paper-with-me

Papers

UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding

2024-06-24 · Dongyang Li, Taolin Zhang, Jiali Deng, Longtao Huang, Chengyu Wang, Xiaofeng He, Hui Xue

Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data generated by token surface matching, regardless of the global context-aware semantics of the surrounding text tokens. In this paper, we propose an Unsupervised Pseudo Semantic Data Augmentation (UniPSDA) mechanism for cross-lingual natural language understanding to enrich the training data without human interventions. Specifically, to retrieve the tokens with similar meanings for the semantic data augmentation across different languages, we propose a sequential clustering process in 3 stages: within a single language, across multiple languages of a language family, and across languages from multiple language families. Meanwhile, considering the multi-lingual knowledge infusion with context-aware semantics while alleviating computation burden, we directly replace the key constituents of the sentences with the above-learned multi-lingual family knowledge, viewed as pseudo-semantic. The infusion process is further optimized via three de-biasing techniques without introducing any neural parameters. Extensive experiments demonstrate that our model consistently improves the performance on general zero-shot cross-lingual natural language understanding tasks, including sequence classification, information extraction, and question answering.

📄 PDF Abstract BibTeX arXiv:2406.16372

Code (1)

MatNLP/UniPSDA 공식 구현 jax

Tasks

Data AugmentationNatural Language UnderstandingQuestion AnsweringRepresentation Learning

Similar Papers 제목 키워드 기반

Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding

2022-10-06 · Guofeng Mei, Cristiano Saltori, Fabio Poiesi, Jian Zhang 외

Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods. However, data augmentation is not ideal as it requires a careful selection of th…

3D Object ClassificationContrastive LearningData AugmentationPseudo Label+1

ECAP: Extensive Cut-and-Paste Augmentation for Unsupervised Domain Adaptive Semantic Segmentation

2024-03-06 · Erik Brorsson, Knut Åkesson, Lennart Svensson, Kristofer Bengtsson

We consider unsupervised domain adaptation (UDA) for semantic segmentation in which the model is trained on a labeled source dataset and adapted to an unlabeled target dataset. Unfortunately, current self-training method…

Data AugmentationDomain AdaptationSemantic SegmentationUnsupervised Domain Adaptation

Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation

2024-08-21 · CVPR 2025 1 · Chuandong Liu, Xingxing Weng, Shuguo Jiang, Pengcheng Li 외

This paper explores scene affinity (AIScene), namely intra-scene consistency and inter-scene correlation, for semi-supervised LiDAR semantic segmentation in driving scenes. Adopting teacher-student training, AIScene empl…

3D Semantic SegmentationData AugmentationLIDAR Semantic SegmentationScene Understanding+2

A Spatiotemporal Correspondence Approach to Unsupervised LiDAR Segmentation with Traffic Applications

2023-08-23 · Xiao Li, Pan He, Aotian Wu, Sanjay Ranka 외

We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios. The key idea is to leverage the spatiotemporal nature of a dynamic point cloud sequence and introdu…

ClusteringPseudo LabelRepresentation LearningSegmentation+2

Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation

2023-02-14 · Chuang Zhu, Kebin Liu, Wenqi Tang, Ke Mei 외

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such problem. Recent works show t…

Domain AdaptationPseudo LabelSemantic SegmentationSynthetic-to-Real Translation+2