Papers › Injecting Hierarchy with U-Net Transformers

Injecting Hierarchy with U-Net Transformers

16 Oct 2019arXiv:1910.10488archive 2025-07-28

David Donahue, Vladislav Lialin, Anna Rumshisky

The Transformer architecture has become increasingly popular over the past two years, owing to its impressive performance on a number of natural language processing (NLP) tasks. However, all Transformer computations occur at the level of word representations and therefore, it may be argued that Transformer models do not explicitly attempt to learn hierarchical structure which is widely assumed to be integral to language. In the present work, we introduce hierarchical processing into the Transformer model, taking inspiration from the U-Net architecture, popular in computer vision for its hierarchical view of natural images. We empirically demonstrate that the proposed architecture outperforms both the vanilla Transformer and some strong baselines in the domain of chit-chat dialogue.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

text-machine-lab/HierarchicalTransformer officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
Guitaricet/unet_transformer_translation mentioned on GitHubpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Machine Translation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEConcatenated Skip ConnectionConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMax PoolingMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformerU-Net

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