Paper Info
Title
Similar Questions Correspond to Similar SQL Queries: A Case-Based Reasoning Approach for Text-to-SQL Translation
Abstract
Based on the natural truth that similar questions correspond to similar SQL queries, a CBR-based approach is proposed to deal with the Text-to-SQL task in this paper. We follow the traditional CBR processes: similarity assessment, case retrieval, and case reuse. First, we introduce a neural classifier in the similarity assessment stage and comprehensively uses classification probability and literal cosine similarity to measure similarity. Then, based on the results of the similarity assessment, our model retrieves a case template. Finally, our model fills the columns and values generated by the Ranker module and Question Answering (QA) module into the solution template. At this point, a SQL query suitable for the new case is generated. We evaluate our models on a large-scale Text-to-SQL dataset-WikiSQL. Experimentally, our model has a competitive performance compared with the baseline and significantly improves the accuracy of the aggregation function prediction.
Year
DOI
Venue
2021
10.1007/978-3-030-86957-1_20
CASE-BASED REASONING RESEARCH AND DEVELOPMENT, ICCBR 2021
Keywords
DocType
Volume
Case-based reasoning, Text-to-SQL, Semantic parsing
Conference
12877
ISSN
Citations 
PageRank 
0302-9743
1
0.37
References 
Authors
7
6
Name
Order
Citations
PageRank
Wei Yu11338118.61
Xiaoting Guo210.37
Fei Chen310.71
Tao Chang410.37
Mengzhu Wang523.44
X. D. Wang6246.63