RSVP for your your local TensorFlow Everywhere event today!

Text Cookbook

This page lists a set of known guides and tools solving problems in the text domain with TensorFlow Hub. It is a starting place for anybody who wants to solve typical ML problems using pre-trained ML components rather than starting from scratch.


When we want to predict a class for a given example, for example sentiment, toxicity, article category, or any other characteristic.

Text Classification Graphic

The tutorials below are solving the same task from different perspectives and using different tools.


Text classification with Keras - example for building an IMDB sentiment classifier with Keras and TensorFlow Datasets.


Text classification - example for building an IMDB sentiment classifier with Estimator. Contains multiple tips for improvement and a module comparison section.


Predicting Movie Review Sentiment with BERT on TF Hub - shows how to use a BERT module for classification. Includes use of bert library for tokenization and preprocessing.


IMDB classification on Kaggle - shows how to easily interact with a Kaggle competition from a Colab, including downloading the data and submitting the results.

Estimator Keras TF2 TF Datasets BERT Kaggle APIs
Text classification done
Text classification with Keras done done done
Predicting Movie Review Sentiment with BERT on TF Hub done done
IMDB classification on Kaggle done done

Bangla task with FastText embeddings

TensorFlow Hub does not currently offer a module in every language. The following tutorial shows how to leverage TensorFlow Hub for fast experimentation and modular ML development.

Bangla Article Classifier - demonstrates how to create a reusable TensorFlow Hub text embedding, and use it to train a Keras classifier for BARD Bangla Article dataset.

Semantic similarity

When we want to find out which sentences correlate with each other in zero-shot setup (no training examples).

Semantic Similarity Graphic


Semantic similarity - shows how to use the sentence encoder module to compute sentence similarity.


Cross-lingual semantic similarity - shows how to use one of the cross-lingual sentence encoders to compute sentence similarity across languages.

Semantic retrieval

Semantic retrieval - shows how to use Q/A sentence encoder to index a collection of documents for retrieval based on semantic similarity.

SentencePiece input

Semantic similarity with universal encoder lite - shows how to use sentence encoder modules that accept SentencePiece ids on input instead of text.

Module creation

Instead of using only modules on, there are ways to create own modules. This can be a useful tool for better ML codebase modularity and for further sharing.

Wrapping existing pre-trained embeddings

Text embedding module exporter - a tool to wrap an existing pre-trained embedding into a module. Shows how to include text pre-processing ops into the module. This allows to create a sentence embedding module from token embeddings.

Text embedding module exporter v2 - same as above, but compatible with TensorFlow 2 and eager execution.