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
Unified Language Model Pre-training for Natural Language Understanding and Generation
Dong, L., Yang, N., Wang, W., Wei, F., Liu, X., Wang, Y., Gao, J., Zhou, M., & Hon, H.-W. (2019) · arXiv · doi:10.48550/arxiv.1905.03197 · Cited by 1,225
GLM: General Language Model Pretraining with Autoregressive Blank Infilling
Du, Z., Qian, Y., Liu, X., Ding, M., Qiu, J., Yang, Z., & Tang, J. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.26 · Cited by 1,068
“Considering the available baseline results, we use the Gigaword dataset (Rush et al., 2015) for abstractive summarization and the SQuAD 1.1 dataset (Rajpurkar et al., 2016) for question generation (Du et al., 2017) as the benchmarks for models pretrained on BookCorpus and Wikipedia.”
MethodInfluentialEvent Extraction by Answering (Almost) Natural Questions
Du, X., & Cardie, C. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.49 · Cited by 459
Self-citationProphetNet: Predicting Future N-gram for Sequence-to-SequencePre-training
Qi, W., Yan, Y., Gong, Y., Liu, D., Duan, N., Chen, J., Zhang, R., & Zhou, M. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.217 · Cited by 459
(2020) · doi:10.18653/v1/2020.acl-main.450 · Cited by 356
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
