Log In Sign Up

Hybrid Ranking Network for Text-to-SQL

by   Qin Lyu, et al.

In this paper, we study how to leverage pre-trained language models in Text-to-SQL. We argue that previous approaches under utilize the base language models by concatenating all columns together with the NL question and feeding them into the base language model in the encoding stage. We propose a neat approach called Hybrid Ranking Network (HydraNet) which breaks down the problem into column-wise ranking and decoding and finally assembles the column-wise outputs into a SQL query by straightforward rules. In this approach, the encoder is given a NL question and one individual column, which perfectly aligns with the original tasks BERT/RoBERTa is trained on, and hence we avoid any ad-hoc pooling or additional encoding layers which are necessary in prior approaches. Experiments on the WikiSQL dataset show that the proposed approach is very effective, achieving the top place on the leaderboard.


page 1

page 2

page 3

page 4


A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions

Text-to-SQL parsing is an essential and challenging task. The goal of te...

Contextualized Word Representations for Document Re-Ranking

Although considerable attention has been given to neural ranking archite...

CEDR: Contextualized Embeddings for Document Ranking

Although considerable attention has been given to neural ranking archite...

GP: Context-free Grammar Pre-training for Text-to-SQL Parsers

A new method for Text-to-SQL parsing, Grammar Pre-training (GP), is prop...

DrugDBEmbed : Semantic Queries on Relational Database using Supervised Column Encodings

Traditional relational databases contain a lot of latent semantic inform...

Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

Most recently, there has been significant interest in learning contextua...

Embedding Individual Table Columns for Resilient SQL Chatbots

Most of the world's data is stored in relational databases. Accessing th...