paper-with-me

홈 › Papers

SegMix: A Simple Structure-Aware Data Augmentation Method

2023-11-16 · Yuxin Pei, Pushkar Bhuse, Zhengzhong Liu, Eric Xing

Interpolation-based Data Augmentation (DA) methods (Mixup) linearly interpolate the inputs and labels of two or more training examples. Mixup has more recently been adapted to the field of Natural Language Processing (NLP), mainly for sequence labeling tasks. However, such a simple adoption yields mixed or unstable improvements over the baseline models. We argue that the direct-adoption methods do not account for structures in NLP tasks. To this end, we propose SegMix, a collection of interpolation-based DA algorithms that can adapt to task-specific structures. SegMix poses fewer constraints on data structures, is robust to various hyperparameter settings, applies to more task settings, and adds little computational overhead. In the algorithm's core, we apply interpolation methods on task-specific meaningful segments, in contrast to applying them on sequences as in prior work. We find SegMix to be a flexible framework that combines rule-based DA methods with interpolation-based methods, creating interesting mixtures of DA techniques. We show that SegMix consistently improves performance over strong baseline models in Named Entity Recognition (NER) and Relation Extraction (RE) tasks, especially under data-scarce settings. Furthermore, this method is easy to implement and adds negligible training overhead.

📄 PDF Abstract BibTeX arXiv:2311.09505

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERRelation Extraction

Methods 이 논문이 사용한 방법론

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:…

Similar Papers 제목 키워드 기반

SegMix: A Simple Structure-Aware Data Augmentation Method

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Many Natural Language Processing tasks involve predicting structures, such as Syntax Parsing and Relation Extraction (RE). One central challenge in supervised structured prediction is the lack of high-quality annotated d…

Data Augmentationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+3

USegMix: Unsupervised Segment Mix for Efficient Data Augmentation in Pathology Images

2025-02-22 · Jiamu Wang, Jin Tae Kwak

In computational pathology, researchers often face challenges due to the scarcity of labeled pathology datasets. Data augmentation emerges as a crucial technique to mitigate this limitation. In this study, we introduce a…

Cancer ClassificationData AugmentationSuperpixels

Granular Ball Guided Masking: Structure-aware Data Augmentation

2025-12-24 · Shuyin Xia, Fan Chen, Dawei Dai, Meng Yang 외 arxiv

Deep learning models have achieved remarkable success in computer vision but still rely heavily on large-scale labeled data and tend to overfit when data is limited or distributions shift. Data augmentation -- particular…

Image ReconstructionImage ClassificationData Augmentation

Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation

2023-11-22 · CVPR 2024 1 · Daichi Horita, Naoto Inoue, Kotaro Kikuchi, Kota Yamaguchi 외

Content-aware graphic layout generation aims to automatically arrange visual elements along with a given content, such as an e-commerce product image. In this paper, we argue that the current layout generation approaches…

Layout GenerationRetrieval

SageMix: Saliency-Guided Mixup for Point Clouds

2022-10-13 · Sanghyeok Lee, Minkyu Jeon, Injae Kim, Yunyang Xiong 외

Data augmentation is key to improving the generalization ability of deep learning models. Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting…

3D Part Segmentation3D Point Cloud Classification3D Point Cloud Data AugmentationData Augmentation+2