Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss
This work improves question generation for knowledge bases, but it is incremental as it builds on existing neural methods with specific enhancements.
The paper tackles question generation over knowledge bases by addressing the need to express given predicates and ensure definitive answers, achieving state-of-the-art performance.
We tackle the task of question generation over knowledge bases. Conventional methods for this task neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to be definitive. In this paper, we strive toward the above two issues via incorporating diversified contexts and answer-aware loss. Specifically, we propose a neural encoder-decoder model with multi-level copy mechanisms to generate such questions. Furthermore, the answer aware loss is introduced to make generated questions corresponding to more definitive answers. Experiments demonstrate that our model achieves state-of-the-art performance. Meanwhile, such generated question can express the given predicate and correspond to a definitive answer.