paper-with-me

Papers

Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks

2020-10-05 · COLING 2020 8 · Lichao Sun, Congying Xia, Wenpeng Yin, TingTing Liang, Philip S. Yu, Lifang He

Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel level. Inspired by this line of research, in this paper, we explore i) how to apply mixup to natural language processing tasks since text data can hardly be mixed in the raw format; ii) if mixup is still effective in transformer-based learning models, e.g., BERT. To achieve the goal, we incorporate mixup to transformer-based pre-trained architecture, named "mixup-transformer", for a wide range of NLP tasks while keeping the whole end-to-end training system. We evaluate the proposed framework by running extensive experiments on the GLUE benchmark. Furthermore, we also examine the performance of mixup-transformer in low-resource scenarios by reducing the training data with a certain ratio. Our studies show that mixup is a domain-independent data augmentation technique to pre-trained language models, resulting in significant performance improvement for transformer-based models.

📄 PDF Abstract BibTeX arXiv:2010.02394

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…
WordPiece 설명 없음
Multi-Head Attention 설명 없음
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…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers

2022-10-14 · Hyeong Kyu Choi, Joonmyung Choi, Hyunwoo J. Kim

Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many saliency detectors require intense computation…

Data Augmentationimage-classificationImage Classification

MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture

2021-02-22 · Wancong Zhang, Ieshan Vaidya

MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the application of MixUp to the natural lang…

Data AugmentationNatural Language UnderstandingSentenceSentence Embedding+1

Dynamic Nonlinear Mixup with Distance-based Sample Selection

2022-10-01 · COLING 2022 10 · Shaokang Zhang, Lei Jiang, Jianlong Tan

Data augmentation with mixup has shown to be effective on the NLP tasks. Although its great success, the mixup still has shortcomings. First, vanilla mixup randomly selects one sample to generate the mixup sample for a g…

Data Augmentation

RC-Mixup: A Data Augmentation Strategy against Noisy Data for Regression Tasks

2024-05-28 · Seong-Hyeon Hwang, Minsu Kim, Steven Euijong Whang

We study the problem of robust data augmentation for regression tasks in the presence of noisy data. Data augmentation is essential for generalizing deep learning models, but most of the techniques like the popular Mixup…

Data Augmentationregression

AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformer

2023-09-22 · Leixin Yang, Yu Xiang

Mixup is an effective data augmentation method that generates new augmented samples by aggregating linear combinations of different original samples. However, if there are noises or aberrant features in the original samp…

Data AugmentationSentencetext-classificationText Classification