Weak Labeling of Fake News Articles with Snorkel and Snuba
-
Updated
Jun 8, 2021 - Python
Weak Labeling of Fake News Articles with Snorkel and Snuba
Python Implementation of Weakly Supervised Clustering article
Using weak supervision to perform named entity recognition and offensive language detection on r/sg comments
PyTorch implementation of the model described my MS thesis: "Weakly Supervised Visual-Textual Grounding based on Concept Similarity" (https://github.com/lparolari/master-thesis)
Weak Supervised Fake News Detection with RoBERTa, XLNet, ALBERT, XGBoost and Logistic Regression classifiers.
Weakly supervised learning framework for classification.
Fine-grained semantic indexing of biomedical literature (a Weakly-Supervised approach)
Weakly supervised RL with safety cages for autonomous highway driving
In this project, we are using Snorkel Python to work with ML algorithms with an unlabeled text dataset.
Utilizing the snorkel machine learning model to label biomimicry papers. Snorkel uses weak supervision to label large amounts of training data using programmatic labeling functions based on keyword rules.
A curated list of awesome Weak-Supervision-Sequence-Labeling (WSSL) papers, methods & resources.
An approach to curating naturally adversarial datasets.
Data labeling using weak supervision
Code accompanying the TOP paper "Predicting the Demographics of Twitter Users with Programmatic Weak Supervision".
Implementing wide variety of transformers, fine tuning as well as trying architectural variants from various research papers and blogs.
Repo accompanying the paper "Monocular spherical depth estimation with explicitly connected weak layout cues".
Add a description, image, and links to the weak-supervision topic page so that developers can more easily learn about it.
To associate your repository with the weak-supervision topic, visit your repo's landing page and select "manage topics."