MixQG: Neural Question Generation with Mixed Answer Types
Open accessAbstract
Asking good questions is an essential ability for both human and machine intelligence.However, existing neural question generation approaches mainly focus on short factoid type of answers.In this paper, we introduce a neural question generator, MixQG, to bridge this gap.We combine nine question answering datasets with diverse answer types, including yes/no, multiple-choice, extractive, and abstractive answers, to train a single generative model.We show with empirical results that our model outperforms existing work in both seen and unseen domains, and can generate questions with different cognitive levels when conditioned on different answer types.We run a human evaluation study to assess the quality of generated questions and find that MixQG outperforms the next best model by 10%.Our code and model checkpoints will be released and integrated with the HuggingFace library to facilitate various downstream applications.
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
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?
The unified T5 and BART model of [69] gave state-of-the-art results on automatic and qualitative evaluation.
“Evaluation of their unified model was done on both automatic metrics and qualitative parameters, which gave state-of-the art results.”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [69]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 52 · Cited by 31
Research works printed but not linked: 5
- Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, and Hsiao-Wuen Hon. 2019b. Unified language model pre-training for natural language understanding and generation. In 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) .
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language models are unsupervised multitask learners. OpenAI blog , 1(8):9.
- Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-totext transformer. Journal of Machine Learning Research , 21(140):1-67.
- Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang, and Ming Zhou. 2020a. Prophetnet: Predicting future ngram for sequence-to-sequence pre-training. arXiv preprint arXiv:2001.04063 . · arXiv
- Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang, and Ming Zhou. 2020b. Prophetnet: Predicting future ngram for sequence-to-sequence pre-training. CoRR , abs/2001.04063. · arXiv
- Authors
- Murakhovs’ka, L., Wu, C.-S., Laban, P., Niu, T., Liu, W., & Xiong, C.
- Affiliations
- Salesforce (United States) (US)
- Venue
- Findings of the Association for Computational Linguistics: NAACL 2022
- Published
- 2022
- Pages
- 1486-1497
- OpenAlex
- W3205871113
- Cited by
- 31
- References
- 52
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 6 · 2023: 15 · 2022: 6
- FWCI
- 4.15
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: NAACL (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
- yes-no questions, multiple-choice questions, question answering dataset, question quality evaluation
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
