Enhancing Brazilian Portuguese Textual Entailment Recognition with a Hybrid Approach

Previous work on textual entailment has not fully exploited aspects of deep linguistic relations, which have been shown as containing important information for entailment identification. In this study, we present a new method to compute semantic textual similarity between two sentences. Our proposal relies on the integration of a set of deep linguistic relations, lexical aspects and distributed representational resources. We used our method with a large set of annotated data available from the ASSIN Workshop in the PROPOR 2016 event. The achieved results score among the best-known results in the literature. A perceived advantage of our approach is the ability to generate good results even with a small corpus on training tasks.