/seal

Systematic Error Analysis and Labeling

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

title emoji colorFrom colorTo sdk sdk_version app_file pinned license
Systematic Error Analysis and Labeling
🦭
yellow
pink
streamlit
1.10.0
app.py
false
apache-2.0

SEAL

Systematic Error Analysis and Labeling (SEAL) is an interactive tool for discovering systematic errors in NLP models via clustering on high-loss example groups and semantic labeling for interpretability of those error-groups. It supports fine-grained analytical visualization for interactively zooming into potential systematic bugs and features for crafting prompts to label those bugs semantically.

🎥 Demo screencast

Demo gif

Table of Contents

Installation

Please use python>=3.8 since some dependencies require that for installation.

git clone https://huggingface.co/spaces/nazneen/seal
cd seal
pip install --upgrade pip
pip install -r requirements.txt

Quickstart

streamlit run app.py

Running Locally

Citation