The DOI matches its Crossref record; 22 of the 24 references it cites were found in a registry or an index.
NewsQA: A Machine Comprehension Dataset
Open accessAbstract
We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text in the articles. We collect this dataset through a four-stage process designed to solicit exploratory questions that require reasoning. Analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment. We measure human performance on the dataset and compare it to several strong neural models. The performance gap between humans and machines (13.3% F1) indicates that significant progress can be made on NewsQA through future research. The dataset is freely available online.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“Existing datasets vary in size, difficulty, and collection methodology; however, as pointed out by Rajpurkar et al. (2016), most suffer from one of two shortcomings: those that are designed explicitly to test comprehension (Richardson et al.”
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×
“Word embeddings are initialized using GloVe vectors (Pennington et al., 2014) pre-trained on the 840-billion Common Crawl corpus.”
BackgroundMethodBLEU: 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 1×
“BLEU is a precision-based metric popular in machine translation that uses a weighted average of variable length phrase matches ( n -grams) against the reference sentence (Papineni et al., 2002).”
MethodSQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 3×
“Existing datasets vary in size, difficulty, and collection methodology; however, as pointed out by Rajpurkar et al. (2016), most suffer from one of two shortcomings: those that are designed explicitly to test comprehension (Richardson et al., 2013) are too small for training data-intensive deep…”
BackgroundMethodInfluentialCIDEr: Consensus-based image description evaluation
Vedantam, R., Zitnick, C. L., & Parikh, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299087 · Cited by 4,845 · cited 2×
“ase matches (n-grams) against the reference sentence (Papineni et al., 2002). CIDEr was designed to correlate better with human judgements of sentence similarity, and uses tf-idf scores over n-grams (Vedantam et al., 2015). As given in Table 4, humans averaged 0.694 F1 on NewsQA. The human EM scores are relatively low…”
MethodInfluentialOn the difficulty of training recurrent neural networks
Pascanu, R., Mikolov, T., & Bengio, Y. (2012) · arXiv · doi:10.48550/arxiv.1211.5063 · Cited by 4,310
Teaching Machines to Read and ComprehendPreprint
Hermann, K. M., Kočiský, T., Grefenstette, E., Espeholt, L., Kay, W., Suleyman, M., & Blunsom, P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.03340 · Cited by 2,855
Liu, C., Lowe, R., Serban, I. V., Noseworthy, M., Charlin, L., & Pineau, J. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1230 · Cited by 1,377
Exact solutions to the nonlinear dynamics of learning in deep linear neural networksPreprint
Saxe, A., McClelland, J. L., & Ganguli, S. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.6120 · Cited by 1,010
MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text
Richardson, M., Burges, C., & Renshaw, E. (2013) · Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1020 · Cited by 778 · cited 5×
“Like Richardson et al. (2013) we want to encourage reasoning in comprehension models.”
BackgroundInfluential
Research works printed but not linked: 3
- NewsQA: A Machine Comprehension Dataset https://aclanthology.org/W17-2623/ (Trischler et al., RepL4NLP 2017)
- Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, and Kaheer Suleman. 2017. NewsQA: A Machine Comprehension Dataset. In Proceedings of the 2nd Workshop on Representation Learning for NLP, pages 191–200, Vancouver, Canada. Association for Computational Linguistics.
- ACL materials are Copyright © 1963–2026 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
Cited by
Sorted by citations
Items 501–600 of 708
AutoEQA: Auto-Encoding Questions for Extractive Question Answering
Varanasi, S., Amin, S., & Neumann, G. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.403 · Cited by 3
“For EQA, given that there is no supervised signal for answer spans, an exhaustive search over all the possible phrases would be sub-optimal as there can be many phrases not suitable for natural language questions (Trischler et al., 2017; Joshi et al., 2017).”
BackgroundMethodLiang, W. E. N., Haibo, S. H. I., Zhang, X., Xin, S. U. N., Wei, X., Wang, J., Cheng, Z., Yin, D., Wang, X., Luo, Y., et al. (2022) · Chinese Journal of Electronics · doi:10.1049/cje.2021.00.079 · Cited by 2
Study of a lifelong learning scenario for question answering
Echegoyen, G., Rodrigo, Á., & Peñas, A. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118271 · Cited by 4
Open-Domain Long-Form Question–Answering Using Transformer-Based Pipeline
Dash, A., Awachar, M., Patel, A. M., & Rudra, B. (2023) · SN Computer Science · doi:10.1007/s42979-023-02039-x · Cited by 3
“The SQUAD [16] dataset and the NewsQA [17] dataset are prominent examples of extractive datasets.”
