alinlab/MASKER
MASKER: Masked Keyword Regularization for Reliable Text Classification (AAAI 2021)
This tool helps data scientists and machine learning engineers build more reliable text classification models. It takes your labeled text datasets (like movie reviews categorized as positive or negative) and produces a text classification model that is less prone to making decisions based on irrelevant or biased keywords. The goal is a model that accurately classifies text, even when facing new, slightly different data.
No commits in the last 6 months.
Use this if you need to train text classification models that are robust and make reliable predictions, avoiding biases from specific keywords in your training data.
Not ideal if you are looking for a simple, out-of-the-box text classification solution without needing to dive into advanced model training techniques.
Stars
54
Forks
11
Language
Python
License
—
Category
Last pushed
Oct 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/alinlab/MASKER"
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...
princeton-nlp/CoFiPruning
[ACL 2022] Structured Pruning Learns Compact and Accurate Models https://arxiv.org/abs/2204.00408
kssteven418/LTP
[KDD'22] Learned Token Pruning for Transformers
georgian-io/Transformers-Domain-Adaptation
:no_entry: [DEPRECATED] Adapt Transformer-based language models to new text domains