Open AccessTowards Fully Automated News Reporting in Brazilian Portuguese
Author(s) -
J.B.L.M. Campos,
André Teixeira,
Thiago Costa Ferreira,
Fábio Gagliardi Cozman,
Adriana Pagano
Publication year - 2020
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/eniac.2020.12158
Subject(s) - computer science , portuguese , publication , cover (algebra) , journalism , world wide web , domain (mathematical analysis) , point (geometry) , architecture , code (set theory) , robot , information retrieval , data science , artificial intelligence , set (abstract data type) , engineering , political science , linguistics , geography , mechanical engineering , mathematical analysis , philosophy , geometry , mathematics , archaeology , law , programming language
We introduce robot journalists that cover two pressing topics in Brazilian society: COVID-19 spread and Legal Amazon deforestation. Our approach is able to automatically analyze structured domain data, select relevant content, generate news texts and publish them on the Web. We provide a thorough description of our system architecture, report on the results of automatic evaluation, discuss some of the advantages of robot-journalism in society, and point out further steps in our work. Corpus and code are publicly available.