Skip to content
All videos
newsDatabricks·July 26, 2023

Explainable Data Drift for NLP

Summary

This video teaches data scientists how to detect and explain data drift in unstructured NLP text using metadata, properties, and embeddings. The speaker demonstrates using the open-source library Deep Checks to identify drift, automatically extract topic clusters via GPT, and trace model performance drops.

Summary generated by brickster.ai from the video transcript.

More from Databricks