dime-xai 0.0.4a14

Explains DIETClassifier model predictions in Rasa chatbot framework.

DIME XAI 0.0.4a14 Pre-release 👽

Pre-release of DIME (Dual Interpretable Model-agnostic Explanations) mainly aimed at Explaining DIET Classifiers in RASA 2.8.X. Models.

Features 🦄

• Explain RASA DIET Classifiers using feature importance
• Generate dual feature importance scores
• No Surrogate models, thus efficient
• Total confidence drop as the feature importance score
• Explain both local and REST models
• Easy to use DIME CLI
• GUI with a dedicated server on-demand
• Generate, Store, Download, Upload, Peak DIME explanations. Read more on docs
• Full Unicode support

What's Cooking? 🍪

• DIME for Jupyter Notebooks
• Stopwords List Generation
• DIME Example Notebooks
• DIME for non-DIET text classification models

Limitations and Known Issues 🤏🏽

• Global Importance is disabled for REST models due to performance bottlenecks
• Explaining RASA models locally on Notebooks such as CoLab is not supported yet due to dependency issues
• Benchmark tests are in progress

📒 Docs: https://dime-xai.github.io
📦 PyPi: https://pypi.org/project/dime-xai/0.0.4a14/
🪵 Full Changelog: Refer the relevant GitHub branch