Improving Text-to-SQL with a Hybrid Decoding Method

Improving Text-to-SQL with a Hybrid Decoding Method

Text-to-SQL is a task that converts natural language questions into SQL queries. Recent text-to-SQL models employ two decoding methods: sketch-based and generation-based, but each has its own shortcomings. The sketch-based method has limitations in performance as it does not reflect the relevance be...

Full description

Bibliographic Details
Main Authors: Geunyeong Jeong, Mirae Han, Seulgi Kim, Yejin Lee, Joosang Lee, Seongsik Park, Harksoo Kim
Format: Article
Language:English
Published: MDPI AG 2023-03-01
Series:Entropy
Subjects:
semantic parsing
text-to-SQL
pointer network
natural language processing
Online Access:https://www.mdpi.com/1099-4300/25/3/513

Similar Items

Similar Items