mRAT-SQL+GAP:A Portuguese Text-to-SQL Transformer

TL;DR

This paper adapts a transformer-based Text-to-SQL system for Portuguese by using multilingual models and translated datasets, demonstrating effective cross-lingual transfer and providing open-source tools for non-English SQL translation tasks.

Contribution

It introduces a multilingual adaptation of RAT-SQL+GAP for Portuguese, including dataset translation and training strategies, enabling effective non-English Text-to-SQL translation.

Findings

Multilingual training improves Portuguese SQL translation performance.

The adapted model achieves 83% of the baseline accuracy.

Training with combined original and translated datasets enhances results.

Abstract

The translation of natural language questions to SQL queries has attracted growing attention, in particular in connection with transformers and similar language models. A large number of techniques are geared towards the English language; in this work, we thus investigated translation to SQL when input questions are given in the Portuguese language. To do so, we properly adapted state-of-the-art tools and resources. We changed the RAT-SQL+GAP system by relying on a multilingual BART model (we report tests with other language models), and we produced a translated version of the Spider dataset. Our experiments expose interesting phenomena that arise when non-English languages are targeted; in particular, it is better to train with original and translated training datasets together, even if a single target language is desired. This multilingual BART model fine-tuned with a double-size training dataset (English and Portuguese) achieved 83% of the baseline, making inferences for the Portuguese test dataset. This investigation can help other researchers to produce results in Machine Learning in a language different from English. Our multilingual ready version of RAT-SQL+GAP and the data are available, open-sourced as mRAT-SQL+GAP at: https://github.com/C4AI/gap-text2sql