MethodLearning to Generalize for Cross-domain QA
Niu, Y., Yang, L., Dong, R., & Zhang, Y. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.84 · Cited by 5
Answer Quality Aware Aggregation for Extractive QA Crowdsourcing
Zhu, P., Wang, Z., Hauff, C., Yang, J., & Anand, A. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.457 · Cited by 2
“Although it is possible to consider more real or simulated datasets, as shown by the experiments on SQuAD and Natural Questions in Appendix A.3, NewsQA is the only large extractive QA dataset that provides all actual annotations to the best of our knowledge.”
InfluentialNegT5: A Cross-Task Text-to-Text Framework for Negation in Question Answering
Jin, T., Racharak, T., & Nguyen, L.-M. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-5837-5_23 · Cited by 2
The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models
Tran, S. Q., Nguyen-Thuan, P., Le, U., & Kretchmar, M. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.113 · Cited by 3
RobustQA: A Framework for Adversarial Text Generation Analysis on Question Answering Systems
Boreshban, Y., Mirbostani, S. M., Ahmadi, S. F., Shojaee, G., Kamani, F., Ghassem-Sani, G., & Mirroshandel, S. A. (2023) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/2023.emnlp-demo.24 · Cited by 2
“With the release of large and high-quality datasets in the field of question answering (QA) (Rajpurkar et al., 2016; Joshi et al., 2017; Trischler et al., 2017; Koˇciský et al., 2018), we witness significant progress in this area of research.”
Beware of Model Collapse! Fast and Stable Test-time Adaptation for Robust Question Answering
Su, Y., Ji, Y., Li, J., Ye, H., & Zhang, M. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.803 · Cited by 3
“MRQA (Fisch et al., 2019) is a cross-domain dataset which includes HotpotQA (Yang et al., 2018), NaturalQA (Kwiatkowski et al., 2019), NewsQA (Trischler et al., 2017), SearchQA (Dunn et al., 2017), and TriviaQA (Joshi et al., 2017).”
BackgroundNguyen, D.-A., Li, M., Lambert, G. W., Kowalczyk, R., McDonald, R. L., & Vo, Q. B. (2024) · JMIR Formative Research · doi:10.2196/52482 · Cited by 2
CoURAGE: A Framework to Evaluate RAG Systems
Galla, D., Hoda, S., Zhang, M., Quan, W., Yang, T. D., & Voyles, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70242-6_37 · Cited by 2
A resilient generative model in few-shot question answering
Zou, A., Chen, Y., Huang, R., & Qin, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113629 · Cited by 2
Attention-Based Memory Network for Sentence-Level Question Answering
Liu, P., Zhang, C., Zhang, W., Zhan, Z., & Zhuang, B. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-6805-8_9 · Cited by 2
Factoid Question Answering with Distant Supervision
Zhang, H., Liang, X., Xu, G.-L., Fu, K., Li, F., & Huang, T.-L. (2018) · Entropy · doi:10.3390/e20060439 · Cited by 1
“Question answering (QA) can facilitate the information acquisition from multiple data sources, such as structured knowledge bases (KB) [1,2], semi-structured tables [3] and free texts [4–6].”
BackgroundSMART: A Stratified Machine Reading Test
Yao, J., Feng, M., Feng, H., Wang, Z., Zhang, Y., & Xue, N. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32233-5_6 · Cited by 2
Introduction to machine reading comprehension
Zhu, C. (2021) · Elsevier eBooks · doi:10.1016/b978-0-323-90118-5.00001-1 · Cited by 6
A Chinese Machine Reading Comprehension Dataset Automatic Generated Based on Knowledge Graph
Zhao, H., Yuan, S., Leng, J., Pan, X., Zhao, X., Ma, Q., & Liang, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-84186-7_18 · Cited by 2
“202 NewsQA (Trischler et al., 2016) is another corpus that focuses on the news field, but it is relatively small, and most questions are the span of words.”
