scholarly journals A Weakly Supervised Learning Framework for Detecting Social Anxiety and Depression

2018 ◽  
Vol 2 (2) ◽  
pp. 1-26 ◽  
Author(s):  
Asif Salekin ◽  
Jeremy W. Eberle ◽  
Jeffrey J. Glenn ◽  
Bethany A. Teachman ◽  
John A. Stankovic
Keyword(s):  
Social Anxiety ◽  
Supervised Learning ◽  
Anxiety And Depression ◽  
Weakly Supervised Learning ◽  
Learning Framework ◽  
Weakly Supervised

scholarly journals Tag, Copy or Predict: A Unified Weakly-Supervised Learning Framework for Visual Information Extraction using Sequences

2021 ◽  
Author(s):  
Jiapeng Wang ◽  
Tianwei Wang ◽  
Guozhi Tang ◽  
Lianwen Jin ◽  
Weihong Ma ◽  
...  
Keyword(s):  
Information Extraction ◽  
Supervised Learning ◽  
Visual Information ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Input Sequence ◽  
Time Step ◽  
Weakly Supervised Learning ◽  
Learning Framework ◽  
Weakly Supervised

Visual information extraction (VIE) has attracted increasing attention in recent years. The existing methods usually first organized optical character recognition (OCR) results in plain texts and then utilized token-level category annotations as supervision to train a sequence tagging model. However, it expends great annotation costs and may be exposed to label confusion, the OCR errors will also significantly affect the final performance. In this paper, we propose a unified weakly-supervised learning framework called TCPNet (Tag, Copy or Predict Network), which introduces 1) an efficient encoder to simultaneously model the semantic and layout information in 2D OCR results, 2) a weakly-supervised training method that utilizes only sequence-level supervision; and 3) a flexible and switchable decoder which contains two inference modes: one (Copy or Predict Mode) is to output key information sequences of different categories by copying a token from the input or predicting one in each time step, and the other (Tag Mode) is to directly tag the input sequence in a single forward pass. Our method shows new state-of-the-art performance on several public benchmarks, which fully proves its effectiveness.

scholarly journals Weakly Supervised Learning Creates a Fusion of Modeling Cultures

2021 ◽  
Vol 7 (1) ◽  
pp. 203-211
Author(s):  
Chengliang Tang ◽  
Gan Yuan ◽  
Tian Zheng
Keyword(s):  
Supervised Learning ◽  
Weakly Supervised Learning ◽  
Weakly Supervised

Weakly Supervised Learning through Rank-based Contextual Measures

2021 ◽  
Author(s):  
Joao Gabriel Camacho Presotto ◽  
Lucas Pascotti Valem ◽  
Nikolas Gomes de Sa ◽  
Daniel Carlos Guimaraes Pedronette ◽  
Joao Paulo Papa
Keyword(s):  
Supervised Learning ◽  
Weakly Supervised Learning ◽  
Weakly Supervised
Sign in / Sign up

Export Citation Format

Share Document