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 501–600 of 695
Ren, Z., Guo, J., Xu, Y., & Xiao, B. J. (2023) · IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) · doi:10.1109/ic-nidc59918.2023.10390776 · Cited by 2
“It improves Question Answering (QA) by providing enriched training data [1], as human annotation is expensive and time-consuming.”
BackgroundMethodSAC-Net: Stroke-Aware Copy Network for Chinese Neural Question Generation
Li, W., Kang, Q., Xu, B., & Zhang, L. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914614 · Cited by 2
“In English Question Generation area, the conventional methods perform grammatical and lexical analysis first, and then rely on heuristic rules to perform syntactic transformations of a sentence to factual questions [18; 7].”
BackgroundMethodInfluentialVocabulary Matters: A Simple yet Effective Approach to Paragraph-level Question Generation
Kumar, V., Joshi, M., Ramakrishnan, G., & Li, Y.-F. (2020) · Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (AACL-IJCNLP) · doi:10.18653/v1/2020.aacl-main.78 · Cited by 2
“Du et al. (2017) recently observed that 20% of the questions in the SQuAD dataset (Rajpurkar et al., 2016) require paragraph-level information to answer them.”
BackgroundExtraction of Question-related Sentences for Reading Comprehension Tests via Attention Mechanism
Shan, J., Nishihara, Y., Maeda, A., & Yamanishi, R. (2020) · Conference on Technologies and Applications of Artificial Intelligence (TAAI) · doi:10.1109/taai51410.2020.00013 · Cited by 2
“Most of the researchers did choose the SQuAD dataset as the training data for generating reading comprehension questions [5], [9], [10].”
BackgroundMethodComparison Question Generation Based on Potential Compared Attributes Extraction
Xie, J., Fang, W., Cai, Y., & Lin, Z. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-85899-5_18 · Cited by 2
Zhou, L., Small, K., Zhang, Y., & Atluri, S. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.416 · Cited by 2
“Both heristic-based (Heilman and Smith, 2010) and neural models (Du et al., 2017; Zhou et al., 2017; Sun et al., 2018) have been applied to QG.”
Easy-to-Hard: Leveraging Simple Questions for Complex Question GenerationPreprint
Zhao, J. W., Deng, X., & Sun, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02367 · Cited by 3
Semantic Graphs for Generating Deep QuestionsPreprint
Pan, L., Xie, Y., Feng, Y., Chua, T., & Kan, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.12704 · Cited by 2
“Many improvements have been proposed since the first Seq2Seq model of Du et al. (2017): applying various techniques to encode the answer information, thus allowing for better quality answer-focused questions (Zhou et al., 2017; Sun et al., 2018; Kim et al., 2019); improving the training via…”
BackgroundMethodEvaluating for Diversity in Question Generation over TextPreprint
Schlichtkrull, M., & Cheng, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.07291 · Cited by 2
“End-to-end neural models were introduced by Du et al. (2017), and extende in (Chan and Fan, 2019; Bao et al., 2020).”
MethodInfluentialQuestion Generation for Supporting Informational Query Intents.Preprint
Yin, X., May, J., Li, Z., & Small, K. (2020) · arXiv (Cornell University) · Cited by 2
Improved Synthetic Training for Reading ComprehensionPreprint
Chen, Y., Sultan, M. A., & Castelli, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12776 · Cited by 3
“…semantic templates (Heilman and Smith, 2010; Lind-berg et al., 2013; Mazidi and Nielsen, 2014), automatic question generation from text has gradually transitioned to neural sequence-to-sequence generation methods (Du et al., 2017; Duan et al., 2017; Harrison and Walker, 2018; Zhu et al., 2019).”