BackgroundUnsupervised Multiple Choices Question Answering: Start Learning from Basic Knowledge
Liu, C.-L., & Lee, H.-Y. (2021) · Workshop on Machine Reading for Question Answering (MRQA) · doi:10.18653/v1/2021.mrqa-1.12 · Cited by 4
“Recently, numerous question answering datasets (Weston et al., 2015; Rajpurkar et al., 2016, 2018; Yang et al., 2018; Trischler et al., 2017; Choi et al., 2018; Joshi et al., 2017; Kwiatkowski et al., 2019; Reddy et al., 2019; Richardson, 2013; Lai et al., 2017a; Khashabi et al., 2018) have been…”
BackgroundMethodInfluentialLinguistic characterization of answer passages for fact-seeking question answering
Ofoghi, B. (2022) · ACM Symposium on Applied Computing · doi:10.1145/3477314.3506999 · Cited by 2
Varghese, N., & Punithavalli, M. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-9113-3_1 · Cited by 2
Trustworthy machine reading comprehension with conditional adversarial calibration
Wu, Z., & Xu, H. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04235-3 · Cited by 2
“Questions [23] and NewsQA [24] datasets indicate that TrustMRC can make reliable predictions under domain shift setting.”
MethodInfluentialMulti-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
Ye, H., Xie, Q., & Ng, H. T. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.537 · Cited by 6
Domain Incremental Lifelong Learning in an Open World
Dai, Y. Q., Lang, H., Zheng, Y., Yu, B., Huang, F., & Li, Y. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.361 · Cited by 2
Discord Questions: A Computational Approach To Diversity Analysis in News Coverage
Laban, P., Wu, C.-S., Murakhovs’ka, L., Chen, X., & Xiong, C. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.380 · Cited by 7
G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks
Wan, Z., Yin, Y., Zhang, W., Shi, J., Shang, L., Chen, G., Jiang, X., & Liu, Q. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.441 · Cited by 13
HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark
Cohen, A., Merhav, H., Goldberg, Y., & Tsarfaty, R. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.915 · Cited by 3
“Other known datasets are NewsQA (Trischler et al., 2017) that were collected from news articles, TriviaQA (Joshi et al., 2017), a large-scale dataset (650K samples) that used questions from quiz web sites aligned with Wikipedia and web re-sults, and CoQA (Reddy et al., 2019), a dataset focused on…”
Natural Response Generation for Chinese Reading Comprehension
Chen, N., Li, H., Bao, Y., Wang, B., & Li, J. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.739 · Cited by 2
An Efficient Document Retrieval for Korean Open-Domain Question Answering Based on ColBERT
Kang, B., Kim, Y., & Shin, Y. (2023) · Applied Sciences · doi:10.3390/app132413177 · Cited by 2
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
“We use the split by [1] for QG. NewsQA [16] contains a large scale of news articles from CNN.”
MethodUnsupervised Story Comprehension with Hierarchical Encoder-Decoder
Wang, B., Yao, T., Zhang, Q., Xu, J., Liu, K., Tian, Z., & Zhao, J. (2019) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3341981.3344227 · Cited by 2
“SQuAD [28], NewsQA [38] and MARCO [23] are recently released MC datasets.”
BackgroundBéchet, F., Aloui, C., Charlet, D., Damnati, G., Heinecke, J., Nasr, A., & Herledan, F. (2019) · Workshop on Machine Reading for Question Answering (MRQA) · doi:10.18653/v1/d19-5803 · Cited by 3
“…mentioned in the introduction, several corpora in English have been proposed for MRC tasks as presented in (Nguyen et al., 2016), such as NewsQA (Trischler et al., 2016), SearchQA (Dunn et al., 2017) including questions from the Jeopardy game paired to text segments collected through search…”
BackgroundMethodLabel Distribution Augmented Maximum Likelihood Estimation for Reading Comprehension
Su, L., Guo, J., Fan, Y., Lan, Y., & Cheng, X. (2020) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3336191.3371835 · Cited by 2
A guide to the dataset explosion in QA, NLI, and commonsense reasoning
Rogers, A., & Rumshisky, A. (2020) · doi:10.18653/v1/2020.coling-tutorials.5 · Cited by 2
“Questions are more difficult if they are collected independently from the text (Kwiatkowski et al., 2019), written from summaries (Trischler et al., 2016) or hints (Choi et al., 2018).”
