UNBNLP at SemEval-2016 task 1: Semantic textual similarity: A unified framework for semantic processing and evaluation

Abstract

In this paper we consider several approaches to predicting semantic textual similarity using word embeddings, as well as methods for forming embeddings for larger units of text. We compare these methods to several baselines, and find that none of them outperform the baselines. We then consider both a supervised and unsupervised approach to combining these methods which achieve modest improvements over the baselines.