Extracting and Structuring Open Relations from Portuguese Text

摘要

The task of Open Relation Extraction from texts faces many challenges, considering the required linguistic knowledge and the sophistication of the language processing techniques employed. This paper presents the extraction and structuring of open relations between named entities from Portuguese texts. We apply the Conditional Random Fields model for the extraction of relation descriptors between named entities belonging to Person, Place and Organisation categories. A 0.64 of F-measure was reached as a result. To make better sense of the output, we structure the extracted relation descriptors using mining configurations.