BackgroundControllable Open-ended Question Generation with A New Question Type OntologyPreprint
Cao, S., & Wang, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00152 · Cited by 2
“Compared to the widely studied task of generating factoid questions that inquire about “one bit” of information (Du et al., 2017; Duan et al., 2017; Li et al., 2019), this work is interested in generating open-ended questions that require deep comprehension and long-form answers (Labutov et al.,…”
A State of the Art Approaches to Question Generation Techniques
Khandait, K., & Bhura, S. A. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-19-6088-8_53 · Cited by 1
Multi-task Question Generation Based Data Augmentation for Biomedical Answer Generation
Zhao, J., Bai, J., Rong, W., Ouyang, Y., & Xiong, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-4749-2_41 · Cited by 1
Generation of Student Questions for Inquiry-based Learning
Ros, K., Jong, M., Chan, C. H., & Zhai, C. (2022) · International Conference on Natural Language Generation · doi:10.18653/v1/2022.inlg-main.14 · Cited by 1
“…review of different lines of work with detailed categorization of the task formulation and comparison of the major approaches including both rule-based approaches (Lindberg et al., 2013) and modern neural network-based approaches (Du et al., 2017; Duan et al., 2017; Lewis et al., 2019).”
BackgroundImproving Low-resource Question Answering by Augmenting Question Information
Chen, A., Sun, Y., Zhao, X., Esparza, R. P. G., Chen, K., Xiang, Y., Zhao, T., & Zhang, M. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.699 · Cited by 1
“…such as template-based question generation (Ali et al., 2010; Heilman and Smith, 2009; Chali and Hasan, 2015), and the broad application of Seq2Seq models in natural language processing (Bahdanau et al., 2014; Du et al., 2017), have made certain progress but also show similar limitations.”
BackgroundUnsupervised Candidate Answer Extraction through Differentiable Masker-Reconstructor Model
Wang, Z., Wang, Y., Zhu, Z., & Caverlee, J. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.379 · Cited by 1
De-Noising Tail Entity Selection in Automatic Question Generation with Fine-Tuned T5 Model
Sairaj, R. T., & Balasundaram, S. R. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-7817-5_32 · Cited by 1
Enhancing Question Generation in Bahasa Using Pretrained Language Models
Fredyan, R., Wiyono, I. S., Suhartono, D., Majiid, M. R. N., & Purnomo, F. (2024) · Revue d intelligence artificielle · doi:10.18280/ria.380421 · Cited by 1
“To address these constraints, researchers have created advanced techniques based on deep neural networks [19], such as recurrent neural networks (RNNs) [20], which include long short-term memory (LSTM) networks [21], gated recurrent units (GRUs) [22], and their variations.”
Intelligent Conversational Agent for Medical Information
Zeltsi, A., Tsourma, M., Alexiadis, A., Mavropoulos, A., Zamichos, A., Mastoras, V., Kontoulis, C.-G., Andreadis, S. T., Matonaki, A., Crisan, A., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70242-6_32 · Cited by 1
Chen, Z., Lin, R., Zhu, B., Chen, J., Zhong, S., & Liu, S. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0119-6_27 · Cited by 1
Answer-Aware Multi-Hop Question Generation Based on Variant Convolutional Networks
Dong, X., Cheng, S., Zhang, X., & Li, F. (2024) · International Conference on Machine Learning and Natural Language Processing (MLNLP) · doi:10.1109/mlnlp63328.2024.10800274 · Cited by 1
Designing for the Future of Information Access with Generative Information Retrieval
Murdock, V., Lee, C., & Hersh, W. (2024) · The information retrieval series · doi:10.1007/978-3-031-73147-1_9 · Cited by 2
A Benchmark Comparison of a Domain-Focused Pipeline with ChatGPT
Zhang, C., Zhao, T., Saraoğlu, H., & Louton, D. A. (2025) · Journal of Computer Information Systems · doi:10.1080/08874417.2024.2446629 · Cited by 1
Diversify Question Generation Based on Diffusion Model in Dialogue
Xu, F., Sumin, L. I. U., Yan, K., & Li, B. (2025) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2025eap1042 · Cited by 1
Automated Question Generation for Arabic Texts
Alhazaymeh, R. A., & Ali, M. Z. (2025) · International Conference on Information and Communication Systems (ICICS) · doi:10.1109/icics65354.2025.11072964 · Cited by 1
Automated question generation for Arabic language
Alhazaymeh, R. A., & Ali, M. Z. (2025) · Cluster Computing · doi:10.1007/s10586-025-05626-0 · Cited by 1
VocQuiz: Vocabulary Question Generation for English Language Education
Li, Y., Wu, J., Tu, S., Yu, J., Liu, H., Hou, L., & Li, J. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761546 · Cited by 1
Watch and Ask: Video Question Generation
Huang, S., Hu, S., & Yan, B. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-36718-3_18 · Cited by 1
A Neural Attention Model for Automatic Question Generation Using Dual Encoders
Kumar, A. P., Sridhar, G., Nayak, A., & Manjula Shenoy, K. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-3342-3_34 · Cited by 1
Learning to generate complex question with intent prediction from long passage
Pan, Y., Hu, B., Wang, S., Wang, X., Chen, Q., Xu, Z., & Zhang, M. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03651-9 · Cited by 1
“• LTA [3]: the first work using the Seq2Seq model for question generation task.”
MethodReview of Parameters, Approaches and Challenges in Reading Comprehension Systems
Gotmare, P. S., & Potey, M. M. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-5221-0_72 · Cited by 3
Graph and Question Interaction Aware Graph2Seq Model for Knowledge Base Question Generation
Li, C., Bai, J., Wang, C., Hu, Y., Rong, W., & Zhang, X. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892028 · Cited by 1
“Here we compare our proposed model on WebQuestions dataset against following baseline models: L2A: a LSTM-based Seq2Seq model with attention mechanism which takes linearized sub-graph as input [36].”
MethodQuestion Generator and Text Summarizer Using NLP
Chettukindi, S. (2023) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2023.50477 · Cited by 1
KTGAT: Improving the Robustness of Knowledge-enhanced Text Generation via Adversarial Training
Zhu, H., Song, Y., & Liu, B. (2023) · International Conference on Computer Engineering and Application (ICCEA) · doi:10.1109/iccea58433.2023.10135313 · Cited by 2
“Baselines (1)RNN[8], A sequence-to-sequence model containing an encoder and decoder, with temporal dependencies constructed by an LSTM; (2) DirectIn by simply taking the longest sentence in the sentence as the prediction of the model; (3) H&S[33] generates multiple questions based on the rules of (subject, relation, o…”
MethodInfluentialGenerative model for formulating relevant questions and answers using transfer learning
Godslove, J. F., & Nayak, A. K. (2023) · AIP conference proceedings · doi:10.1063/5.0136892 · Cited by 1
Robust Domain Adaptation for Machine Reading Comprehension
Jiang, L., Huang, Z. H., Liu, J., Wen, Z., & Peng, X. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i7.25974 · Cited by 2
Progress in Combining Image Captioning and Visual Question Answering Tasks
Kamath, P., Jamkhandi, P., Ghanti, P., Gupta, P., & Neelima, M. L. (2023) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet57972.2023.10170744 · Cited by 1
“[15] presents a neural network-based approach for generating questions about images, which can be used for visual question answering or image captioning tasks.”
BackgroundQuestion Generation via Generative Adversarial Networks
Liu, D., Hong, Y., Yao, J., & Zhou, G. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191871 · Cited by 2
“Specifically, Split11 [16] randomly divides the canonical training data of SQuAD into the QG-oriented training, validation and test sets, in the proportions of 80%, 10% and 10%.”
MethodMCQG: Multitask Approach for Chinese Question Generation and Question Answering
Deng, L., Li, J., Qi, P., Liu, Z., & Zhang, L. (2022) · International Conference on Signal Processing Systems (ICSPS) · doi:10.1109/icsps58776.2022.00133 · Cited by 1
“In Du’s work[3], the sentence and the paragraph which contains the sentence are encoded using separate bidirectional LSTMs, then they are concatenated to form a representation of encoder.”
