Learning What’s in a Name with Graphical Models

Presented at VISxAI at IEEE VIS 2023

Made in 2023 with D3, React, and Python

An in-depth account of graphical models and their natural fit for named entity recognition — the task of extracting names (of people, organizations, locations, etc.) from a body of text.

Custom-built network visualizations help bring important concepts to life. Readers can explore alternative parameter configurations and test their understanding of the material.

Tiled scatter plots
Emission paths of a Hidden Markov Model
Transition paths of a Hidden Markov Model
Named entity predictions from HMM, MEMM, and CRF models
Breakdown of how to calculate the transition probability in a Maximum-Entropy Markov Model