USFD at SemEval-2016 task 1: Putting different state-of-the-arts into a box

Abstract

In this paper we describe our participation in the STS Core subtask which is the determination of the monolingual semantic similarity between pair of sentences. In our participation we adapted state-of-the-art approaches from related work applied on previous STS Core subtasks and run them on the 2016 data. We investigated the performance of single methods but also the combination of them. Our results show that Convolutional Neural Networks (CNN) are superior to both the Monolingual Word Alignment and the Word2Vec approaches. The combination of all the three methods performs slightly better than using CNN only. Our results also show that the performance of our systems varies between the datasets.