INESC-ID@ASSIN: Medição de Similaridade Semântica e Reconhecimento de Inferência Textual

Abstract

In this article we present INESC-ID@ASSIN, a system that competed in the 2016 joint evaluation effort entitled Avaliacao de Similaridade Semântica e Inferencia Textual (ASSIN), in the tasks of semantic similarity and textual entailment recognition. INESC-ID@ASSIN addresses the problem of detecting sentence similarity as a regression task, and it addresses textual entailment as a classification task. Although INESC-ID@ASSIN relies mainly on simple lexical features for detecting paraphrases and recognizing textual entailment, promising results were achieved in this joint evaluation.