paper-with-me

Papers

Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection

2020-10-29 · EMNLP 2020 11 · Shaolei Wang, Zhongyuan Wang, Wanxiang Che, Ting Liu

Most existing approaches to disfluency detection heavily rely on human-annotated corpora, which is expensive to obtain in practice. There have been several proposals to alleviate this issue with, for instance, self-supervised learning techniques, but they still require human-annotated corpora. In this work, we explore the unsupervised learning paradigm which can potentially work with unlabeled text corpora that are cheaper and easier to obtain. Our model builds upon the recent work on Noisy Student Training, a semi-supervised learning approach that extends the idea of self-training. Experimental results on the commonly used English Switchboard test set show that our approach achieves competitive performance compared to the previous state-of-the-art supervised systems using contextualized word embeddings (e.g. BERT and ELECTRA).

📄 PDF Abstract BibTeX arXiv:2010.15360

Code (1)

scir-zywang/self-training-self-supervised-disfluency 공식 구현 pytorch

Tasks

Self-Supervised LearningWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Stochastic Depth Stochastic Depth aims to shrink the depth of a network during training, while keeping it unchanged during testing. This is achieved by randomly dropping entire…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
WordPiece 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

MSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR

2025-05-30 · Dimitrios Damianos, Georgios Paraskevopoulos, Alexandros Potamianos

In this work, we investigate the Meta PL unsupervised domain adaptation framework for Automatic Speech Recognition (ASR). We introduce a Multi-Stage Domain Adaptation pipeline (MSDA), a sample-efficient, two-stage adapta…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain AdaptationSelf-Supervised Learning+3

Geometric Unsupervised Domain Adaptation for Semantic Segmentation

2021-03-30 · ICCV 2021 10 · Vitor Guizilini, Jie Li, Rares Ambrus, Adrien Gaidon

Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world…

Depth EstimationDepth PredictionDomain AdaptationMonocular Depth Estimation+3

ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation

2022-12-01 · ICCV 2021 10 · Octave Mariotti, Oisin Mac Aodha, Hakan Bilen

Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale. I…

Image ReconstructionSelf-Supervised LearningViewpoint Estimation

Self supervised contrastive learning for digital histopathology

2020-11-27 · Ozan Ciga, Tony Xu, Anne L. Martel

Unsupervised learning has been a long-standing goal of machine learning and is especially important for medical image analysis, where the learning can compensate for the scarcity of labeled datasets. A promising subclass…

Contrastive LearningMedical Image AnalysisSelf-Supervised Learning

SelfAct: Personalized Activity Recognition based on Self-Supervised and Active Learning

2023-04-19 · Luca Arrotta, Gabriele Civitarese, Samuele Valente, Claudio Bettini

Supervised Deep Learning (DL) models are currently the leading approach for sensor-based Human Activity Recognition (HAR) on wearable and mobile devices. However, training them requires large amounts of labeled data whos…

Active LearningActivity RecognitionHuman Activity Recognition