Papers by Zecheng Zhan

1 papers
Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation (P19-1)

Copied to clipboard

Challenge: IRNet synthesizes SQL queries in an end-to-end manner, but it yields unsatisfactory performance on public benchmarks.
Approach: They propose a neural approach called IRNet for complex and cross-domain Text-to-SQL.
Outcome: IRNet achieves 46.7% accuracy on the Spider benchmark, a 19.5% improvement over state-of-the-art approaches.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations