Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation
This work addresses a novel task in natural language processing for generating complex questions, which could benefit applications like question answering and education, though it appears incremental as it builds on existing simple question datasets and models.
The paper tackles the problem of automatically generating complex questions from knowledge graphs by leveraging existing simple question datasets, either through sub-questions or pseudo sub-questions. The proposed extension models, CoGSub2Q and CoGSub^m2Q, significantly outperform the base model and its augmented variant, demonstrating the importance of instance-level connections over model-level ones.
This paper makes one of the first efforts toward automatically generating complex questions from knowledge graphs. Particularly, we study how to leverage existing simple question datasets for this task, under two separate scenarios: using either sub-questions of the target complex questions, or distantly related pseudo sub-questions when the former are unavailable. First, a competitive base model named CoG2Q is designed to map complex query qraphs to natural language questions. Afterwards, we propose two extension models, namely CoGSub2Q and CoGSub^m2Q, respectively for the above two scenarios. The former encodes and copies from a sub-question, while the latter further scores and aggregates multiple pseudo sub-questions. Experiment results show that the extension models significantly outperform not only base CoG2Q, but also its augmented variant using simple questions as additional training examples. This demonstrates the importance of instance-level connections between simple and corresponding complex questions, which may be underexploited by straightforward data augmentation of CoG2Q that builds model-level connections through learned parameters.