snowood1/BERT-ENN
Uncertainty-Aware Reliable Text Classification (KDD 2021)
This project helps data scientists and machine learning engineers create more reliable text classification models. It takes your labeled text data and outputs a classification model that not only categorizes text but also identifies when it encounters text examples that are outside of its training distribution, preventing misclassifications on unfamiliar data. This ensures your text classification systems provide trustworthy results.
No commits in the last 6 months.
Use this if you need to build text classification systems that can confidently identify and flag text it's not familiar with, rather than guessing incorrectly.
Not ideal if you are looking for a plug-and-play solution without needing to train and evaluate machine learning models yourself.
Stars
18
Forks
8
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 04, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/snowood1/BERT-ENN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thunlp/OpenAttack
An Open-Source Package for Textual Adversarial Attack.
thunlp/TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
jind11/TextFooler
A Model for Natural Language Attack on Text Classification and Inference
thunlp/OpenBackdoor
An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
thunlp/SememePSO-Attack
Code and data of the ACL 2020 paper "Word-level Textual Adversarial Attacking as Combinatorial...