From Word to Sense Embeddings: A Survey on Vector Representations of Meaning

TL;DR

This survey reviews vector-based semantic representations, focusing on transitioning from word to sense embeddings to address meaning conflation, covering techniques, evaluations, and applications.

Contribution

It provides a comprehensive overview of sense embedding methods, highlighting recent advances and analyzing key aspects like interpretability and domain adaptability.

Findings

Sense embeddings improve lexical disambiguation

Unsupervised and knowledge-based methods are both effective

Evaluation procedures vary across applications

Abstract

Over the past years, distributed semantic representations have proved to be effective and flexible keepers of prior knowledge to be integrated into downstream applications. This survey focuses on the representation of meaning. We start from the theoretical background behind word vector space models and highlight one of their major limitations: the meaning conflation deficiency, which arises from representing a word with all its possible meanings as a single vector. Then, we explain how this deficiency can be addressed through a transition from the word level to the more fine-grained level of word senses (in its broader acceptation) as a method for modelling unambiguous lexical meaning. We present a comprehensive overview of the wide range of techniques in the two main branches of sense representation, i.e., unsupervised and knowledge-based. Finally, this survey covers the main evaluation procedures and applications for this type of representation, and provides an analysis of four of its important aspects: interpretability, sense granularity, adaptability to different domains and compositionality.