A Survey of Deep Learning Methods on Semantic Similarity and Sentence Modeling

Abstract

Semantics is a research field that has gained an extensive interest recently. This survey describes recent works in the field of semantics, a part of the broader area of computational linguistics. One of the important aspects of computational linguistics is using proper methods to distribute semantics for obtaining representations of the meaning of words. This survey summarizes the latest state of the art approaches in semantics that use deep learning methods, datasets, and lexical databases, specifying semantics under two categories such as semantic similarity and sentence modeling.