Generating and Answering Simple and Complex Questions from Text and from Knowledge Graphs

摘要

While both text and Knowledge Graphs (KG) may be used to answer a question, most current Question Answering and Generation models only work on a single modality. In this paper, we introduce a multi-task model such that questions can be generated and answered from both KG and text. The model has wide coverage and handles both simple (one KG fact) and complex (more than one KG fact) questions. Extensive internal, cross-modal and external consistency checks, and analysis of the quality of the generated questions, show that our approach out-performs previous work. Our data and modeling also leads to improvements in downstream tasks, including better performance with fine-tuning Open-Domain QA architectures and better correlation with human judgments than the Data-QuestEval metric which was previously proposed for evaluating the semantic adequacy of KG-to-Text generations.