paper-with-me

Papers

MSMix:An Interpolation-Based Text Data Augmentation Method Manifold Swap Mixup

2023-05-31 · Mao Ye, Haitao Wang, Zheqian Chen

To solve the problem of poor performance of deep neural network models due to insufficient data, a simple yet effective interpolation-based data augmentation method is proposed: MSMix (Manifold Swap Mixup). This method feeds two different samples to the same deep neural network model, and then randomly select a specific layer and partially replace hidden features at that layer of one of the samples by the counterpart of the other. The mixed hidden features are fed to the model and go through the rest of the network. Two different selection strategies are also proposed to obtain richer hidden representation. Experiments are conducted on three Chinese intention recognition datasets, and the results show that the MSMix method achieves better results than other methods in both full-sample and small-sample configurations.

📄 PDF Abstract BibTeX arXiv:2305.19617

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationIntent Detection

Similar Papers 제목 키워드 기반

SMSMix: Sense-Maintained Sentence Mixup for Word Sense Disambiguation

2022-12-14 · Hee Suk Yoon, Eunseop Yoon, John Harvill, Sunjae Yoon 외

Word Sense Disambiguation (WSD) is an NLP task aimed at determining the correct sense of a word in a sentence from discrete sense choices. Although current systems have attained unprecedented performances for such tasks,…

Data AugmentationSentenceWord Sense Disambiguation

MSMixer: Learned Multi-Scale Temporal Mixing with Complementary Linear Shortcut for Long-Term Time Series Forecasting

2026-05-04 · Ahmed Cherif arxiv

Long-term time series forecasting requires models that simultaneously capture rapid oscillations, medium-range periodicities, and slowly evolving macro-trends from a fixed look-back window. Existing lightweight MLP-based…

Time Series Forecasting

Autoencoder Image Interpolation by Shaping the Latent Space

2020-08-04 · Alon Oring, Zohar Yakhini, Yacov Hel-Or

Autoencoders represent an effective approach for computing the underlying factors characterizing datasets of different types. The latent representation of autoencoders have been studied in the context of enabling interpo…

Data Augmentation

HypMix: Hyperbolic Interpolative Data Augmentation

2021-11-01 · EMNLP 2021 11 · Ramit Sawhney, Megh Thakkar, Shivam Agarwal, Di Jin 외

Interpolation-based regularisation methods for data augmentation have proven to be effective for various tasks and modalities. These methods involve performing mathematical operations over the raw input samples or their …

Adversarial RobustnessData Augmentation

PointMixup: Augmentation for Point Clouds

2020-08-14 · ECCV 2020 8 · Yunlu Chen, Vincent Tao Hu, Efstratios Gavves, Thomas Mensink 외

This paper introduces data augmentation for point clouds by interpolation between examples. Data augmentation by interpolation has shown to be a simple and effective approach in the image domain. Such a mixup is however …

3D Point Cloud Classification3D Point Cloud Data AugmentationData AugmentationPoint Cloud Classification