086/vnucsce.340 · Cited by 14
“), question generation (Du et al., 2017), and information retrieval (Karpukhin et al.”
BackgroundReview-based Question Generation with Adaptive Instance Transfer and Augmentation
Yu, Q., Bing, L., Zhang, Q., Lam, W. P., & Si, L. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.26 · Cited by 19
Better Distractions: Transformer-based Distractor Generation and Multiple Choice Question FilteringPreprint
Offerijns, J., Verberne, S., & Verhoef, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.09598 · Cited by 32
“In the last decade, these rule-based models were mostly replaced by neural networks, primarily sequence-to-sequence architectures (Du et al., 2017; Kim et al., 2019).”
MethodInvestigating Educational and Noneducational Answer Selection for Educational Question Generation
Steuer, T., Filighera, A., & Tregel, T. (2022) · IEEE Access · doi:10.1109/access.2022.3180838 · Cited by 13
“The SQuAD dataset is probably the most widespread dataset for AQG, and it has been shown that systems trained on the dataset generate fluent questions useful for augmenting question answering training data (e.g. [3], [8]).”
BackgroundMethodŠtěpánek, L., Dlouhá, J., & Martinková, P. (2023) · Mathematics · doi:10.3390/math11194104 · Cited by 18
Sohrab, M. G., Asada, M., Rikters, M., & Miwa, M. (2023) · IEEE Access · doi:10.1109/access.2023.3346952 · Cited by 17
“We follow the same train, validation test data split setting as Du et al. [25].”
MethodOpinerium: Subjective Question Generation Using Large Language Models
Babakhani, P., Lommatzsch, A., Brodt, T., Sacker, D., Sivrikaya, F., & Albayrak, Ş. (2024) · IEEE Access · doi:10.1109/access.2024.3398553 · Cited by 17
“Over the years, AQG techniques have evolved significantly, transitioning from classic rule-based [20] and template-based [21] methods to neural network methods [22] and trans-former architecture [23].”
BackgroundAutomated multiple-choice question generation in Spanish using neural language models
de-Fitero-Dominguez, D., García‐Cabot, A., & García‐López, E. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10076-7 · Cited by 15
“To boost performance, additional mechanisms are often used in the question generation task, like the inclusion of linguistic features [74] or the answer-aware mechanism, where a question is generated based on both the context and the answer [10, 12, 73].”
Zeng, H., Zhi, Z., Liu, J., & Wei, B. (2021) · Information Sciences · doi:10.1016/j.ins.2021.04.026 · Cited by 14
Phan, T. H. V., & Do, P. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06477-7 · Cited by 14
“The BLEU method has also been used in many Q&A studies with different n-grams BLEU-1, BLEU-2, BLEU-3, and BLUE-4 [6] [14] [17].”
MethodAutomatic question-answer pair generation using Deep Learning
Kumar, A., Kharadi, A., Singh, D., & Kumari, M. (2021) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca51532.2021.9544654 · Cited by 13
Shahidi, H., Li, M., & Lin, J. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.355 · Cited by 13
Synthetic QA Corpora Generation with Roundtrip ConsistencyPreprint
Alberti, C., Andor, D., Pitler, E., Devlin, J., & Collins, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05416 · Cited by 45
“Question generation is a well-studied task in its own right (Heilman and Smith, 2010; Du et al., 2017; Du and Cardie, 2018).”
BackgroundNatural Question Generation with Reinforcement Learning Based Graph-to-Sequence ModelPreprint
Chen, Y., Wu, L., & Zaki, M. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.08832 · Cited by 12
“Recent works on QG mostly formulate it as a sequence-to-sequence (Seq2Seq) learning problem [8, 41, 15].”
BackgroundOneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop ApproachPreprint
Cui, S., Bao, X., Zu, X., Guo, Y., Zhao, Z., Zhang, J., & Chen, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.12128 · Cited by 19
“• DeepNQG: the neural question generation model proposed in [8], an end-to-end model implemented with GRU module.”
BackgroundMethodQAScore—An Unsupervised Unreferenced Metric for the Question Generation Evaluation
Ji, T., Lyu, C., Jones, G., Zhou, L., & Graham, Y. (2022) · Entropy · doi:10.3390/e24111514 · Cited by 12
“QG is highly related to the task of machine reading comprehension (MRC), which is a sub-task of question answering (QA) (Du et al., 2017; Xie et al., 2020; Pan et al., 2020a; Puri et al., 2020; Lyu et al., 2021; Chen et al., 2019; Li et al., 2021).”
ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions
Pham, P. V. L., Vu-Duc, A., Hoang, N. M., Long, X., & Tuan, L. A. (2024) · ACM Symposium on Applied Computing · doi:10.1145/3605098.3636030 · Cited by 26
“Folloing previous works [7, 8, 23], we use BLEU-4 [26], ROUGE-L [19], METEOR [1] as our n-gram evaluation metrics, and use BERTScore [43] to measure the similarity between the generated candidate and ground-truth questions.”
MethodAutomated Generation and Evaluation of MultipleChoice Quizzes using Langchain and Gemini LLM
Pawar, P., Dube, R., Joshi, A., Gulhane, Z., & Patil, R. (2024) · International Conference on Electrical Electronics and Computing Technologies (ICEECT) · doi:10.1109/iceect61758.2024.10739326 · Cited by 13
“Other studies focused on neural question generation models with attention mechanisms [9] or leveraged large language models like GPT-4 [10] and BERT [11] for specialized domains like programming education.”
BackgroundA survey on aspect sentiment triplet extraction methods and challenges
Zou, W., Sun, X., Zhao, X., Feng, J. H., Long, Y., & Xing, Y. (2025) · Computer Science Review · doi:10.1016/j.cosrev.2025.100761 · Cited by 13
Neural Duplicate Question Detection without Labeled Training Data
Rücklé, A., Moosavi, N. S., & Gurevych, I. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1171 · Cited by 12
“Most of the previous work in QG is in the context of reading comprehension (e.g., Du et al., 2017; Subramanian et al., 2018; Zhao et al., 2018; Du and Cardie, 2018) or QG for question answering (Duan et al., 2017).”
Question Answering for Fact-Checking
Jobanputra, M. (2019) · Fact Extraction and VERification Workshop (FEVER) · doi:10.18653/v1/d19-6609 · Cited by 15
“Du et al. (2017) introduced a sequence-to-sequence model with an attention mechanism, out-performing rule-base question generation systems.”
Steuer, T., Bongard, L., Uhlig, J., & Zimmer, G. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86436-1_22 · Cited by 12
Wu, Q., Zhang, Q., & Huang, X. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3155284 · Cited by 14
Natural Question Generation using Transformers and Reinforcement Learning
Biswas, D., Nadipalli, S., Sneha, B., Gupta, D., & Amudha, J. (2022) · OITS International Conference on Information Technology (OCIT) · doi:10.1109/ocit56763.2022.00061 · Cited by 12
“Some previous works focused on incorporating a selfattention mechanism, without the use of RL [27].”
MethodVarifocal Question Generation for Fact-checking
Ousidhoum, N. D., Yuan, Z., & Vlachos, A. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.163 · Cited by 14
IDK-MRC: Unanswerable Questions for Indonesian Machine Reading Comprehension
Putri, R. A., & Oh, A. H. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.465 · Cited by 14
Neural Question Generation with Semantics of Question Type
Dong, X., Yu, H., Chen, X., Li, W., Zhang, M., & Zhu, Q. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-99501-4_18 · Cited by 13
Learning to Ask Screening Questions for Job Postings
Shi, B., Li, S., Yang, J., Kazdagli, M. E., & He, Q. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401118 · Cited by 16
Talk to Papers: Bringing Neural Question Answering to Academic Search
Zhao, T., & Lee, K. (2020) · Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL Demo) · doi:10.18653/v1/2020.acl-demos.5 · Cited by 13
Learning to Ask Like a Physician
Lehman, E., Lialin, V., Legaspi, K. E., Sy, A. J., Pile, P. T., Alberto, N. R., Ragasa, R. R., Puyat, C. V., Taliño, M. K., Alberto, I. R., et al. (2022) · Proceedings of the 4th Clinical Natural Language Processing Workshop · doi:10.18653/v1/2022.clinicalnlp-1.8 · Cited by 10
A Method for Generating Course Test Questions Based on Natural Language Processing and Deep Learning
Wang, H., Chiang, Y.-H., & Chen, I. (2023) · Education and Information Technologies · doi:10.1007/s10639-023-12159-9 · Cited by 11
“Du et al. (2017) proposed the first NQG model to generate questions from sentences using an attention-based Seq2Seq model with the RNN encoder-decoder architecture.”
InfluentialQuestion Generation Using Sequence-to-Sequence Model with Semantic Role Labels
Naeiji, A., An, A., Davoudi, H., Delpisheh, M., & Alzghool, M. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.207 · Cited by 13
“level SQuAD dataset (Du et al., 2017), where the answer in a QA pair is a single sentence.”
