Semantic Representations of Word Senses and Concepts

TL;DR

This paper discusses the importance of representing individual word senses and concepts in NLP to overcome limitations of traditional word embeddings, highlighting recent advances and their broad applicability.

Contribution

It reviews recent developments in semantic representations of word senses and concepts, emphasizing their advantages and potential for improving NLP tasks.

Findings

Sense-level representations improve NLP performance

Models can be applied to phrases and sentences

Recent experimental results show significant gains

Abstract

Representing the semantics of linguistic items in a machine-interpretable form has been a major goal of Natural Language Processing since its earliest days. Among the range of different linguistic items, words have attracted the most research attention. However, word representations have an important limitation: they conflate different meanings of a word into a single vector. Representations of word senses have the potential to overcome this inherent limitation. Indeed, the representation of individual word senses and concepts has recently gained in popularity with several experimental results showing that a considerable performance improvement can be achieved across different NLP applications upon moving from word level to the deeper sense and concept levels. Another interesting point regarding the representation of concepts and word senses is that these models can be seamlessly applied to other linguistic items, such as words, phrases and sentences.