BackgroundInteractive Machine Comprehension with Dynamic Knowledge Graphs
Yuan, X. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.540 · Cited by 3
“Like an adversarial game, researchers release new datasets (Hill et al., 2015; Chen et al., 2016; Rajpurkar et al., 2016; Trischler et al., 2016a; Nguyen et al., 2016; Reddy et al., 2018; Yang et al., 2018a; Choi et al., 2018; Clark et al., 2020) and novel models (Trischler et al., 2016b; Wang and…”
BackgroundSelf-citationZhou, 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
“, 2018), NewsQA (Trischler et al., 2017), and Natural Questions (NQ) (Kwiatkowski et al.”
Machine Reading Comprehension Model for Low-Resource Languages and Experimenting on Vietnamese
Nguyen, B. H. T., Nguyen, D. M., & Nguyen, T. T. T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-08530-7_31 · Cited by 2
Datasets for Machine Reading Comprehension: A Literature ReviewPreprint
Ingale, V., Singh, P., & Bhardwaj, A. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3454037 · Cited by 2
Relation Module for Non-answerable Prediction on Question AnsweringPreprint
Huang, K., Tang, Y., Huang, J., He, X., & Zhou, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.10843 · Cited by 2
“By taking a weighted sum of all of the relation scores that the sentence has, we generate a non-answerable score that is trained jointly with answer span scores from any MRC model to determine non-answerability.”
BackgroundInfluentialPrerequisites for Explainable Machine Reading Comprehension: A Position Paper.Preprint
Sugawara, S., Stenetorp, P., & Aizawa, A. (2020) · arXiv (Cornell University) · Cited by 2
Composing Answer from Multi-spans for Reading ComprehensionPreprint
Zhang, Z., Zhang, Y., Zhao, H., Zhou, X., & Zhou, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.06141 · Cited by 2
“Further, the span extraction task (Rajpurkar et al. 2016; Ra-jpurkar, Jia, and Liang 2018; Trischler et al. 2017; Joshi et al. 2017; Dunn et al. 2017) requires to predict the answer span from the given passage.”
MethodQuestion 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
“0 (Rajpurkar et al., 2018) and NewsQA (Trischler et al., 2017), smaller subsets of such high-loss examples yield better MRC training than larger populations of random roundtrip-consistent examples.”
BackgroundZero-Shot Dialogue State Tracking via Cross-Task TransferPreprint
Lin, Z., Liu, B., Madotto, A., Moon, S., Crook, P., Zhou, Z., Wang, Z., Yu, Z., Cho, E., Subba, R., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.04655 · Cited by 2
“The first is extractive QA (Ra-jpurkar et al., 2016, 2018; Trischler et al., 2017; Joshi et al., 2017; Dunn et al., 2017; Yang et al., 2018; Kwiatkowski et al., 2019), where the answer to each answerable question appears as a span of tokens in the passage.”
BackgroundInfluentialQu, F., Jia, X., & Wu, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.05179 · Cited by 6
“Tang et al. (2017) regard QA and QG as dual tasks and explicitly leverage their probabilistic correlation to guide the training process of both QA and QG. Wang et al. (2017) design a generative machine that encodes the document and generates a question (answer) given an answer (question).”
Learn a prior question-aware feature for machine reading comprehension
Zhang, Y., Shen, B., & Cao, X. (2022) · Frontiers in Physics · doi:10.3389/fphy.2022.1085102 · Cited by 1
“Since humans leverage various forms of questions to assess how well language learners have mastered the language, MRC also generates various types of tasks to evaluate the machine’s understanding level of the article [1], such as reading comprehension with multiple choice [2], cloze test [3], span extraction [4, 5], f…”
BackgroundMA-MRC: A Multi-answer Machine Reading Comprehension Dataset
Yue, Z., Liu, J., Zhang, C., Wang, C., Jiang, H., Zhang, Y., Tian, X., Cen, Z., Xiao, Y., & Ruan, T. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3592015 · Cited by 1
Curriculum Learning Driven Domain Adaptation for Low-Resource Machine Reading Comprehension
Zhang, L., Wang, Q., Xu, B., Liu, Y., & Mao, Z. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3429270 · Cited by 1
W iki H int : A Human-Annotated Dataset for Hint Ranking and Generation
Mozafari, J., Gerhold, F., & Jatowt, A. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730284 · Cited by 6
Nawaz, A., Ahmed, M., Khan, H. U., Daud, A. Y., Alshemaimri, B. K., & Iqbal, T. (2025) · Scientific Reports · doi:10.1038/s41598-025-26671-0 · Cited by 2
“To assess the model’s generalization, we further performed experiments on three additional benchmark datasets including SQuAD, NewsQA, and Natural Questions and the model maintained competitive performance across all datasets.”
