SE-HCL: Schema Enhanced Hybrid Curriculum Learning for Multi-Turn Text-to-SQL
Existing multi-turn Text-to-SQL approaches, mainly use data in a randomized order when training the model, ignoring the rich structural information contained in the dialog and schema. In this paper, we propose to use curriculum learning (CL) to better leverage the curriculum structure of schema, que...
Saved in:
Main Authors: | Yiyun Zhang, Sheng'an Zhou, Gengsheng Huang |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10433573/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Self-correcting complex semantic analysis method based on pre-training mechanism
by: Qing LI, et al.
Published: (2019-12-01) -
Research on the SQL injection filtering based on SQL syntax tree
by: Chen-wang HAN, et al.
Published: (2016-11-01) -
Performance Evaluation of NewSQL Databases in a Distributed Architecture
by: Zhiyao Zhang, et al.
Published: (2025-01-01) -
LotusSQL: SQL Engine for High-Performance Big Data Systems
by: Xiaohan Li, et al.
Published: (2021-12-01) -
Network log analysis with SQL-on-Hadoop
by: Si-yu ZHANG, et al.
Published: (2014-10-01)