ECNU at SemEval-2016 task 1: Leveraging word embedding from macro and micro views to boost performance for semantic textual similarity

Abstract

This paper presents our submissions for semantic textual similarity task in SemEval 2016. Based on several traditional features (i.e., string-based, corpus-based, machine translation similarity and alignment metrics), we leverage word embedding from macro (i.e., first get representation of sentence, then measure the similarity of sentence pair) and micro views (i.e., measure the similarity of word pairs separately) to boost performance. Due to the various domains of training data and test data, we adopt three different strategies: 1) U-SEVEN: an unsupervised model, which utilizes seven straight-forward metrics; 2) S1-All: using all available dataset-s; 3) S2: selecting the most similar training sets for each test set. Results on test sets show that the unified supervised model (i.e., S1-All) achieves the best averaged performance with a mean correlation of 75.07%.