InfluentialExplainable Semantic Text Relations: A Question-Answering Framework for Comparing Document Content
Aperstein, Y., Gottlib, A., Benita, G., & Apartsin, A. (2025) · Information · doi:10.3390/info16121090 · Cited by 1
“Trischler et al. [40] collected ∼ 100K QA pairs; later analyses [36] note that a significant fraction ( ∼ 13 – 14% in train) are “ nil ” questions with no answer span.”
Anwar, M. R., Khalid, S., Alshahrani, S., Bilal, H. S. M., & Aldawsari, M. F. (2026) · IEEE Access · doi:10.1109/access.2026.3652006 · Cited by 2
Liu, Z., Huang, P., Xu, Z., Li, X., Liu, S., Peng, C., Xin, H., Yan, Y., Wang, S., Han, X., et al. (2026) · AI Open · doi:10.1016/j.aiopen.2026.02.002 · Cited by 1
Ke, W., Yang, L., & Xu, M. (2026) · AI · doi:10.3390/ai7080320 · Cited by 1
Can Knowledge Enhance Reading Comprehension? An Integrated Approach with Semantic Lexicon
Wei Kun, K. O. N. G., Racharak, T., & Nguyen, L.-M. (2020) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse50997.2020.9287218 · Cited by 1
A Transfer Learning Approach for Descriptive Question Answering System
Bansode, G., Jha, D. K., Hasabnis, A., Nayak, A., & Pagare, R. (2021) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon52575.2021.9686521 · Cited by 1
Wu, Z., Xu, H., Fang, J., & Gao, K. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.179 · Cited by 1
“For CDA-C setting, we regard MRC datasets with different passage corpora (e.g., Wikipedia, News, and Web snippets) as different domains and choose five datasets: SQuAD 1.1 (Rajpurkar et al., 2016), HotpotQA (Yang et al., 2018), Natural Questions (Trischler et al., 2017), NewsQA (Trischler et al., 2017), and TriviaQA (J…”
BackgroundInfluentialA Sequence Modelling Approach to Question Answering in Text-Based Games
Furman, G., Toledo, E., Shock, J. P., & Buys, J. (2022) · doi:10.18653/v1/2022.wordplay-1.4 · Cited by 1
“Traditional methods for question answering (QA) and machine reading comprehension (MRC) are primarily concerned with the retrieval of declarative knowledge , that is, explicitly stated or static descriptions of entities in text documents or within a knowledge base (KB) (Trischler et al., 2017).”
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
Kaushik, P., Kumar, K. V., & Biswas, P. (2022) · 2022 8th International Conference on Signal Processing and Communication (ICSC) · doi:10.1109/icsc56524.2022.10009634 · Cited by 1
Deep QA: An Open-Domain Dataset of Deep Questions and Comprehensive Answers
Anbarasu, H. S., Navalli, H. V., Vidapanakal, H., Gowd, K. M., & Das, B. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-35299-7_16 · Cited by 1
Phan, T.-A., Jung, J. J., & Bui, K. N. (2023) · IEEE Access · doi:10.1109/access.2023.3298100 · Cited by 1
“This method is straightforward, but it leads the severe problems due to the limitation in reading space in case the model must synthesize the content of multi-part of the document to reason the results [5], [6], [7].”
MethodClaimDiff: Comparing and Contrasting Claims on Contentious Issues
Ko, M., Seong, I., Lee, H., Park, J., Chang, M., & Seo, M. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.289 · Cited by 3
“Extracting the phrases from a given text is similar to the previous MRC (Rajpurkar et al., 2016; Trischler et al., 2017).”
