HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing

Autor:	Zheng, Yanzhao, Wang, Haibin, Dong, Baohua, Wang, Xingjun, Li, Changshan
Rok vydání:	2022
Předmět:	Computer Science - Databases Computer Science - Artificial Intelligence Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	Recently, context-dependent text-to-SQL semantic parsing which translates natural language into SQL in an interaction process has attracted a lot of attention. Previous works leverage context-dependence information either from interaction history utterances or the previous predicted SQL queries but fail in taking advantage of both since of the mismatch between natural language and logic-form SQL. In this work, we propose a History Information Enhanced text-to-SQL model (HIE-SQL) to exploit context-dependence information from both history utterances and the last predicted SQL query. In view of the mismatch, we treat natural language and SQL as two modalities and propose a bimodal pre-trained model to bridge the gap between them. Besides, we design a schema-linking graph to enhance connections from utterances and the SQL query to the database schema. We show our history information enhanced methods improve the performance of HIE-SQL by a significant margin, which achieves new state-of-the-art results on the two context-dependent text-to-SQL benchmarks, the SparC and CoSQL datasets, at the writing time. Comment: Accepted at ACL 2022 Findings
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2203.07376 Zobrazit plný text záznamu View this record from Arxiv