This paper aims to improve the performance of text-to-SQL parsing by exploring the intrinsic uncertainties in the neural network based approaches (called SUN). From the data uncertainty perspective, it is indisputable that a single SQL can be learned from multiple semantically-equivalent questions.Different from previous methods that are limited to one-to-one mapping, we propose a data uncertainty constraint to explore the underlying complementary semantic information among multiple semantically-equivalent questions (many-to-one) and learn the robust feature representations with reduced spurious associations. In this way, we can reduce the sensitivity of the learned representations and improve the robustness of the parser. From the model uncertainty perspective, there is often structural information (dependence) among the weights of neural networks. To improve the generalizability and stability of neural text-to-SQL parsers, we propose a model uncertainty constraint to refine the query representations by enforcing the output representations of different perturbed encoding networks to be consistent with each other. Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms strong competitors and achieves new state-of-the-art results. For reproducibility, we release our code and data at https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/sunsql.
翻译:本文旨在通过探索神经网络方法(称为 SUN ) 的内在不确定性来改进文本到 SQL 分析的性能。 从数据不确定性的角度来看,一个单一 SQL 能够从多个等量问题中学习,这是无可争议的。 与以往方法不同,这些方法仅限于一对一的映射,我们提出了数据不确定性限制,以探索多个语义等同问题(many-to-one)之间的基本补充语义信息,并学习与虚构的关联关系减少的强大特征表现。这样,我们可以降低所学的表达方式的敏感性,提高分析器的稳健性。从模型不确定性的角度来看,神经网络的重量中往往有结构性信息(依赖性)。为了改善神经文本到SQL 剖析器的可通用性和稳定性,我们提出了模型不确定性限制,通过执行不同深层编码网络的产出表述来改进查询表达方式,使之与对方一致。 在五个基准数据集上进行广泛的实验,显示我们的方法大大超越了AFUR/ARABA 数据库的强大竞争者和新代码。