Prior latent distribution comparison for the RNN Variational Autoencoder in low-resource language modeling

Yevhen Kostiuk, Mykola Lukashchuk, Alexander Gelbukh, Grigori Sidorov

Producción científica: Contribución a una revistaArtículorevisión exhaustiva

Resumen

Probabilistic Bayesian methods are widely used in the machine learning domain. Variational Autoencoder (VAE) is a common architecture for solving the Language Modeling task in a self-supervised way. VAE consists of a concept of latent variables inside the model. Latent variables are described as a random variable that is fit by the data. Up to now, in the majority of cases, latent variables are considered normally distributed. The normal distribution is a well-known distribution that can be easily included in any pipeline. Moreover, the normal distribution is a good choice when the Central Limit Theorem (CLT) holds. It makes it effective when one is working with i.i.d. (independent and identically distributed) random variables. However, the conditions of CLT in Natural Language Processing are not easy to check. So, the choice of distribution family is unclear in the domain. This paper studies the priors selection impact of continuous distributions in the Low-Resource Language Modeling task with VAE. The experiment shows that there is a statistical difference between the different priors in the encoder-decoder architecture. We showed that family distribution hyperparameter is important in the Low-Resource Language Modeling task and should be considered for the model training.

Idioma originalInglés
Páginas (desde-hasta)4541-4549
Número de páginas9
PublicaciónJournal of Intelligent and Fuzzy Systems
Volumen42
N.º5
DOI
EstadoPublicada - 2022

Huella

Profundice en los temas de investigación de 'Prior latent distribution comparison for the RNN Variational Autoencoder in low-resource language modeling'. En conjunto forman una huella única.

Citar esto