Abstract
We propose a type-controlled framework for inquisitive question generation. We annotate an inquisitive question dataset with question types, train question type classifiers, and finetune models for type-controlled question generation. Empirical results demonstrate that we can generate a variety of questions that adhere to specific types while drawing from the source texts. We also investigate strategies for selecting a single question from a generated set, considering both an informative vs. inquisitive question classifier and a pairwise ranker trained from a small set of expert annotations. Question selection using the pairwise ranker yields strong results in automatic and manual evaluation. Our human evaluation assesses multiple aspects of the generated questions, finding that the ranker chooses questions with the best syntax (4.59), semantics (4.37), and inquisitiveness (3.92) on a scale of 1-5, even rivaling the performance of human-written questions.- Anthology ID:
- 2022.starsem-1.22
- Volume:
- Proceedings of the 11th Joint Conference on Lexical and Computational Semantics
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, Washington
- Editors:
- Vivi Nastase, Ellie Pavlick, Mohammad Taher Pilehvar, Jose Camacho-Collados, Alessandro Raganato
- Venue:
- *SEM
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 240–257
- Language:
- URL:
- https://aclanthology.org/2022.starsem-1.22
- DOI:
- 10.18653/v1/2022.starsem-1.22
- Cite (ACL):
- Lingyu Gao, Debanjan Ghosh, and Kevin Gimpel. 2022. “What makes a question inquisitive?” A Study on Type-Controlled Inquisitive Question Generation. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 240–257, Seattle, Washington. Association for Computational Linguistics.
- Cite (Informal):
- “What makes a question inquisitive?” A Study on Type-Controlled Inquisitive Question Generation (Gao et al., *SEM 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2022.starsem-1.22.pdf
- Code
- educationaltestingservice/inquisitive-questions
- Data
- INQUISITIVE, Penn Treebank, SQuAD