SimCompass: Using Deep Learning Word Embeddings to Assess Cross-level Similarity

Abstract

This article presents our team’s participating system at SemEval-2014 Task 3. Using a meta-learning framework, we experiment with traditional knowledgebased metrics, as well as novel corpusbased measures based on deep learning paradigms, paired with varying degrees of context expansion. The framework enabled us to reach the highest overall performance among all competing systems.