Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation

Zichen Wu, Xin Jia, Fanyi Qu, Yunfang Wu


Abstract
Today the pre-trained language models achieve great success for question generation (QG) task and significantly outperform traditional sequence-to-sequence approaches. However, the pre-trained models treat the input passage as a flat sequence and are thus not aware of the text structure of input passage. For QG task, we model text structure as answer position and syntactic dependency, and propose answer localness modeling and syntactic mask attention to address these limitations. Specially, we present localness modeling with a Gaussian bias to enable the model to focus on answer-surrounded context, and propose a mask attention mechanism to make the syntactic structure of input passage accessible in question generation process. Experiments on SQuAD dataset show that our proposed two modules improve performance over the strong pre-trained model ProphetNet, and combing them together achieves very competitive results with the state-of-the-art pre-trained model.
Anthology ID:
2022.coling-1.571
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6564–6574
Language:
URL:
https://aclanthology.org/2022.coling-1.571
DOI:
Bibkey:
Cite (ACL):
Zichen Wu, Xin Jia, Fanyi Qu, and Yunfang Wu. 2022. Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6564–6574, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation (Wu et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.571.pdf
Data
SQuAD