论文标题
Duorat：朝着更简单的文本到SQL模型
DuoRAT: Towards Simpler Text-to-SQL Models
论文作者
论文摘要
最近的神经文本到SQL模型可以有效地将自然语言问题转化为看不见的数据库中的相应的SQL查询。研究人员主要在蜘蛛数据集上工作，提出了越来越复杂的解决方案。与这一趋势相反，在本文中，我们专注于简化。我们首先要构建Duorat，这是对最先进的RAT-SQL模型的重新实现，而Rat-SQL仅使用关系感知或Vanilla Transformers作为构建块。我们使用Duorat作为基线模型进行了几个消融实验。我们的实验证实了某些技术的有用性，并指出了其他技术的冗余，包括将问题与模式联系起来的结构SQL功能和功能。
Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases. Working mostly on the Spider dataset, researchers have proposed increasingly sophisticated solutions to the problem. Contrary to this trend, in this paper we focus on simplifications. We begin by building DuoRAT, a re-implementation of the state-of-the-art RAT-SQL model that unlike RAT-SQL is using only relation-aware or vanilla transformers as the building blocks. We perform several ablation experiments using DuoRAT as the baseline model. Our experiments confirm the usefulness of some techniques and point out the redundancy of others, including structural SQL features and features that link the question with the schema.