BackgroundResultOn Conditional and Compositional Language Model Differentiable Prompting
Pilault, J., Liu, C., Bansal, M., & Dreyer, M. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/460 · Cited by 4
Fangfang, W., Zhang, J., & Yuan, H. (2023) · International Conference on Asian Language Processing · doi:10.1109/ialp61005.2023.10337119 · Cited by 1
Alexandrov, D., Zakharova, A., & Butakov, N. A. (2023) · International Journal of Semantic Computing · doi:10.1142/s1793351x24410046 · Cited by 1
Analysis of Machine Reading Comprehension Problem Using Machine Learning Techniques
Kakulapati, V., Gagganapalli, J. R., Reddy, K. K. K., Reddy, P. A., & Reddy, D. (2023) · Journal of Scientific Research and Reports · doi:10.9734/jsrr/2023/v29i121814 · Cited by 1
NORMY: Non-Uniform History Modeling for Open Retrieval Conversational Question Answering
Rashid, M. S., Meem, J. A., & Hristidis, V. (2024) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc59802.2024.00022 · Cited by 5
“It started with TREC [5] in the early days where the goal was to retrieve the appropriate passage for 200 factoid questions and advanced to recent high-quality datasets like NQ [4], SQuAD [6], NewsQA [36].”
BackgroundZhao, P., Zhang, Z., & Liu, B. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9431-7_4 · Cited by 1
Multi-Perspective Fusion Network for Commonsense Reading Comprehension
Liu, C., Yan, Z., Si, Q., Zhang, H., Li, B., & Yu, D. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01716-3_22 · Cited by 1
“Several datasets have been constructed for testing the comprehension ability of a system, such as MCTest [15], SQuAD [14], BAbI [22], TriviaQA [6], RACE [8], and NewsQA [17].”
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
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
“Examples of extractive QA are SQuAD (Rajpurkar et al. 2016), NewsQA (Trischler et al. 2016), and TriviaQA (Joshi et al. 2017), based on web documents.”
MethodScholarlyRead: A New Dataset for Scientific Article Reading Comprehension.
Saikh, T., Ekbal, A., & Bhattacharyya, P. (2020) · Language Resources and Evaluation · Cited by 1
Multi-span Extractive Reading Comprehension Without Multi-span Supervision
Takahashi, T., Taniguchi, M., Taniguchi, T., & Ohkuma, T. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72240-1_41 · Cited by 1
CSFQGD: 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
Shimmei, M., & Matsuda, N. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78270-2_57 · Cited by 1
“Large datasets such as SQuAD [6], NewsQA [7], MSMARCO [8] enabled training a recurrent neural network (RNN) for question generation.”
MethodBiQuAD: Towards QA based on deeper text understanding
Grimm, F., & Cimiano, P. (2021) · Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/2021.starsem-1.10 · Cited by 1
“Together with NewsQA (Trischler et al., 2017), these datasets represent the largest, crowd-sourced, extractive QA datasets available.”
MethodThinkTwice: A Two-Stage Method for Long-Text Machine Reading Comprehension
Dong, M., Zou, B., Qian, J., Huang, R., & Hong, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88480-2_34 · Cited by 1
Relying on Discourse Analysis to Answer Complex Questions by Neural Machine Reading Comprehension
Galitsky, B. A., Ilvovsky, D., & Goncharova, E. (2021) · International conference Recent advances in natural language processing · doi:10.26615/978-954-452-072-4_051 · Cited by 1
“We should also mention that the introduced ensemble model outperforms both the stand-alone fine-tuned BERT and current state-of-the-art models for NewsQA and achieves comparable results on QuAC.”
MethodInfluentialKamath, U., Liu, J., & Whitaker, J. (2019) · Springer eBooks · doi:10.1007/978-3-030-14596-5_1 · Cited by 1
A Review of Machine Reading Comprehension
殷, 明. (2020) · Computer Science and Application · doi:10.12677/csa.2020.1012261 · Cited by 1
Exploring the Utility of Dutch Question Answering Datasets for Human Resource Contact Centres
van Toledo, C., Schraagen, M., van Dijk, F., Brinkhuis, M. J. S., & Spruit, M. R. (2022) · Information · doi:10.3390/info13110513 · Cited by 3
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
“Previous works mostly focus on extractive QA datasets, such as SQuAD [11] and NewsQA [29].”
BackgroundUKP-SQuARE v3: A Platform for Multi-Agent QA Research
Puerto, H., Baumgärtner, T., Sachdeva, R. S., Fang, H., Zhang, H., Tariverdian, S., Wang, K., & Gurevych, I. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-demo.55 · Cited by 1
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
Jeong, S., Baek, J., Hwang, S. J., & Park, J. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.35 · Cited by 2
Learning Open Information Extraction of Implicit Relations from Reading Comprehension DatasetsPreprint
Beckerman, J. P., & Christakis, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.07471 · Cited by 3
“We created a large training corpus for implicit OpenIE extractors based on SQuAD and NewsQA, trained a baseline on this dataset, and presented promising results on implicit extraction.”
