paper-with-me

홈 › Papers

Pseudo-Labels Are All You Need

2022-08-19 · GermEval 2022 9 · Bogdan Kostić, Mathis Lucka, Julian Risch

Automatically estimating the complexity of texts for readers has a variety of applications, such as recommending texts with an appropriate complexity level to language learners or supporting the evaluation of text simplification approaches. In this paper, we present our submission to the Text Complexity DE Challenge 2022, a regression task where the goal is to predict the complexity of a German sentence for German learners at level B. Our approach relies on more than 220,000 pseudo-labels created from the German Wikipedia and other corpora to train Transformer-based models, and refrains from any feature engineering or any additional, labeled data. We find that the pseudo-label-based approach gives impressive results yet requires little to no adjustment to the specific task and therefore could be easily adapted to other domains and tasks.

📄 PDF Abstract BibTeX arXiv:2208.09243

Code (0)

등록된 구현이 없습니다.

Tasks

AllFeature EngineeringPseudo LabelSentenceText Simplification

Similar Papers 제목 키워드 기반

Unsupervised Clustering using Pseudo-semi-supervised Learning

2020-05-01 · ICLR 2020 1 · Divam Gupta, Ramachandran Ramjee, Nipun Kwatra, Muthian Sivathanu

In this paper, we propose a framework that leverages semi-supervised models to improve unsupervised clustering performance. To leverage semi-supervised models, we first need to automatically generate labels, called pseud…

Clustering

Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation

2022-10-18 · Jun-Kun Wang, Andre Wibisono

We consider a setting that a model needs to adapt to a new domain under distribution shifts, given that only unlabeled test samples from the new domain are accessible at test time. A common idea in most of the related wo…

Binary ClassificationDomain AdaptationTest-time Adaptation

Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation

2022-10-19 · Sebastian Scherer, Robin Schön, Rainer Lienhart

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very …

Pose EstimationPseudo LabelPseudo Label FilteringSemantic Segmentation+1

Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection

2022-07-06 · HongYu Zhou, Zheng Ge, Songtao Liu, Weixin Mao 외

To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseu…

object-detectionObject DetectionPseudo LabelSemi-Supervised Object Detection

Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation

2023-05-09 · Tianle Chen, Zheda Mai, Ruiwen Li, Wei-Lun Chao

Weakly supervised semantic segmentation (WSSS) aims to bypass the need for laborious pixel-level annotation by using only image-level annotation. Most existing methods rely on Class Activation Maps (CAM) to derive pixel-…

ObjectPseudo LabelSemantic SegmentationWeakly supervised Semantic Segmentation+1