@inproceedings{kreitlow-oliveira-2026-describe,
    title = "To Describe or Not to Describe? Benchmarking Database Representations for Schema Linking in Text-to-{SQL}",
    author = "Kreitlow, Daiane Ucceli  and
      Oliveira, Hil{\'a}rio Tomaz Alves de",
    editor = "Souza, Marlo  and
      de-Dios-Flores, Iria  and
      Santos, Diana  and
      Freitas, Larissa  and
      Souza, Jackson Wilke da Cruz  and
      Ribeiro, Eug{\'e}nio",
    booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
    month = apr,
    year = "2026",
    address = "Salvador, Brazil",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-dnd/2026.propor-1.15/",
    pages = "151--160",
    ISBN = "979-8-89176-387-6",
    abstract = "Text-to-SQL systems aim to translate natural language questions into Structured Query Language (SQL) queries, enabling database access without requiring SQL expertise. In real-world scenarios, these systems often need to manage multiple databases with heterogeneous schemas, making Schema Linking a crucial preliminary step for identifying relevant databases, tables, and columns. This study investigates Schema Linking for questions written in Brazilian Portuguese and compares two schema representation strategies: natural-language descriptions generated by Large Language Models (LLMs) and representations based on Data Definition Language (DDL) and Data Manipulation Language (DML) commands. Experiments conducted on a Brazilian Portuguese version of the Spider dataset, with over 200 databases, evaluated several LLMs and embedding models. The experimental results based on Hit@k show that natural language descriptions consistently outperform DDL/DML-based representations, demonstrating the effectiveness of LLM-generated schema descriptions for Schema Linking tasks."
}