paper-with-me

홈 › Papers

Effective Data Augmentation for Sentence Classification Using One VAE per Class

2022-10-01 · COLING 2022 10 · Frédéric Piedboeuf, Philippe Langlais

In recent years, data augmentation has become an important field of machine learning. While images can use simple techniques such as cropping or rotating, textual data augmentation needs more complex manipulations to ensure that the generated examples are useful. Variational auto-encoders (VAE) and its conditional variant the Conditional-VAE (CVAE) are often used to generate new textual data, both relying on a good enough training of the generator so that it doesn’t create examples of the wrong class. In this paper, we explore a simpler way to use VAE for data augmentation: the training of one VAE per class. We show on several dataset sizes, as well as on four different binary classification tasks, that it systematically outperforms other generative data augmentation techniques.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationData AugmentationSentenceSentence Classification

Similar Papers 제목 키워드 기반

Improving Sentence Classification by Multilingual Data Augmentation and Consensus Learning

2020-10-01 · CCL 2020 10 · Yanfei Wang, Yangdong Chen, Yuejie Zhang

Neural network based models have achieved impressive results on the sentence classification task. However, most of previous work focuses on designing more sophisticated network or effective learning paradigms on monoling…

ClassificationData AugmentationMachine TranslationSentence+2

Augmenting Data with Mixup for Sentence Classification: An Empirical Study

2019-05-22 · Hongyu Guo, Yongyi Mao, Richong Zhang

Mixup, a recent proposed data augmentation method through linearly interpolating inputs and modeling targets of random samples, has demonstrated its capability of significantly improving the predictive accuracy of the st…

ClassificationData AugmentationGeneral Classificationimage-classification+5

DMix: Distance Constrained Interpolative Mixup

2021-11-01 · EMNLP (MRL) 2021 11 · Ramit Sawhney, Megh Thakkar, Shrey Pandit, Debdoot Mukherjee 외

Interpolation-based regularisation methods have proven to be effective for various tasks and modalities. Mixup is a data augmentation method that generates virtual training samples from convex combinations of individual …

ClassificationData AugmentationSentenceSentence Classification

AMR-DA: Data Augmentation by Abstract Meaning Representation

2022-05-01 · Findings (ACL) 2022 5 · Ziyi Shou, Yuxin Jiang, Fangzhen Lin

Abstract Meaning Representation (AMR) is a semantic representation for NLP/NLU. In this paper, we propose to use it for data augmentation in NLP. Our proposed data augmentation technique, called AMR-DA, converts a sample…

Abstract Meaning RepresentationData AugmentationSemantic Textual SimilaritySentence+4

How DDAIR you? Disambiguated Data Augmentation for Intent Recognition

2026-01-16 · Galo Castillo-López, Alexis Lombard, Nasredine Semmar, Gaël de Chalendar arxiv

Large Language Models (LLMs) are effective for data augmentation in classification tasks like intent detection. In some cases, they inadvertently produce examples that are ambiguous with regard to untargeted classes. We …

Intent RecognitionData AugmentationIntent Detection