Abstract

In this paper, a novel morph-fitting procedure is proposed to injects morphological constraints generated using simple language-specific rules.

Result:

1. improves low-frequency word estimates;
2. boosts the semantic quality of the entire word vector collection

Introduction

The key idea of the fine-tuning process is to pull synonymous examples described by the constraints closer together in the transformed vector space, while at the same time pushing antonymous examples away from each other.

1. the estimation of more accurate vectors for low-frequency words which are linked to their high-frequency forms by the constructed constraints
2. specialising the distributional space to distinguish between similarity and relatedness