DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment

Abstract

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.

Accepted at BRACIS 2021

References in corpus (7)

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• REALM: Retrieval-Augmented Language Model Pre-Training
• Analyzing Sustainability Reports Using Natural Language Processing
• CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims
• ClimaText: A Dataset for Climate Change Topic Detection
• Pirá: A Bilingual Portuguese-English Dataset for Question-Answering about the Ocean
• PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data

Cited by in corpus (2)

• Integrating question answering and text-to-SQL in Portuguese
• Question Answering with Texts and Tables through Deep Reinforcement Learning