基于关系型T5和重排名解码的Text-to-SQL方法分析
Analysis of Text to SQL Method Based on Relational T5 and Reordering Decoding
杨智慧1
作者信息
摘要
阐述针对Text-to-SQL任务,构建一个带有重排名解码模块的关系型T5模型.将关系感知的自我注意模块引入T5编码器,以此提高模型对各种关系结构的语义理解能力.在解码过程中,对PICARD获得的N-best列表引入重排名解码,可通过搜寻算法,检查列表中的每个预测实体名称是否在数据库中出现,以提高结果的选择正确性.
Abstract
This paper expounds that a relational T5 model with a re-ranking decoding module is constructed for the Text-to-SQL task.Specifically,introduces a relationship-aware self-attentive module into the T5 encoder as a way to improve the model's semantic understanding of various relationship structures.In addition,in the decoding process,this paper introduces re-ranking decoding to the N-best list obtained by PICARD,which can be used to check whether the entity name in each prediction in the list appears in the database by a search algorithm to improve the correctness of the selection of results.
关键词
智能算法/文本到SQL/语义解析/关系图注意力网络Key words
intelligent algorithms/Text-to-SQL/semantic parsing/relational graph attention network引用本文复制引用
出版年
2024
NETL
NSTL
万方数据