Generating Sense Embeddings for Syntactic and Semantic Analogy for Portuguese

TL;DR

This paper introduces sense embeddings for Portuguese that capture different meanings of ambiguous words, outperforming traditional word vectors in analogy tasks and enhancing NLP applications.

Contribution

It presents the first Portuguese sense embeddings, demonstrating their superiority over traditional vectors in syntactic and semantic analogy evaluations.

Findings

Sense vectors outperform traditional word vectors in analogy tasks.

The generated resources improve NLP task performance in Portuguese.

First experiments of sense embeddings for Portuguese are reported.

Abstract

Word embeddings are numerical vectors which can represent words or concepts in a low-dimensional continuous space. These vectors are able to capture useful syntactic and semantic information. The traditional approaches like Word2Vec, GloVe and FastText have a strict drawback: they produce a single vector representation per word ignoring the fact that ambiguous words can assume different meanings. In this paper we use techniques to generate sense embeddings and present the first experiments carried out for Portuguese. Our experiments show that sense vectors outperform traditional word vectors in syntactic and semantic analogy tasks, proving that the language resource generated here can improve the performance of NLP tasks in Portuguese.