Godin, F., Kumar, A., & Mittal, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.10236 · Cited by 4
“Recently, popular textual QA datasets have been extended with not-answerable questions (Trischler et al., 2017; Rajpurkar et al., 2018).”
BackgroundMovie Plot Analysis via Turning Point IdentificationPreprint
Papalampidi, P., Keller, F., & Lapata, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.10328 · Cited by 14
“…Answering (QA) tasks are transitioning from investigating single short and clean articles or queries (Rajpurkar et al., 2016; Nguyen et al., 2016; Trischler et al., 2016) to large scale datasets that consist of complex stories (Tapaswi et al., 2016; Frermann et al., 2018; Koˇcisk`y et al.,…”
What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question AnsweringPreprint
Khot, T., Sabharwal, A., & Clark, P. E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.09253 · Cited by 2
“While several RC datasets (Ra-jpurkar et al., 2016; Trischler et al., 2017; Joshi et al., 2017) can be addressed with single sentence understanding, newer datasets (Weston et al., 2015; Welbl et al., 2018; Khashabi et al., 2018; Yang et al., 2018) specifically target multi-hop reasoning.”
BackgroundLearning a Cost-Effective Annotation Policy for Question AnsweringPreprint
Kratzwald, B., Feuerriegel, S., & Sun, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03476 · Cited by 2
“Prominent examples include the Stanford Question and Answer Dataset (SQuAD; Ra-jpurkar et al., 2016), HotPotQA (Yang et al., 2018), or NewsQA (Trischler et al., 2017).”
BackgroundMulti-turn Dialogue Reading Comprehension with Pivot Turns and KnowledgePreprint
Zhang, Z., Li, J., & Zhao, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.05474 · Cited by 1
“Although the dialogue comprehension shares a similar form with the standard reading comprehension tasks [31], [38], [55], [58], [59], understanding multi-turn dialogues is much more complex for two key challenges.”
BackgroundTowards Solving Multimodal ComprehensionPreprint
Sahu, P., Sikka, K., & Divakaran, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.10139 · Cited by 1
“Research in this area has been propelled by multiple datasets from different domains and of varying complexity [25, 7, 16, 18, 8, 6, 30].”
BackgroundTracing Origins: Coref-aware Machine Reading Comprehension.Preprint
Huang, B., Zhang, Z., & Zhao, H. (2021) · arXiv (Cornell University) · Cited by 1
Learning with Noisy Labels by Targeted Relabeling.Preprint
Chen, D., Yu, Z., & Bowman, S. R. (2021) · arXiv (Cornell University) · Cited by 1
A framework for closed domain question answering systems in the low data regime.
Carmo, V. C. D. O. (2022) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.3.2022.tde-24052023-152815 · Cited by 1
Abeyratne, R., Wiratunga, N., Martin, K., & Nkisi-Orji, I. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6153652 · Cited by 1
X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension
Abdou, M., Sas, C., Aralikatte, R., Augenstein, I., & Søgaard, A. (2019) · Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo) · doi:10.18653/v1/d19-6130 · Cited by 9
“It has, however, recently been incorporated into newer datasets (Trischler et al., 2017; Rajpurkar et al., 2018; Saha et al., 2018).”
Background
Metadata
- Authors
- Trischler, A., Wang, T., Yuan, X., Harris, J., Sordoni, A., Bachman, P., & Suleman, K.
- Venue
- Proceedings of the 2nd Workshop on Representation Learning for NLP
- Published
- 2017
- Pages
- 191-200
- OpenAlex
- W2557764419
- Cited by
- 706
- References
- 24
- Citations by year
- 2026: 18 · 2025: 26 · 2024: 39 · 2023: 96 · 2022: 110 · 2021: 134 · 2020: 138 · 2019: 87 · 2018: 41 · 2017: 16
- FWCI
- 35.17
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Workshop on Representation Learning for NLP (RepL4NLP) (publishedVersion, cc-by)
- 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
- machine reading comprehension, question answering, news articles, exploratory questions, reasoning
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
