Bayesian Neural Word Embedding

TL;DR

This paper introduces a scalable Bayesian neural word embedding method using Variational Bayes, demonstrating competitive performance on word analogy and similarity tasks across multiple datasets.

Contribution

It presents a novel Bayesian neural embedding algorithm for word representations, leveraging Variational Bayes for improved scalability and probabilistic modeling.

Findings

Competitive performance on word analogy tasks

Effective on multiple datasets

Scalable Bayesian approach

Abstract

Recently, several works in the domain of natural language processing presented successful methods for word embedding. Among them, the Skip-Gram with negative sampling, known also as word2vec, advanced the state-of-the-art of various linguistics tasks. In this paper, we propose a scalable Bayesian neural word embedding algorithm. The algorithm relies on a Variational Bayes solution for the Skip-Gram objective and a detailed step by step description is provided. We present experimental results that demonstrate the performance of the proposed algorithm for word analogy and similarity tasks on six different datasets and show it is competitive with the original Skip-Gram method.