Posterior Sampling of Probabilistic Word Embeddings
This work addresses the need for reliable uncertainty estimation in word embeddings for natural language processing applications, offering a scalable solution that is incremental over prior Bayesian methods.
The authors tackled the problem of quantifying uncertainty in word embeddings, proposing scalable Gibbs sampling and Laplace approximation methods that correctly estimate uncertainties, unlike existing Bayesian approaches, and demonstrated that posterior mean embeddings improve hold-out likelihood over MAP estimates, especially for smaller sample sizes.
Quantifying uncertainty in word embeddings is crucial for reliable inference from textual data. However, existing Bayesian methods such as Hamiltonian Monte Carlo (HMC) and mean-field variational inference (MFVI) are either computationally infeasible for large data or rely on restrictive assumptions. We propose a scalable Gibbs sampler using Polya-Gamma augmentation as well as Laplace approximation and compare them with MFVI and HMC for word embeddings. In addition, we address non-identifiability in word embeddings. Our Gibbs sampler and HMC correctly estimate uncertainties, while MFVI does not, and Laplace approximation only does so on large sample sizes, as expected. Applying the Gibbs sampler to the US Congress and the Movielens datasets, we demonstrate the feasibility on larger real data. Finally, as a result of having draws from the full posterior, we show that the posterior mean of word embeddings improves over maximum a posteriori (MAP) estimates in terms of hold-out likelihood, especially for smaller sampling sizes, further strengthening the need for posterior sampling of word embeddings.