glanceable-io/ordinal-log-loss
Repository of the COLING 2022 paper : Ordinal Log-Loss - A simple log-based loss function for ordinal text classification.
This project offers a specialized way to improve how AI models categorize text, especially when categories have a natural order (like movie ratings from 'negative' to 'positive'). It takes existing text data with ordered labels and helps refine the AI's learning process. The result is a more accurate model for sentiment analysis or other ordinal text classification tasks, valuable for data scientists and machine learning engineers working with natural language.
No commits in the last 6 months.
Use this if you are building or fine-tuning text classification models where your labels have a clear, meaningful order (e.g., product review ratings, severity levels, confidence scores).
Not ideal if your text classification labels are completely independent with no inherent order (e.g., classifying text into categories like 'sports,' 'finance,' or 'politics').
Stars
32
Forks
2
Language
Python
License
—
Category
Last pushed
Mar 17, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/glanceable-io/ordinal-log-loss"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HelmchenLabSoftware/Cascade
Calibrated inference of spiking from calcium ΔF/F data using deep networks
adobe/antialiased-cnns
pip install antialiased-cnns to improve stability and accuracy
KaiyangZhou/pytorch-center-loss
Pytorch implementation of Center Loss
devsisters/pointer-network-tensorflow
TensorFlow implementation of "Pointer Networks"
kimhc6028/relational-networks
Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)