ChaosCodes/UNTL
EMNLP'2022: Unsupervised Non-transferable Text Classification
This project helps researchers and machine learning engineers classify text documents without needing to manually label data for each new domain. It takes unlabeled text data from a specific domain and outputs a trained model capable of classifying that text. This is designed for academics and practitioners working on text classification problems who want to avoid the time and cost of extensive data annotation.
No commits in the last 6 months.
Use this if you need to classify text data in a new domain but lack the resources or time to create a large dataset of labeled examples.
Not ideal if you already have ample labeled data for your target domain or if you require an explanation for why certain text is classified in a particular way.
Stars
9
Forks
—
Language
Python
License
MIT
Category
Last pushed
Nov 01, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ChaosCodes/UNTL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kk7nc/HDLTex
HDLTex: Hierarchical Deep Learning for Text Classification
richliao/textClassifier
Text classifier for Hierarchical Attention Networks for Document Classification
RandolphVI/Hierarchical-Multi-Label-Text-Classification
The code of CIKM'19 paper《Hierarchical Multi-label Text Classification: An Attention-based...
yumeng5/LOTClass
[EMNLP 2020] Text Classification Using Label Names Only: A Language Model Self-Training Approach
sgrvinod/a-PyTorch-Tutorial-to-Text-Classification
Hierarchical Attention Networks | a PyTorch Tutorial to Text Classification