yzhan238/PIEClass
The source code used for paper "PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training", published in EMNLP 2023.
This is a machine learning framework for academic researchers focused on natural language processing. It takes in text datasets and outputs a text classification model, even when only a small amount of labeled data is available. This tool is designed for NLP researchers and PhD students experimenting with weakly-supervised text classification methods.
No commits in the last 6 months.
Use this if you are an NLP researcher working on weakly-supervised text classification and need to experiment with prompting and iterative ensemble training techniques.
Not ideal if you are a practitioner looking for an off-the-shelf text classification solution without deep machine learning expertise.
Stars
12
Forks
1
Language
Python
License
—
Category
Last pushed
Oct 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yzhan238/PIEClass"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
airaria/TextBrewer
A PyTorch-based knowledge distillation toolkit for natural language processing
sunyilgdx/NSP-BERT
The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original...
kssteven418/LTP
[KDD'22] Learned Token Pruning for Transformers
princeton-nlp/CoFiPruning
[ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408
georgian-io/Transformers-Domain-Adaptation
:no_entry: [DEPRECATED] Adapt Transformer-based language models to new text domains