MethodVeriActor: Dynamic Generation of Challenge-Response Questions for Enhanced Email Sender Verification
Abdeen, B., Al-Shaer, E. S., & Shadid, W. (2023) · IEEE Conference on Communications and Network Security · doi:10.1109/cns59707.2023.10289040 · Cited by 1
BRQG: A BART-Based Retouching Framework for Multi-hop Question Generation
Liao, T., Xu, B., Han, Y., Li, S., & Zhang, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46677-9_12 · Cited by 1
Generating Relevant Question Answer from Video
Bhanot, G., Pal, B., Sah, B., & Chhikara, G. (2023) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt56998.2023.10306677 · Cited by 1
“We further investigated the relationship between neural networks and the development of questions and answers, and found that the researches [6], [7] and [8] was founded on neural network algorithms for question generation.”
BackgroundDialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog
Zheng, X., Liu, T., Meng, H., Wang, X., Jiang, Y., Rao, M., Lin, B., Cao, Y., & Sui, Z. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.435 · Cited by 2
Fangfang, W., Zhang, J., & Yuan, H. (2023) · International Conference on Asian Language Processing · doi:10.1109/ialp61005.2023.10337119 · Cited by 1
“Consequently, we conducted experiments on this dataset and employed Du’s [4]”
BackgroundMethodLearning by Asking Questions for Knowledge-Based Novel Object Recognition
Uehara, K., & Harada, T. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-023-01976-7 · Cited by 1
“For instance, Du et al. (2017) explored automatic question generation from text passages, leveraging attention-based sequence learning models.”
Text-based Q&A: Automated Question Generation and Answering for Enhanced Data Processing
Rhythm, E. R., Hosain, A. H., Raya, N. Z., Pranta, K. A. R., Trina, T. T., Hossain, M. S., Mehedi, M. H. K., & Rasel, A. A. (2023) · Computer Applications & Technological Solutions (CATS) · doi:10.1109/cats58046.2023.10424125 · Cited by 1
“The paper [15] proposed a neural question generation approach that focuses on generating questions based on specific chapters of a given document.”
BackgroundАлександрович, С. О. (2024) · Computers · doi:10.3390/computers13060144 · Cited by 1
“A significant part of the methods of question generation is concentrated on processing natural-language texts and generating questions about the content of that text [8,14–17].”
BackgroundAttentional Seq2Seq Model for Arabic Opinion Question Generation
Ouahrani, L., & Bennouar, D. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-82112-7_9 · Cited by 1
Improving Question Generation with the Teacher’s Implicit Feedback
Rodrigues, H. P., Coheur, L., & Nyberg, E. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-93846-2_56 · Cited by 1
Otsuka, A., Nishida, K., Saito, I., Asano, H., Tomita, J., & Satoh, T. (2019) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.a-j14 · Cited by 1
Question Generation Based Product Information
Xiao, K., Zhou, X., Wang, Z., Duan, X., & Zhang, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32236-6_40 · Cited by 1
Segment-Then-Rank: Non-Factoid Question Answering on Instructional Videos
Lee, K., Duan, N., Ji, L., Li, J., & Hwang, S.-W. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6327 · Cited by 1
“%) is inferred in a single factoid sentence (Du, Shao, and Cardie 2017), and in action localization task (Regneri et al. 2013), text description consists of a short sentence (9 words on average).”
BackgroundRAD: Reinforced Attention Decoder Model On Question Generation
Li, X., Huang, Z., Liu, F., Wang, C., Hu, M., Xu, S., & Peng, Y. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207483 · Cited by 1
“However, such methods have been proven empirically weak for QA [5].”
MethodDRG2vec: Learning Word Representations from Definition Relational Graph
Shu, X., Yu, B., Zhang, Z., & Liu, T. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207015 · Cited by 1
“Continuous distributional word representations have become a common technique across a wide variety of natural language processing (NLP) tasks, such as neural machine translation [1, 2] and machine reading comprehension [3, 4].”
BackgroundFinding the Blank with Sequence Labeling for English Learning
Mehta, S., & Smetannikov, I. (2020) · International Conference on Control, Robotics and Intelligent System (CCRIS) · doi:10.1145/3437802.3437834 · Cited by 1
“The models performed comparably with the model defined in [3].”
