Photo by Joshua Sukoff on Unsplash

Using BERT Sentence Embeddings, T-SNE and K-Means to Visualize and Explore Statements

A visual method for exploring natural clusters in transcribed speeches

Process

Extracting and preprocessing the data

Creating embeddings for each sentence

Using K-Means to cluster the statements

T-SNE for dimensionality reduction

Visualizing and exploring the data with Streamlit

Data Scientist