paper-with-me

Papers

TensorCoder: Dimension-Wise Attention via Tensor Representation for Natural Language Modeling

2020-07-28 · Shuai Zhang, Peng Zhang, Xindian Ma, Junqiu Wei, Ningning Wang, Qun Liu

Transformer has been widely-used in many Natural Language Processing (NLP) tasks and the scaled dot-product attention between tokens is a core module of Transformer. This attention is a token-wise design and its complexity is quadratic to the length of sequence, limiting its application potential for long sequence tasks. In this paper, we propose a dimension-wise attention mechanism based on which a novel language modeling approach (namely TensorCoder) can be developed. The dimension-wise attention can reduce the attention complexity from the original $O(N^2d)$ to $O(Nd^2)$, where $N$ is the length of the sequence and $d$ is the dimensionality of head. We verify TensorCoder on two tasks including masked language modeling and neural machine translation. Compared with the original Transformer, TensorCoder not only greatly reduces the calculation of the original model but also obtains improved performance on masked language modeling task (in PTB dataset) and comparable performance on machine translation tasks.

📄 PDF Abstract BibTeX arXiv:2008.01547

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMachine TranslationMasked Language ModelingTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Deep Attention Neural Tensor Network for Visual Question Answering

2018-09-01 · ECCV 2018 9 · Yalong Bai, Jianlong Fu, Tiejun Zhao, Tao Mei

Visual question answering (VQA) has drawn great attention in cross-modal learning problems, which enables a machine to answer a natural language question given a reference image. Significant progress has been made by lea…

Deep AttentionQuestion AnsweringTripletVisual Question Answering+1

Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together

2018-05-02 · NAACL 2019 6 · Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang 외

Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, their expressive power and performance can…

Tensor Low-Rank Reconstruction for Semantic Segmentation

2020-08-02 · ECCV 2020 8 · Wanli Chen, Xinge Zhu, Ruoqi Sun, Junjun He 외

Context information plays an indispensable role in the success of semantic segmentation. Recently, non-local self-attention based methods are proved to be effective for context information collection. Since the desired c…

Semantic Segmentation

Variational Structured Attention Networks for Dense Pixel-Wise Prediction

2021-01-01 · Guanglei Yang, Paolo Rota, Xavier Alameda-Pineda, Dan Xu 외

State-of-the-art performances in dense pixel-wise prediction tasks are obtained with specifically designed convolutional networks. These models often benefit from attention mechanisms that allow better learning of deep r…

Prediction

TESA: Tensor Element Self-Attention via Matricization

2020-06-01 · CVPR 2020 6 · Francesca Babiloni, Ioannis Marras, Gregory Slabaugh, Stefanos Zafeiriou

Representation learning is a fundamental part of modern computer vision, where abstract representations of data are encoded as tensors optimized to solve problems like image segmentation and inpainting. Recently, self-at…

Image InpaintingImage SegmentationInstance SegmentationRepresentation Learning+1