BackgroundMethodInfluentialTransformer based Answer-Aware Bengali Question Generation
Ruma, J. F., Mayeesha, T. T., & Rahman, R. M. (2023) · International Journal of Cognitive Computing in Engineering · doi:10.1016/j.ijcce.2023.09.003 · Cited by 13
Fine-Tuning a Large Language Model with Reinforcement Learning for Educational Question Generation
Lamsiyah, S., Mahdaouy, A. E., Nourbakhsh, A., & Schommer, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-64302-6_30 · Cited by 12
A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education
Li, Z., Cukurova, M., & Bulathwela, S. (2025) · International Conference on Learning Analytics and Knowledge (LAK) · doi:10.1145/3706468.3706487 · Cited by 12
“While existing research in relevant academic communities with a more technical focus explores generating questions from descriptive texts [22, 55], the task remains highly complex and there is less focus on the educational value of the generated questions in evaluations.”
Unsupervised Adaptation of Question Answering Systems via Generative Self-training
Rennie, S. J., Marcheret, E., Mallinar, N., Nahamoo, D., & Goel, V. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.87 · Cited by 12
“…question answering systems, with most of the work we are aware of either augmenting the training set, or generating synthetic QA pairs on auxiliary data (Sachan and Xing, 2018; Du et al., 2017; Duan et al., 2017; Song et al., 2017; Alberti et al., 2019; Dong et al., 2019; Zhang and Bansal, 2019).”
BackgroundImproving Asynchronous Interview Interaction with Follow-up Question Generation.
Rao, P. S. B., Agnihotri, M., & Jayagopi, D. B. (2021) · International Journal of Interactive Multimedia and Artificial Intelligence · doi:10.9781/ijimai.2021.02.010 · Cited by 13
Kulshreshtha, D., Belfer, R., Serban, I. V., & Reddy, S. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.566 · Cited by 14
“Question Generation methods have focused on training neural Seq2Seq models (Du et al., 2017; Mishra et al., 2020; Zhao et al., 2018; Chan and Fan, 2019; Klein and Nabi, 2019) on supervised QA datasets such as SQuAD (Rajpurkar et al.”
Closed-book Question Generation via Contrastive Learning
Dong, X., Lu, J., Wang, J., & Caverlee, J. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.230 · Cited by 11
CopyBERT: A Unified Approach to Question Generation with Self-Attention
Varanasi, S., Amin, S., & Neumann, G. (2020) · Workshop on NLP for Conversational AI (NLP4ConvAI) · doi:10.18653/v1/2020.nlp4convai-1.3 · Cited by 12
“23 UniLM (Dong et al., 2019) 22 Du et al. (2017).”
MethodKuthy, K. D., Kannan, M., Ponnusamy, H. S., & Meurers, D. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.509 · Cited by 12
“Another important challenge of QG is question word generation so that Sun et al. (2018) and Du et al. (2017) split the QG task into determining the question word or type and then generating the rest of the question.”
BackgroundAutomatic Opinion Question Generation
Chali, Y., & Baghaee, T. (2018) · International Conference on Natural Language Generation · doi:10.18653/v1/w18-6518 · Cited by 11
“One of the latest studies on the QG task has been conducted by Du et al. (2017).”
BackgroundMethodResultInfluentialLearning Semantic Sentence Embeddings using Pair-wise Discriminator.Preprint
Patro, B. N., Kurmi, V. K., Kumar, S., & Namboodiri, V. P. (2018) · arXiv (Cornell University) · Cited by 11
Neural relation extraction: a surveyPreprint
Aydar, M., Bozal, Ö., & Özbay, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.04247 · Cited by 17
“Neural question generation from text is an emerging research field [13, 31, 63, 70, 81].”
BackgroundChung, C.-Y., Hsiao, I., & Lin, Y. (2022) · Journal of Research on Technology in Education · doi:10.1080/15391523.2022.2123872 · Cited by 10
“For example, Du et al. (2017) demonstrated a seq2seq model based on the recurrent neural network (RNN) encoder-decoder architecture.”
MethodA Unified Framework for Contextual and Factoid Question Generation
Dong, C., Shen, Y., Lin, S., Lin, Z., & Deng, Y. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3280182 · Cited by 10
Diversity Enhanced Narrative Question Generation for Storybooks
Yoon, H., & Bak, J. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.31 · Cited by 15
Song, T., Tian, Q., Xiao, Y., & Liu, S. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-0730-0_28 · Cited by 10
Towards automatic question generation using pre-trained model in academic field for Bahasa Indonesia
Suhartono, D., Majiid, M. R. N., & Fredyan, R. (2024) · Education and Information Technologies · doi:10.1007/s10639-024-12717-9 · Cited by 28
“Using Bahdanau et al.’s model (Bahdanau et al., 2015) and Luong et al.’s improvements (Luong et al., 2015, Du et al., 2017) introduced a new architecture that uses beam search and a simplified copy mechanism to deal with words that are not in the vocabulary (Garneau et al., 2019).”
