The Interplay of Semantics and Morphology in Word Embeddings
This work addresses the problem of understanding linguistic representation in embeddings for NLP researchers, but it is incremental as it builds on existing methods without major breakthroughs.
The study investigated how word embeddings capture semantic and morphological similarity by training models with different linguistic properties, revealing insights into their interplay.
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.