MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing

Abstract

Text-to-SQL semantic parsing is an important NLP task, which facilitates the interaction between users and the database. Much recent progress in text-to-SQL has been driven by large-scale datasets, but most of them are centered on English. In this work, we present MultiSpider, the largest multilingual text-to-SQL semantic parsing dataset which covers seven languages (English, German, French, Spanish, Japanese, Chinese, and Vietnamese). Upon MultiSpider we further identify the lexical and structural challenges of text-to-SQL (caused by specific language properties and dialect sayings) and their intensity across different languages. Experimental results under various settings (zero-shot, monolingual and multilingual) reveal a 6.1% absolute drop in accuracy in non-English languages. Qualitative and quantitative analyses are conducted to understand the reason for the performance drop of each language. Besides the dataset, we also propose a simple schema augmentation framework SAVe (Schema-Augmentation-with-Verification), which significantly boosts the overall performance by about 1.8% and closes the 29.5% performance gap across languages.

FastRAT: Fast and Efficient Cross-lingual Text-to-SQL Semantic Parsing

“…The efforts of the scientific community to build systems for cross-lingual semantic parsing have led to the development of a series of relevant benchmark datasets (Min et al, 2019;Dou et al, 2023;Zhang et al, 2023). Most recent approaches for cross-lingual semantic parsing have sought to localise parsers to new target languages using backtranslations (Sherborne et al, 2020) or machine translation (Xia and Monti, 2021;Shi et al, 2022).…”

“…In an effort to alleviate the shortcomings of Textto-SQL solutions, increasingly difficult datasets and benchmarks have been developed (Zhong et al, 2017;Yu et al, 2018;Min et al, 2019;Dou et al, 2023;Zhang et al, 2023). The efforts to explore the generalisability of such Text-to-SQL systems have recently culminated with the introduction of multiple database datasets, which distinguish between training and evaluation databases.…”