文献类型：期刊文献

英文题名：A Comprehensive Exploration on Spider with Fuzzy Decision Text-to-SQL Model

作者：Li, Qing[1];Li, Lili[2];Li, Qi[3];Zhong, Jiang[1]

机构：[1]Chongqing Univ, Coll Comp Sci, Chongqing 400044, Peoples R China;[2]Chongqing Univ, Sch Civil Engn, Chongqing 400044, Peoples R China;[3]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Peoples R China

年份：2020

卷号：16

期号：4

起止页码：2542

外文期刊名：IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS

收录：SCI-EXPANDED(收录号：WOS:000510901000035)、、EI(收录号：20200508106014)、Scopus(收录号：2-s2.0-85078514431)、WOS

基金：This work was supported in part by the Fundamental Research Funds for the Central University (No.2018CDYJSY0055), in part by the National Key Research and Development Program of China (No.2017YFB1402401), in part by the Graduate Research and Innovation Foundation of Chongqing, China (No.CYB18058), and in part by the Key Research Program of Chongqing Science and Technology Bureau (No.cstc2018jszx-cyzdX0086). Paper no. TII-19-2387.

语种：英文

外文关键词：Fuzzy decision; fuzzy semantic deep network; natural language processing (NLP); text-to-SQL

外文摘要：The challenge of natural language processing is from natural language to logical form (SQL). In this article, we present an fuzzy semantic to structured query language (F-SemtoSql) neural approach that is a fuzzy decision semantic deep network query model based on demand aggregation. It aims to address the problem of the complex and cross-domain text-to-SQL generation task. The corpus is trained as the input word vector of the model with LSTM and Word2Vec embedding technology. Combined with the dependency graph method, the problem of SQL statement generation is converted to slot filling. Complex tasks are divided into four levels via F-SemtoSql and constructed by the need of aggregation. At the same time, to avoid the order problem in the traditional model effectively, we have adopted the attention mechanism and used a fuzzy decision mechanism to improve the model decision. On the challenging text-to-SQL benchmark Spider and the other three datasets, F-SemtoSql achieves faster convergence and occupies the first position.