Towards a Pragmatic Open Information Extraction for Portuguese Text - ICEIS17, InferPortOIE and PragmaticOIE on IberLEF Rafael Glauber, Daniela Barreiro Claro  [0000-0001-8586-1042] , and Cleiton Fernando Lima Sena FORMAS Research Group, LaSiD/DCC/UFBA Federal University of Bahia, Brazil rglauber@dcc.ufba.br, dclaro@ufba.br,cflsena2@gmail.com http://formas.ufba.br Abstract. This paper describes the participation of the FORMAS re- search group with the systems ICEIS17, InferPortOIE, and Pragmati- cOIE in the Iberian Languages Evaluation Forum 2019. Our activities have focused on the “General Open Relation Extraction” task of relation extraction for Portuguese texts. We present our choices on this challenge, as well as the performance of our systems and their results. Keywords: Shared Task · Open Information Extraction · Relation Ex- traction · Pragmatic Open IE · Inference Extraction. 1 Introduction Information Extraction (IE) emerged as a research area to identify relevant pat- terns in large quantities of textual documents [10]. The tasks employed by IE were carried out in specific, homogeneous, and previously established domains. As a consequence, a first challenge was to scale traditional IE to the Web [1]. However, some drawbacks were considered, such as low coverage of relations and human intervention for new relations. Open Information Extraction (Open IE) comes up to extract information freely from texts and scales for the Web [6]. While the quantity and diversity of textual content grow on the Web, the tradi- tional IE tools have low coverage in this scenario [3]. In the study conducted by [1], the authors proposed a new approach called Open Information Extraction (Open IE) that extracts facts from a sentence in the following triple format: triple =(arg1, rel, arg2) (1) Copyright c  2019 for this paper by its authors. Use permitted under Creative Com- mons License Attribution 4.0 International (CC BY 4.0). IberLEF 2019, 24 Septem- ber 2019, Bilbao, Spain.