M-SQL: Multi-Task Representation Learning for Single-Table Text2sql Generation
Authors:
- Xiaoyu ZhangXZXiaoyu Zhang
- Fengjing YinFYFengjing Yin
- Guojie MaGMGuojie Ma
- Bin GeBGBin Ge
- Weidong XiaoWXWeidong Xiao
Open Access
- 2 March 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 43156-43167
Abstract
Text2SQL can help non-professionals connect with databases by turning natural languages into SQL. Although previous researches about Text2SQL have provided some workable solutions, most of them extract values based on column representation. If there are multiple values in the query and these values belong to different columns, the previous approaches based on column representation cannot accurately extract values. In this work, we propose a new neural network architecture based on the pre-trained BERT, called M-SQL. The column-based value extraction is divided into two modules, value extraction and value-column matching. We evaluate M-SQL on a more complicated TableQA dataset, which comes from an AI competition. We rank first in this competition. Experimental results and competition ranking show that our proposed M-SQL achieves state-of-the-art results on TableQA.Keywords
Funding Information
- National Natural Science Foundation of China (71971212, 61902417, 61872446)
This publication has 9 references indexed in Scilit:
- Multi-Task Deep Neural Networks for Natural Language Understanding2019
- Semantic Parsing for Task Oriented Dialog using Hierarchical Representations2018
- Coarse-to-Fine Decoding for Neural Semantic Parsing2018
- Deep Contextualized Word Representations2018
- TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation2018
- Language to Logical Form with Neural Attention2016
- Data Recombination for Neural Semantic Parsing2016
- Ontology-based Sentiment Analysis Process for Social Media ContentProcedia Computer Science, 2015
- Long Short-Term MemoryNeural Computation, 1997