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

Findings of the Association for Computational Linguistics: ACL 2022, pages 2997 - 3007 May 22-27, 2022 c⃝2022 Association for Computational Linguistics HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing Yanzhao Zheng∗ Haibin Wang∗ Baohua Dong Xingjun Wang Changshan Li† Alibaba Group, Hangzhou, China {zhengyanzhao.zyz,binke.whb,baohua.dbh,xingjun.wxj}@alibaba-inc.com, lics16@mails.tsinghua.edu.cn Abstract Recently, context-dependent text-to-SQL se- mantic parsing which translates natural lan- guage into SQL in an interaction process has attracted a lot of attention. Previous works leverage context-dependence information ei- ther from interaction history utterances or the previous predicted SQL queries but fail in taking advantage of both since of the mis- match 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 in- formation 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 im- prove the performance of HIE-SQL by a signif- icant 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. 1 Introduction Conversation user interfaces to databases have launched a new research hotspot in Text-to-SQL se- mantic parsing (Zhang et al., 2019; Guo et al., 2019; Wang et al., 2020; Lin et al., 2020; Xu et al., 2021; Cao et al., 2021; Hui et al., 2021; Yu et al., 2021b) and benefited us in industry (Dhamdhere et al., 2017; Weir et al., 2020). Most previous works fo- cus on the context-independent text-to-SQL task and propose many competitive models. Some mod- els (Wang et al., 2020; Scholak et al., 2021) even surprisingly work well on the context-dependent ∗ Equal contribution. † Corresponding author. Figure 1: An example of context-dependent text-to- SQL interaction in CoSQL where Ui is the utterance of turn i and Si is the corresponding SQL query for Ui. The tokens with red color are the history informa- tion that should be considered in later predictions. It is context-independent if we just consider the prediction of S1. text-to-SQL task by just appending the interac- tion history utterances to the input. Especially, PICARD (Scholak et al., 2021) achieves state-of-the- art performances both in Spider (Yu et al., 2018b), a cross-domain context-independent text-to-SQL benchmark, and CoSQL (Yu et al., 2019a), a cross- domain context-dependent text-to-SQL benchmark, before our work. However, every coin has two sides. That implies underachievement of the explo- ration of context information in context-dependent text-to-SQL semantic parsing. Compared with context-independent text-to- SQL semantic parsing, context-dependent text-to- SQL semantic parsing are more challenging since of the various types of dependence in utterances which make models vulnerable to parsing errors. As R2SQL (Hui et al., 2021) considers, different context dependencies between two adjacent utter- ances require the model to establish …

Content truncated to 500 words