---
license: apache-2.0
library_name: tfhub
language: en
tags:
- text
- sentence-similarity
- use
- universal-sentence-encoder
- dan
- tensorflow
---

## Model name: universal-sentence-encoder
## Description adapted from [TFHub](https://tfhub.dev/google/universal-sentence-encoder/4)

# Overview

The Universal Sentence Encoder encodes text into high-dimensional vectors that can be used for text classification, semantic similarity, clustering and other natural language tasks.

The model is trained and optimized for greater-than-word length text, such as sentences, phrases or short paragraphs. It is trained on a variety of data sources and a variety of tasks with the aim of dynamically accommodating a wide variety of natural language understanding tasks. The input is variable length English text and the output is a 512 dimensional vector. We apply this model to the [STS benchmark](https://ixa2.si.ehu.es/stswiki/index.php/STSbenchmark) for semantic similarity, and the results can be seen in the [example notebook](https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/semantic_similarity_with_tf_hub_universal_encoder.ipynb) made available. The universal-sentence-encoder model is trained with a deep averaging network (DAN) encoder.

To learn more about text embeddings, refer to the [TensorFlow Embeddings](https://www.tensorflow.org/tutorials/text/word_embeddings) documentation. Our encoder differs from word level embedding models in that we train on a number of natural language prediction tasks that require modeling the meaning of word sequences rather than just individual words. Details are available in the paper "Universal Sentence Encoder" [1].

## Universal Sentence Encoder family

There are several versions of universal sentence encoder models trained with different goals including size/performance multilingual, and fine-grained question answer retrieval.

- [Universal Sentence Encoder family](https://tfhub.dev/google/collections/universal-sentence-encoder/1)

### Example use


### Using TF Hub and HF Hub
```
model_path = snapshot_download(repo_id="Dimitre/universal-sentence-encoder")
model =  KerasLayer(handle=model_path)
embeddings = model([
    "The quick brown fox jumps over the lazy dog.",
    "I am a sentence for which I would like to get its embedding"])
    
print(embeddings)

# The following are example embedding output of 512 dimensions per sentence
# Embedding for: The quick brown fox jumps over the lazy dog.
# [-0.03133016 -0.06338634 -0.01607501, ...]
# Embedding for: I am a sentence for which I would like to get its embedding.
# [0.05080863 -0.0165243   0.01573782, ...]
```

### Using [TF Hub fork](https://github.com/dimitreOliveira/hub)
```
model = pull_from_hub(repo_id="Dimitre/universal-sentence-encoder")
embeddings = model([
    "The quick brown fox jumps over the lazy dog.",
    "I am a sentence for which I would like to get its embedding"])

print(embeddings)

# The following are example embedding output of 512 dimensions per sentence
# Embedding for: The quick brown fox jumps over the lazy dog.
# [-0.03133016 -0.06338634 -0.01607501, ...]
# Embedding for: I am a sentence for which I would like to get its embedding.
# [0.05080863 -0.0165243   0.01573782, ...]
```

This module is about 1GB. Depending on your network speed, it might take a while to load the first time you run inference with it. After that, loading the model should be faster as modules are cached by default ([learn more about caching](https://www.tensorflow.org/hub/tf2_saved_model)). Further, once a module is loaded to memory, inference time should be relatively fast.

### Preprocessing

The module does not require preprocessing the data before applying the module, it performs best effort text input preprocessing inside the graph.

# Semantic Similarity

![Semantic Similarity Graphic](https://www.gstatic.com/aihub/tfhub/universal-sentence-encoder/example-similarity.png)

Semantic similarity is a measure of the degree to which two pieces of text carry the same meaning. This is broadly useful in obtaining good coverage over the numerous ways that a thought can be expressed using language without needing to manually enumerate them.

Simple applications include improving the coverage of systems that trigger behaviors on certain keywords, phrases or utterances. [This section of the notebook](https://colab.research.google.com/github/tensorflow/hub/blob/master/examples/colab/semantic_similarity_with_tf_hub_universal_encoder.ipynb#scrollTo=BnvjATdy64eR) shows how to encode text and compare encoding distances as a proxy for semantic similarity.

# Classification
![Text Classification Graphic](https://www.gstatic.com/aihub/tfhub/universal-sentence-encoder/example-classification.png)

[This notebook](https://colab.research.google.com/github/tensorflow/hub/blob/master/docs/tutorials/text_classification_with_tf_hub.ipynb) shows how to train a simple binary text classifier on top of any TF-Hub module that can embed sentences. The Universal Sentence Encoder was partially trained with custom text classification tasks in mind. These kinds of classifiers can be trained to perform a wide variety of classification tasks often with a very small amount of labeled examples.