Papers › Regularizing Transformers With Deep Probabilistic Layers

Regularizing Transformers With Deep Probabilistic Layers

23 Aug 2021arXiv:2108.10764archive 2025-07-28

Aurora Cobo Aguilera, Pablo Martínez Olmos, Antonio Artés-Rodríguez, Fernando Pérez-Cruz

Language models (LM) have grown with non-stop in the last decade, from sequence-to-sequence architectures to the state-of-the-art and utter attention-based Transformers. In this work, we demonstrate how the inclusion of deep generative models within BERT can bring more versatile models, able to impute missing/noisy words with richer text or even improve BLEU score. More precisely, we use a Gaussian Mixture Variational Autoencoder (GMVAE) as a regularizer layer and prove its effectiveness not only in Transformers but also in the most relevant encoder-decoder based LM, seq2seq with and without attention.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Decoder

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: GMVAE

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutGMVAELSTMLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSeq2SeqSigmoid ActivationSoftmaxTanh ActivationWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections