Papers with deep Transformers

3 papers
Lipschitz Constrained Parameter Initialization for Deep Transformers (2020.acl-main)

Copied to clipboard

Challenge: Existing studies show that deep Transformers have difficulty in training even with residual connection and layer normalization.
Approach: They propose a method that leverages the Lipschitz constraint on the initialization of Transformer parameters to ease the optimization difficulties caused by its multi-layer encoder/decoder structure.
Outcome: The proposed model outperforms previous RNN/CNN models but fails to converge with the original computation order.
Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention (D19-1)

Copied to clipboard

Challenge: Existing methods to improve NLP convergence and computational overhead are limited by stacking more layers.
Approach: They propose a depth-scaled initialization method which reduces parameter variance at initialization and reduces output variance of residual connections to ease gradient back-propagation.
Outcome: The proposed method outperforms the base model on translation tasks with five translation directions while matching the decoding speed of the baseline model.
Rewiring the Transformer with Depth-Wise LSTMs (2024.lrec-main)

Copied to clipboard

Challenge: Stacking non-linear layers allows deep neural networks to model complicated functions . but residual connections within each layer fail to fuse information from previous layers effectively .
Approach: They propose a Transformer with depth-wise LSTMs connecting cascading Transformer layers and sub-layers.
Outcome: The proposed model improves in English-German / French and multilingual tasks with BLEU.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations