Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing

Authors

  • Run-Ze Wang National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China
  • Zhen-Hua Ling National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China
  • Jingbo Zhou Business Intelligence Lab, Baidu Research
  • Yu Hu iFLYTEK Research

Keywords:

Lexical & Frame Semantics, Semantic Parsing

Abstract

The task of multi-turn text-to-SQL semantic parsing aims to translate natural language utterances in an interaction into SQL queries in order to answer them using a database which normally contains multiple table schemas. Previous studies on this task usually utilized contextual information to enrich utterance representations and to further influence the decoding process. While they ignored to describe and track the interaction states which are determined by history SQL queries and are related with the intent of current utterance. In this paper, two kinds of interaction states are defined based on schema items and SQL keywords separately. A relational graph neural network and a non-linear layer are designed to update the representations of these two states respectively. The dynamic schema-state and SQL-state representations are then utilized to decode the SQL query corresponding to current utterance. Experimental results on the challenging CoSQL dataset demonstrate the effectiveness of our proposed method, which achieves better performance than other published methods on the task leaderboard.

Downloads

Published

2021-05-18

How to Cite

Wang, R.-Z., Ling, Z.-H., Zhou, J., & Hu, Y. (2021). Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16), 13979-13987. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17646

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing III