论文标题
超越I.I.D。：在知识基础上回答问题的三个概括
Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases
论文作者
论文摘要
关于知识库（KBQA）的问题的现有研究主要以标准的I.I.D假设（即，对问题上的培训分布与测试分布相同）进行。但是，i.i.d在大规模的KB上可能既可以合理地可以实现，也不是可取的，因为1）很难捕获真正的用户分布，而2）来自巨大空间的随机样品训练示例将是很高的数据范围。取而代之的是，我们建议KBQA模型应具有三个内置的概括：I.I.D，组成和零射。为了促进具有更强概括的KBQA模型的开发，我们构建和释放了一个新的大规模，高质量的数据集，其中包含64,331个问题，即Grailqa，并为所有三个概括提供了评估设置。此外，我们提出了一种基于BERT的新型KBQA模型。我们的数据集和模型的组合使我们能够首次彻底检查和证明预训练的上下文嵌入（如BERT）在KBQA概括中的关键作用。
Existing studies on question answering on knowledge bases (KBQA) mainly operate with the standard i.i.d assumption, i.e., training distribution over questions is the same as the test distribution. However, i.i.d may be neither reasonably achievable nor desirable on large-scale KBs because 1) true user distribution is hard to capture and 2) randomly sample training examples from the enormous space would be highly data-inefficient. Instead, we suggest that KBQA models should have three levels of built-in generalization: i.i.d, compositional, and zero-shot. To facilitate the development of KBQA models with stronger generalization, we construct and release a new large-scale, high-quality dataset with 64,331 questions, GrailQA, and provide evaluation settings for all three levels of generalization. In addition, we propose a novel BERT-based KBQA model. The combination of our dataset and model enables us to thoroughly examine and demonstrate, for the first time, the key role of pre-trained contextual embeddings like BERT in the generalization of KBQA.
