This post is a brief summary about the paper that I read for my study and curiosity, so I shortly arrange the content of the paper, titled Towards Generalizable and Robust Text-to-SQL Parsing (Gao et al., EMNLP 2022), that I read and studied.

They proposed that Text-to-SQL parser should be built with strong generalizability in terms of all three levels of generalization, namely i.i.d., zero-shot, and compositional, and robustness again input perturbations.

So, they propose a novel framework consisting of three learning stages including Task decomposition, Knowledge acquisition, and Knowledge composition (TKK)

For detailed experiment and explanation, refer to the paper, titled Towards Generalizable and Robust Text-to-SQL Parsing (Gao et al., EMNLP 2022)

Reference

• Paper
  • ArXiv Version: Towards Generalizable and Robust Text-to-SQL Parsing(Gao et al., ArXiv 2022)
  • EMNLP Version: Towards Generalizable and Robust Text-to-SQL Parsing (Gao et al., EMNLP 2022)
• Leaderboard & Github
  • Github1
• How to use html for alert
  • how to use icon
• How to use MathJax
  • MathJax basic tutorial and quick reference in StackExchange