A review on Relation Extraction with an eye on Portuguese

摘要

The task of Relation Extraction is one of the main challenges in Natural Language Processing. We present a review of the state-of-the-art for Relation Extraction in free texts, addressing the progress and difficulties of the area, and situating Portuguese in that frame. We discuss the different aspects related to this task, considering the main computational strategies, used resources, as well as the evaluation methods applied. We also give special attention to the literature for Portuguese tools, which need further progress. On the best of our knowledge, this is the first comprehensive survey on Relation Extraction to include the state of the work done for Portuguese.