paper-with-me

홈 › Papers

Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding

2021-09-03 · EMNLP 2021 11 · YingMei Guo, Linjun Shou, Jian Pei, Ming Gong, Mingxing Xu, Zhiyong Wu, Daxin Jiang

Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource target languages, the augmented data sets are often noisy, and thus impede the performance of SLU models. In this paper we focus on mitigating noise in augmented data. We develop a denoising training approach. Multiple models are trained with data produced by various augmented methods. Those models provide supervision signals to each other. The experimental results show that our method outperforms the existing state of the art by 3.05 and 4.24 percentage points on two benchmark datasets, respectively. The code will be made open sourced on github.

📄 PDF Abstract BibTeX arXiv:2109.01583

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDenoisingSpoken Language Understanding

Similar Papers 제목 키워드 기반

Human-Guided Column Networks: Augmenting Deep Learning with Advice

2019-05-01 · ICLR 2019 5 · Mayukh Das, Yang Yu, Devendra Singh Dhami, Gautam Kunapuli 외

While extremely successful in several applications, especially with low-level representations; sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most…

Deep Learning

Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice

2019-04-15 · Mayukh Das, Yang Yu, Devendra Singh Dhami, Gautam Kunapuli 외

Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are …

Adapt, Agree, Aggregate: Semi-Supervised Ensemble Labeling for Graph Convolutional Networks

2025-03-22 · Maryam Abdolali, Romina Zakerian, Behnam Roshanfekr, Fardin Ayar 외

In this paper, we propose a novel framework that combines ensemble learning with augmented graph structures to improve the performance and robustness of semi-supervised node classification in graphs. By creating multiple…

Ensemble LearningNode ClassificationPseudo Label

Learnable Sequence Augmenter for Triplet Contrastive Learning in Sequential Recommendation

2025-03-26 · Wei Wang, Yujie Lin, Jianli Zhao, Moyan Zhang 외

Most existing contrastive learning-based sequential recommendation (SR) methods rely on random operations (e.g., crop, reorder, and substitute) to generate augmented sequences. These methods often struggle to create posi…

Contrastive LearningSelf-Supervised LearningSequential RecommendationTriplet

Attention-augmented Spatio-Temporal Segmentation for Land Cover Mapping

2021-05-02 · Rahul Ghosh, Praveen Ravirathinam, Xiaowei Jia, Chenxi Lin 외

The availability of massive earth observing satellite data provide huge opportunities for land use and land cover mapping. However, such mapping effort is challenging due to the existence of various land cover classes, n…