Samsung Poland NLP Team at SemEval-2016 Task 1: Necessity for diversity; combining recursive autoencoders, WordNet and ensemble methods to measure semantic similarity

This paper describes our proposed solutions designed for a STS core track within the SemEval 2016 English Semantic Textual Similarity (STS) task. Our method of similarity detection combines recursive autoencoders with a WordNet award-penalty system that accounts for semantic relatedness, and an SVM classifier, which produces the final score from similarity matrices. This solution is further supported by an ensemble classifier, combining an aligner with a bi-directional Gated Recurrent Neural Network and additional features, which then performs Linear Support Vector Regression to determine another set of scores.