DEEPAGÉ: Answering Questions in Portuguese About the Brazilian Environment

• Flávio Nakasato Cação USP https://orcid.org/0000-0003-4771-6009
• Marcos Menon José USP https://orcid.org/0000-0003-4663-4386
• André Seidel Oliveira USP https://orcid.org/0000-0001-6551-6911
• Stefano Spindola USP https://orcid.org/0000-0002-3604-9346
• Anna Helena Reali Costa USP https://orcid.org/0000-0001-7309-4528
• Fabio Gagliardi Cozman USP https://orcid.org/0000-0003-4077-4935

Resumo

The challenge of climate change and biome conservation is one of the most pressing issues of our time—particularly in Brazil, where key environmental reserves are located. Given the availability of large textual databases on ecological themes, it is natural to resort to question answering (QA) systems to increase social awareness and understanding about these topics. In this work, we introduce multiple QA systems that combine in novel ways the BM25 algorithm, a sparse retrieval technique, with PTT5, a pre-trained state-of-the-art language model. Our QA systems focus on the Portuguese language, thus offering resources not found elsewhere in the literature. As training data, we collected questions from open-domain datasets, as well as content from the Portuguese Wikipedia and news from the press. We thus contribute with innovative architectures and novel applications, attaining an F1-score of 36.2 with our best model.

Palavras-chave: Question answering, Environment in Brazil, Natural language processing in Portuguese