Skip to content

Files

Latest commit

author
Kangyi Zhang
Apr 16, 2020
737c722 · Apr 16, 2020

History

History

universal-sentence-encoder

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
Dec 20, 2019
Feb 15, 2019
Jan 10, 2020
Feb 7, 2019
May 13, 2019
Mar 27, 2020
Oct 25, 2019
Apr 16, 2020
Jul 11, 2019
Feb 4, 2019
Feb 4, 2019
Oct 25, 2019
Apr 16, 2020

Universal Sentence Encoder lite

The Universal Sentence Encoder (Cer et al., 2018) (USE) is a model that encodes text into 512-dimensional embeddings. These embeddings can then be used as inputs to natural language processing tasks such as sentiment classification and textual similarity analysis.

This module is a TensorFlow.js GraphModel converted from the USE lite (module on TFHub), a lightweight version of the original. The lite model is based on the Transformer (Vaswani et al, 2017) architecture, and uses an 8k word piece vocabulary.

In this demo we embed six sentences with the USE, and render their self-similarity scores in a matrix (redder means more similar):

selfsimilarity

The matrix shows that USE embeddings can be used to cluster sentences by similarity.

The sentences (taken from the TensorFlow Hub USE lite colab):

  1. I like my phone.
  2. Your cellphone looks great.
  3. How old are you?
  4. What is your age?
  5. An apple a day, keeps the doctors away.
  6. Eating strawberries is healthy.

Installation

Using yarn:

$ yarn add @tensorflow/tfjs @tensorflow-models/universal-sentence-encoder

Using npm:

$ npm install @tensorflow/tfjs @tensorflow-models/universal-sentence-encoder

Usage

To import in npm:

const use = require('@tensorflow-models/universal-sentence-encoder');

or as a standalone script tag:

<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs"></script>
<script src="https://cdn.jsdelivr.net/npm/@tensorflow-models/universal-sentence-encoder"></script>

Then:

// Load the model.
use.load().then(model => {
  // Embed an array of sentences.
  const sentences = [
    'Hello.',
    'How are you?'
  ];
  model.embed(sentences).then(embeddings => {
    // `embeddings` is a 2D tensor consisting of the 512-dimensional embeddings for each sentence.
    // So in this example `embeddings` has the shape [2, 512].
    embeddings.print(true /* verbose */);
  });
});

To use the Tokenizer separately:

use.loadTokenizer().then(tokenizer => {
  tokenizer.encode('Hello, how are you?'); // [341, 4125, 8, 140, 31, 19, 54]
});