paper-with-me

홈 › Papers

The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models

2021-06-03 · ACL 2021 5 · Ulme Wennberg, Gustav Eje Henter

Mechanisms for encoding positional information are central for transformer-based language models. In this paper, we analyze the position embeddings of existing language models, finding strong evidence of translation invariance, both for the embeddings themselves and for their effect on self-attention. The degree of translation invariance increases during training and correlates positively with model performance. Our findings lead us to propose translation-invariant self-attention (TISA), which accounts for the relative position between tokens in an interpretable fashion without needing conventional position embeddings. Our proposal has several theoretical advantages over existing position-representation approaches. Experiments show that it improves on regular ALBERT on GLUE tasks, while only adding orders of magnitude less positional parameters.

📄 PDF Abstract BibTeX arXiv:2106.01950

Code (3)

ulmewennberg/tisa 공식 구현 pytorch
MindSpore-scientific-2/code-4/tree/main/Case_TranslationInvariantAttn mindspore
MindSpore-scientific-2/code-5/tree/main/Case_TranslationInvariantAttn mindspore

Tasks

PositionTranslation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Adam 설명 없음
LAMB LAMB is a a layerwise adaptive large batch optimization technique. It provides a strategy for adapting the learning rate in large batch settings. LAMB uses…

Similar Papers 제목 키워드 기반

SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learning

2024-06-21 · Matthias Weissenbacher, Rishabh Agarwal, Yoshinobu Kawahara

An open challenge in reinforcement learning (RL) is the effective deployment of a trained policy to new or slightly different situations as well as semantically-similar environments. We introduce Symmetry-Invariant Trans…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Alias-Free ViT: Fractional Shift Invariance via Linear Attention

2025-10-26 · Hagay Michaeli, Daniel Soudry arxiv

Transformers have emerged as a competitive alternative to convnets in vision tasks, yet they lack the architectural inductive bias of convnets, which may hinder their potential performance. Specifically, Vision Transform…

Image Classification

SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks

2020-06-18 · NeurIPS 2020 12 · Fabian B. Fuchs, Daniel E. Worrall, Volker Fischer, Max Welling

We introduce the SE(3)-Transformer, a variant of the self-attention module for 3D point clouds and graphs, which is equivariant under continuous 3D roto-translations. Equivariance is important to ensure stable and predic…

Translation

Synchronous Syntactic Attention for Transformer Neural Machine Translation

2021-08-01 · ACL 2021 5 · Hiroyuki Deguchi, Akihiro Tamura, Takashi Ninomiya

This paper proposes a novel attention mechanism for Transformer Neural Machine Translation, {``}Synchronous Syntactic Attention,{''} inspired by synchronous dependency grammars. The mechanism synchronizes source-side and…

DecoderMachine TranslationTranslation

Dependency-Based Self-Attention for Transformer NMT

2019-09-01 · RANLP 2019 9 · Hiroyuki Deguchi, Akihiro Tamura, Takashi Ninomiya

In this paper, we propose a new Transformer neural machine translation (NMT) model that incorporates dependency relations into self-attention on both source and target sides, dependency-based self-attention. The dependen…

DecoderMachine TranslationNMTSemantic Role Labeling+1