Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases

Sheng Bi, Xiya Cheng, Yuan-Fang Li, Yongzhen Wang, Guilin Qi


Abstract
Question generation over knowledge bases (KBQG) aims at generating natural-language questions about a subgraph, i.e. a set of triples. Two main challenges still face the current crop of encoder-decoder-based methods, especially on small subgraphs: (1) low diversity and poor fluency due to the limited information contained in the subgraphs, and (2) semantic drift due to the decoder’s oblivion of the semantics of the answer entity. We propose an innovative knowledge-enriched, type-constrained and grammar-guided KBQG model, named KTG, to addresses the above challenges. In our model, the encoder is equipped with auxiliary information from the KB, and the decoder is constrained with word types during QG. Specifically, entity domain and description, as well as relation hierarchy information are considered to construct question contexts, while a conditional copy mechanism is incorporated to modulate question semantics according to current word types. Besides, a novel reward function featuring grammatical similarity is designed to improve both generative richness and syntactic correctness via reinforcement learning. Extensive experiments show that our proposed model outperforms existing methods by a significant margin on two widely-used benchmark datasets SimpleQuestion and PathQuestion.
Anthology ID:
2020.coling-main.250
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2776–2786
Language:
URL:
https://aclanthology.org/2020.coling-main.250
DOI:
10.18653/v1/2020.coling-main.250
Bibkey:
Cite (ACL):
Sheng Bi, Xiya Cheng, Yuan-Fang Li, Yongzhen Wang, and Guilin Qi. 2020. Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2776–2786, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases (Bi et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.250.pdf
Data
PathQuestion