Integrating question answering and text-to-SQL in Portuguese
Abstract
Deep learning transformers have drastically improved systems that automatically answer questions in natural language. However, different questions demand different answering techniques; here we propose, build and validate an architecture that integrates different modules to answer two distinct kinds of queries. Our architecture takes a free-form natural language text and classifies it to send it either to a Neural Question Answering Reasoner or a Natural Language parser to SQL. We implemented a complete system for the Portuguese language, using some of the main tools available for the language and translating training and testing datasets. Experiments show that our system selects the appropriate answering method with high accuracy (over 99\%), thus validating a modular question answering strategy.
Cite
@article{arxiv.2202.04048,
title = {Integrating question answering and text-to-SQL in Portuguese},
author = {Marcos Menon José and Marcelo Archanjo José and Denis Deratani Mauá and Fábio Gagliardi Cozman},
journal= {arXiv preprint arXiv:2202.04048},
year = {2022}
}
Comments
Published at International Conference on the Computational Processing of Portuguese (PROPOR 2022)