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

arXiv: https://arxiv.org/abs/2010.03157 · HTML: https://mlsanity.com/paper/2010.03157/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection](https://mlsanity.com/paper/2105.09509/) (2021)
- [Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Model](https://mlsanity.com/paper/2110.06560/) (2021)
- [AutoQGS: Auto-Prompt for Low-Resource Knowledge-based Question Generation from SPARQL](https://mlsanity.com/paper/2208.12461/) (2022)
- [SGSH: Stimulate Large Language Models with Skeleton Heuristics for Knowledge Base Question Generation](https://mlsanity.com/paper/2404.01923/) (2024)
- [A Survey on Neural Question Generation: Methods, Applications, and Prospects](https://mlsanity.com/paper/2402.18267/) (2024)
- [Data Distribution Bottlenecks in Grounding Language Models to Knowledge Bases](https://mlsanity.com/paper/2309.08345/) (2023)
- [Ask To The Point: Open-Domain Entity-Centric Question Generation](https://mlsanity.com/paper/2310.14126/) (2023)
- [KGConv, a Conversational Corpus grounded in Wikidata](https://mlsanity.com/paper/2308.15298/) (2023)
- [Knowledge Graph Quality Evaluation under Incomplete Information](https://mlsanity.com/paper/2212.00994/) (2022)

## Abstract (arXiv)

Question generation over knowledge bases (KBQG) aims at generating natural-language questions about a subgraph, i.e. a set of (connected) 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.