Tomikawa, Y., Suzuki, A., & Uto, M. (2024) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2024.3491801 · Cited by 18
Automatically Generating Interesting Facts from Wikipedia Tables
Korn, F. R., Wang, X., Wu, Y., & Yu, C. (2019) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3299869.3314043 · Cited by 10
“Reading comprehension question generation has the goal of generating questions to test the reader’s understanding of a given text passage such as a sentence [5].”
BackgroundImproving Neural Question Generation using Deep Linguistic Representation
Yuan, W., He, T., & Dai, X. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3449975 · Cited by 10
“Du et al. [9] and Zhou et al. [60] first propose a sequence-to-sequence model to address the QG problem, and achieve success compared to the previous state-of-the-art model using automatic metrics and human evaluation.”
MethodResultLearning to Generate Questions by Learning to Recover Answer-containing Sentences
Back, S., Kedia, A., Chinthakindi, S. C., Lee, H., & Choo, J. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.132 · Cited by 11
“We calculate BLEU-4, METEOR, and ROUGE-L with the script from Du et al. (2017).”
BackgroundMethodInfluentialUnified Question Generation with Continual Lifelong Learning
Yuan, W., Yin, H., He, T., Chen, T., Wang, Q., & Cui, L. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3511930 · Cited by 11
“[19] are the first to explore how to address the QG problem via building end-to-end neural models.”
BackgroundSteuer, T., Filighera, A., Tregel, T., & Miede, A. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.900304 · Cited by 10
“In recent years, these challenges have been addressed by applying statistical and neural network-based algorithms to select important passages and concepts (Du and Cardie, 2017; Chen et al., 2019) and generate questions concerning their selection (Du et al., 2017; Dong et al., 2019).”
BackgroundAutomatic Question Generation from Indonesian Texts Using Text-to-Text Transformers
Fuadi, M., & Wibawa, A. D. (2022) · International Conference on Electrical and Information Technology (IEIT) · doi:10.1109/ieit56384.2022.9967858 · Cited by 15
Mulla, N., & Gharpure, P. (2023) · International Journal of Information Technology · doi:10.1007/s41870-023-01262-2 · Cited by 10
“In [18], an attention mechanism and a dual encoder in an encoder-decoder setup is experimented with, where the first encoder encoded paragraph-level information and the second encoder encoded sentence-level information.”
MethodDevelopment of system for generating questions, answers, distractors using transformers
Barlybayev, A., & Matkarimov, B. T. (2024) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v14i2.pp1851-1863 · Cited by 17
“In study [16], the first neural question generation model was introduced, which has shown to be much more effective than traditional rule-based methods as it uses recurrent neural network (RNN) based Seq2Seq model with attention [17].”
MethodEncoder-Decoder Architectures for Generating Questions
Singh, J., & Sharma, Y. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.05.019 · Cited by 10
Video Question Generation via Semantic Rich Cross-Modal Self-Attention Networks Learning
Wang, Y.-S., Su, H.-T., Chang, C.-H., Liu, Z., & Hsu, W. H. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053476 · Cited by 10
“Comparing to the text question generation task [5] where the target questions are highly overlapped with the input passage or the image question generation task [6] where the questions are regardless of the temporal information, Video QG is arguably more challenging.”
BackgroundMulti-turn dialogue-oriented pretrained question generation model
Wang, Y., Rong, W., Zhang, J., Zhou, S., & Xiong, Z. (2020) · Complex & Intelligent Systems · doi:10.1007/s40747-020-00147-2 · Cited by 10
“Its purpose is to generate human-like questions from a given sentence or paragraph [7].”
BackgroundEngage the Public: Poll Question Generation for Social Media Posts
Lu, Z., Ding, K., Zhang, Y., Li, J., Peng, B., & Liu, L. (2021) · doi:10.18653/v1/2021.acl-long.3 · Cited by 10
“On the contrary, for the question length, the two S2S baselines both exhibit obvious performance drops when generating long questions, while TOPIC and C MT (NTM) perform steadily.”
BackgroundMethodInfluentialRestatement and Question Generation for Counsellor Chatbot
Lee, J. S. Y., Liang, B., & Fong, H. (2021) · Workshop on NLP for Positive Impact (NLP4PI) · doi:10.18653/v1/2021.nlp4posimpact-1.1 · Cited by 11
“For example, a sequence-to-sequence model with an attention mechanism has been proposed by Du et al. (2017).”
BackgroundA Tool for Automatic Question Generation for Teaching English to Beginner Students
Moron, M., Scocozza, J., Chiruzzo, L., & Rosá, A. (2021) · International Conference of the Chilean Computer Science Society (SCCC) · doi:10.1109/sccc54552.2021.9650423 · Cited by 10
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
