YujiaBao/Distributional-Signatures
"Few-shot Text Classification with Distributional Signatures" ICLR 2020
This project helps classify short texts into categories, even when you only have a few examples for each category. It takes in various text types like news articles, product reviews, or headlines, and outputs the correct category for new, unseen texts. It's ideal for data scientists, researchers, or anyone building AI models who need to categorize text efficiently with minimal labeled data.
261 stars. No commits in the last 6 months.
Use this if you need to quickly classify text into categories but have very few labeled examples available for each category.
Not ideal if you have a large amount of labeled data for all your text categories, as traditional supervised learning methods might be more straightforward.
Stars
261
Forks
54
Language
Python
License
MIT
Category
Last pushed
Dec 17, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/YujiaBao/Distributional-Signatures"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/setfit
Efficient few-shot learning with Sentence Transformers
zhongyuchen/few-shot-text-classification
Few-shot binary text classification with Induction Networks and Word2Vec weights initialization
ELM-Research/ECG-Language-Models
A Training and Evaluation Framework for ECG-Language Models (ELMs)
StefanHeng/ECG-Representation-Learning
Self-supervised pre-training for ECG representation with inspiration from transformers & computer vision
cloudera/CML_AMP_Few-Shot_Text_Classification
Perform topic classification on news articles in several limited-labeled data regimes.