Tracking Interaction States for Multi-Turn Text-to-SQL Semantic Parsing
This work provides an incremental improvement for researchers and developers working on multi-turn text-to-SQL systems by achieving better performance on a challenging dataset.
This paper addresses multi-turn text-to-SQL semantic parsing by defining and tracking interaction states based on schema items and SQL keywords. The proposed method utilizes relational graph neural networks and non-linear layers to update these state representations, which are then used to decode SQL queries.
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.