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

TL;DR

This paper introduces MultiSpider, the largest multilingual text-to-SQL dataset covering seven languages, analyzes language-specific challenges, and proposes a schema augmentation method that improves multilingual performance.

Contribution

It provides a comprehensive multilingual dataset for text-to-SQL and a schema augmentation framework to enhance cross-lingual performance.

Findings

Non-English languages experience a 6.1% accuracy drop.

The SAVe framework improves overall accuracy by 1.8%.

The performance gap across languages is reduced by 29.5%.

Abstract

Text-to-SQL semantic parsing is an important NLP task, which greatly facilitates the interaction between users and the database and becomes the key component in many human-computer interaction systems. 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 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 three typical 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.