MixQG: Neural Question Generation with Mixed Answer Types
Lidiya Murakhovs’ka, Chien-Sheng Wu, Philippe Laban, Tong Niu, Wenhao Liu, Caiming Xiong
Abstract
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.- Anthology ID:
- 2022.findings-naacl.111
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2022
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1486–1497
- Language:
- URL:
- https://aclanthology.org/2022.findings-naacl.111
- DOI:
- 10.18653/v1/2022.findings-naacl.111
- Cite (ACL):
- Lidiya Murakhovs’ka, Chien-Sheng Wu, Philippe Laban, Tong Niu, Wenhao Liu, and Caiming Xiong. 2022. MixQG: Neural Question Generation with Mixed Answer Types. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1486–1497, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- MixQG: Neural Question Generation with Mixed Answer Types (Murakhovs’ka et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2022.findings-naacl.111.pdf
- Code
- salesforce/qgen
- Data
- BoolQ, DROP, MCTest, NarrativeQA, Natural Questions, Quoref, SQuAD