The Interplay of Semantics and Morphology in Word Embeddings

TL;DR

This paper investigates how different linguistic properties like surface form, lemma, and morphological tags influence the ability of word embeddings to capture semantic and morphological similarities, providing insights into their interplay.

Contribution

It systematically compares models trained on various property subsets to analyze their effects on semantic and morphological representation quality.

Findings

Models using morphological tags improve morphological similarity detection.

Surface form information enhances semantic similarity performance.

Insights into the relationship between morphology and semantics in embeddings.

Abstract

We explore the ability of word embeddings to capture both semantic and morphological similarity, as affected by the different types of linguistic properties (surface form, lemma, morphological tag) used to compose the representation of each word. We train several models, where each uses a different subset of these properties to compose its representations. By evaluating the models on semantic and morphological measures, we reveal some useful insights on the relationship between semantics and morphology.