Universal Sentence Encoder lite demo

This demo is taken from the TensorFlow Hub Universal Sentence Encoder lite colab. It shows the model's ability to group sentences by semantic similarity usings their embeddings. The matrix on the right shows self-similarity scores (dot products) between the embeddings for the sentences on the left. The redder the cell, the higher the similarity score.
Loading the model...

Universal Sentence Encoder QnA demo

Loading the model...

Encode Question and Answers


How are you feeling today?

Answer 1

I'm not feeling very well.

Answer 2

Beijing is the capital of China.

Answer 3

You have five fingers on your hand.