HCTI at SemEval-2017 Task 1: Use convolutional neural network to evaluate Semantic Textual Similarity

Abstract

This paper describes our convolutional neural network (CNN) system for the Semantic Textual Similarity (STS) task. We calculated semantic similarity score between two sentences by comparing their semantic vectors. We generated a semantic vector by max pooling over every dimension of all word vectors in a sentence. There are two key design tricks used by our system. One is that we trained a CNN to transfer GloVe word vectors to a more proper form for the STS task before pooling. Another is that we trained a fully-connected neural network (FCNN) to transfer the difference of two semantic vectors to the probability distribution over similarity scores. All hyperparameters were empirically tuned. In spite of the simplicity of our neural network system, we achieved a good accuracy and ranked 3rd on primary track of SemEval 2017.