MethodCSFQGD: Chinese Sentence Fill-in-the-blank Question Generation Dataset for Examination
Zhang, T., Cui, Z., Leng, J., & Liu, Y. (2021) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd49262.2021.9437824 · Cited by 2
“Recently, (cid:1) some (cid:1) question (cid:1) generation approaches (cid:1) [4], (cid:1) [5] (cid:1) based (cid:1) on (cid:1) neural (cid:1) network (cid:1) have (cid:1) achieved good (cid:1) performance.”
BackgroundMethodQuestion Generation via Multi-stage Answers Editing Network
Wang, L., Sheng, D., & Zheng, H.-T. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534027 · Cited by 1
Kannan, M., Ponnusamy, H. S., Kuthy, K. D., Stein, L., & Meurers, D. (2021) · International Conference on Natural Language Generation · doi:10.18653/v1/2021.inlg-1.3 · Cited by 1
“The work done by Du et al. (2017) introduces two such models, which are provided with the source sentence and paragraph-level information that encodes the context of the generated question.”
BackgroundAttention virtual adversarial based semi‐supervised question generation
An, J., Wang, K., Sun, H., Cui, C., Li, W., & Ma, C. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6797 · Cited by 1
“29 Thedifferenceisthatitsinputisadocumentratherthanaparagraph.”
MethodHarvesting More Answer Spans from Paragraph beyond Annotation
Bao, Q., Chen, J., Liu, L., Liu, J., Liang, J., & Xiao, Y. (2022) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3488560.3498399 · Cited by 1
Generating Questions for Abstractive Answers with a Multi-Channel Fusion Encoder-Decoder Model
Qiu, J., & Xiong, D. (2022) · International Conference on Asian Language Processing · doi:10.1109/ialp57159.2022.9961247 · Cited by 1
“[7] pioneer the neural QG using a neural seq2seq model.”
BackgroundMethodKnowledge Enhancement using Question Generation for Images and Chart Data Input
Tayal, D. K., Jain, A., Shrivastava, N., Jain, A., & Gaur, H. (2022) · International Conference on Artificial Intelligence and Speech Technology (AIST) · doi:10.1109/aist55798.2022.10064970 · Cited by 1
“From the various approaches proposed in literature for generating multi-choice questions, several approaches [11][12][20] are neural mode-based approaches using attention-based sequence learning model, recurrent neural model and sequence-to-sequence architecture with attention.”
QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation
Yue, Z., Zeng, H., Kratzwald, B., Feuerriegel, S., & Wang, D. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.147 · Cited by 2
Consecutive Question Generation via Dynamic Multitask Learning
Li, Y., Li, S., & Shi, X. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.493 · Cited by 1
How Well Do You Know Your Audience? Toward Socially-aware Question Generation
Stewart, I., & Mihalcea, R. F. (2022) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/2022.sigdial-1.27 · Cited by 1
“In addition to typical supervised learning approaches (Du et al., 2017), reinforcement learning has proven useful, where questions are assigned a higher “reward” if they are more likely to have interesting answers (Qi et al., 2020a) and more relevant to the context (Rao and Daumé, 2019).”
BackgroundEngaging Audiences in Virtual Museums by Interactively Prompting Guiding QuestionsPreprint
Zhao, Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.03527 · Cited by 1
Keeping Notes: Conditional Natural Language Generation with a Scratchpad MechanismPreprint
Benmalek, R. Y., Khabsa, M., Desu, S., Cardie, C., & Banko, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05275 · Cited by 1
“…the question generation domain, there has been a recent surge in research on generating questions for a given paragraph of text (Song et al., 2017; Du et al., 2017; Tang et al., 2017; Duan et al., 2017; Wang et al., 2018; Yao et al., 2018), with most of the work being a variant of the seq2seq…”
BackgroundSelf-citationVideo Question Generation via Cross-Modal Self-Attention Networks LearningPreprint
Wang, Y.-S., Su, H.-T., Chang, C.-H., Liu, Z.-Y., & Hsu, W. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.03049 · Cited by 1
“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.”
