Tracking Interaction States for Multi-Turn Text-to-SQL 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.

Accepted by AAAI 2021

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
• Improving Text-to-SQL Evaluation Methodology
• Language to Logical Form with Neural Attention
• CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
• Coarse-to-Fine Decoding for Neural Semantic Parsing
• Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
• Global Reasoning over Database Structures for Text-to-SQL Parsing