LFKQG: A Controlled Generation Framework with Local Fine-tuning for Question Generation over Knowledge Bases

Zichu Fei, Xin Zhou, Tao Gui, Qi Zhang, Xuanjing Huang


Abstract
Question generation over knowledge bases (KBQG) aims at generating natural questions about a subgraph, which can be answered by a given answer entity. Existing KBQG models still face two main challenges: (1) Most models often focus on the most relevant part of the answer entity, while neglecting the rest of the subgraph. (2) There are a large number of out-of-vocabulary (OOV) predicates in real-world scenarios, which are hard to adapt for most KBQG models. To address these challenges, we propose LFKQG, a controlled generation framework for Question Generation over Knowledge Bases. (1) LFKQG employs a simple controlled generation method to generate the questions containing the critical entities in the subgraph, ensuring the question is relevant to the whole subgraph. (2) We propose an optimization strategy called local fine-tuning, which can make good use of the rich information hidden in the pre-trained model to improve the ability of the model to adapt the OOV predicates. Extensive experiments show that our method outperforms existing methods significantly on three widely-used benchmark datasets SimpleQuestion, PathQuestions, and WebQuestions.
Anthology ID:
2022.coling-1.572
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:
6575–6585
Language:
URL:
https://aclanthology.org/2022.coling-1.572
DOI:
Bibkey:
Cite (ACL):
Zichu Fei, Xin Zhou, Tao Gui, Qi Zhang, and Xuanjing Huang. 2022. LFKQG: A Controlled Generation Framework with Local Fine-tuning for Question Generation over Knowledge Bases. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6575–6585, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
LFKQG: A Controlled Generation Framework with Local Fine-tuning for Question Generation over Knowledge Bases (Fei et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.572.pdf