We propose an iterative framework designed for end-to-end nl2sql translation models to autonomously generate the best output through self-evaluation.

We propose a confidence-based knowledge integration framework that uses a two-stage deep-learning-based ranking technique to mitigate the low-confidence problem commonly associated with Seq2seq models for TableQA.

We propose a unified generate-then-rank framework that can be flexibly incorporated with existing NLIDBs to consistently improve their translation accuracy.

We propose a generate-and-rank approach for accurate natural language to SQL translation.