BackgroundAntNet: Deep Answer Understanding Network for Natural Reverse QA.Preprint
Yang, L., Yin, Q., Hou, L., Gui, J., Wu, O., & Kwok, J. T.-Y. (2019) · arXiv (Cornell University) · Cited by 1
Variational Question-Answer Pair Generation for Machine Reading Comprehension.Preprint
Shinoda, K., & Aizawa, A. (2020) · arXiv (Cornell University) · Cited by 1
Asking Complex Questions with Multi-hop Answer-focused ReasoningPreprint
Ma, X., Zhu, Q., Zhou, Y., Li, X., & Wu, D. O. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.07402 · Cited by 4
“Du et al. (2017) firstly proposes the question generation task that asks a free question given the context.”
BackgroundCan questions summarize a corpus? Using question generation for characterizing COVID-19 researchPreprint
Surita, G., Nogueira, R. F., & Lotufo, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.09290 · Cited by 2
“The inverse task of extractive question answering is known as oriented question generation (QG) [19].”
BackgroundKnowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge BasesPreprint
Bi, S., Cheng, X., Li, Y.-F., Wang, Y., & Qi, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03157 · Cited by 1
“3 Typed Decoder In order to generate questions that are consistent with the input subgraph, inspired by previous work (Du et al., 2017), we employ a typed decoder based on LSTM to calculate type-specific word probability distributions, which assumes that each word has a latent type of the set {interrogative, entity wo…”
BackgroundMethodInfluentialAGenT Zero: Zero-shot Automatic Multiple-Choice Question Generation for Skill AssessmentsPreprint
Li, E., Su, J., Sheng, H., & Wai, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.01186 · Cited by 2
“Given a context paragraph, Context-based Methods (Rajpurkar et al. 2016; Du, Shao, and Cardie 2017) are able to generate questions together with the correct answer.”
BackgroundSpartQA: : A Textual Question Answering Benchmark for Spatial ReasoningPreprint
Mirzaee, R., Faghihi, H. R., Ning, Q., & Kordjmashidi, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.05832 · Cited by 29
“, 2015), neural networks (Du et al., 2017), and their combinations (Dhole and Manning, 2020).”
BackgroundSemantic Answer Similarity for Evaluating Question Answering ModelsPreprint
Risch, J., Möller, T., Gutsch, J., & Pietsch, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.06130 · Cited by 29
“In line with the evaluation of QA models, the automated evaluation of models for question generation also relies on BLEU, ROUGE, and ME-TEOR, while human evaluation is limited to small datasets (Du et al., 2017).”
MethodKourouklides, I. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/sjrkh_v1 · Cited by 1
Computational Natural Language Inference: Robust and Interpretable Question Answering
Sharp, R. (2017) · UA Campus Repository (The University of Arizona)
A Scalable, Flexible Augmentation of the Student Education ProcessPreprint
Mehta, B. B., & Ramanathan, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.09845
“To do this, we train a Paragraph Level question-generation model as described in [8], and feed it the five sentences that had the highest total sentence score, where score was computed by summing the score given by all of the (concept, score) pairs in a given sentence.”
MethodThe RLLChatbot: a solution to the ConvAI challengePreprint
Gontier, N., Sinha, K., Henderson, P., Serban, I. V., Noseworthy, M., Parthasarathi, P., & Pineau, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.02714 · Cited by 1
“In this work, two distinct models under this scope are implemented: the Hierarchical Recurrent Encoder Decoder ( HRED ) (Serban et al., 2016) and the Neural Question Generator ( NQG ) (Du et al., 2017).”
BackgroundMethodHow Biased Is Your NLG Evaluation? (short paper).
Vougiouklis, P., Maddalena, E., Hare, J. S., & Simperl, E. P. B. (2018)
Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums
Chai, Z., Xing, X., Wan, X., & Huang, B. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1497
“We apply a Seq2seq model similar to Du et al. (2017), and use a CopyNet similar to Kumar et al. (2018b).”
MethodParaQG: A System for Generating Questions and Answers from ParagraphsPreprint
Kumar, V., Muneeswaran, S., Ramakrishnan, G., & Li, Y.-F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.01642 · Cited by 1
“Most of these models (Du et al., 2017; Kumar et al., 2018; Song et al., 2018; Kumar et al., 2019c,b) take single sentence as input, thus limiting their usefulness in real-world settings.”
BackgroundMaquera, F. I. M., Castro-Gutiérrez, E., & Valderrama, A. P. (2019) · LACCEI International Multi-Conference for Engineering, Education and Technology (LACCEI) · doi:10.18687/laccei2019.1.1.178
“Fourth, It has been trained a state-of-the-art sequence-to-sequence model to generate questions from paragraphs and sentences [4] for Spanish language.”
BackgroundMethodInfluentialTriple-Joint Modeling for Question Generation Using Cross-Task Autoencoder
Wang, H., Wu, R., Li, Z., Wang, Z., Chen, Z., & Zhou, G. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32236-6_26
Asking goal-oriented questions and learning from answers.
Rothe, A., Lake, B. M., & Gureckis, T. M. (2019) · eScholarship (California Digital Library)
Distant Supervised Why-Question Generation with Passage Self-Matching Attention
Hu, J., Li, Z., Wu, R., Wang, H., Liu, A., Xu, J., Zhao, P., & Zhao, L. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851781
“• Attention-based Seq2seq [6] is the first work for QG task using an end-to-end trainable sequence to sequence neural model with attention mechanism.”
BackgroundMethodInfluentialNeural Duplicate Question Detection without Labeled Training Data
Rücklé, A., Moosavi, N. S., & Gurevych, I. (2019) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.1911.05594
“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).”
Extended Answer and Uncertainty Aware Neural Question GenerationPreprint
Zeng, H., Zhi, Z., Liu, J., & Wei, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.08112
“(Du, Shao, and Cardie 2017) first tackle the QG using the attention-based encoder-decoder framework in an end-to-end fashion.”
Method3Q: A 3-Layer Semantic Analysis Model for Question Suite Reduction
Dai, W., Sheni, S., & Hei, T. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-36204-1_18
LocalGAN: Modeling Local Distributions for Adversarial Response Generation
Wang, B., Xu, Z. X., Zhang, H., Qiu, K., Zhang, D., & Sun, C. (2021) · Journal of Machine Learning Research
Separate Answer Decoding for Multi-class Question Generation
Wu, K., Hong, Y., Zhu, M., Tang, H., & Zhang, M. (2019) · International Conference on Asian Language Processing · doi:10.1109/ialp48816.2019.9037710
“Answers are sub-spans in the articles. split-1 Du et al. [6] extracted sentences and paired them with the questions, and then re-divided them into train/dev/test splits.”
BackgroundMethodInfluentialMapping Machine-Generated Questions to Their Related Paragraphs in the Textbook
Zhang, L. (2020) · Advances in analytics for learning and teaching · doi:10.1007/978-3-030-41099-5_14
Wu, X., Jiang, N., & Wu, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11665
“Du’s work (Du et al., 2017) is the first one to tackle this problem, and (Scialom et al.”
BackgroundMethodInfluentialEncoder-Decoder with Attention Mechanisms for Developing Question Generation Models in Education
Wijanarko, B. D. (2020) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2020/266942020
Question Generalization in Conversation
Peng, J., Zhong, S.-H., & Li, P. (2020) · Studies in computational intelligence · doi:10.1007/978-3-030-56178-9_7
DORB: Dynamically Optimizing Multiple Rewards with BanditsPreprint
Pasunuru, R., Guo, H., & Bansal, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.07635
“For question generation, we present results on the SQuAD QG dataset (Du et al., 2017), and for data-to-text NLG, we choose the WebNLG dataset (Gardent et al., 2017).”
BackgroundMethodInfluentialAn Embedding-Based Approach to Repairing Question Semantics
Zhou, H., & Wang, K. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-73216-5_8
Questions Generation for Reading Comprehension Using Coherence Relations
Anamika, Pathak, V., Shrivastava, V., & Panday, A. (2021) · Algorithms for intelligent systems · doi:10.1007/978-981-15-6707-0_6
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
