Movie review feelings
Solve a text classification problem with BERT
In this tutorial, you will solve a text classification problem using BERT (Bidirectional Encoder Representations from Transformers). The input is an IMDB dataset consisting of movie reviews, tagged with either positive or negative sentiment – i.e., how a user or customer feels about the movie.
Text classification aims to assign text, e.g., tweets, messages, or reviews, to one or multiple categories. Such categories can be the author’s mood: is a review positive or negative?
- Target audience: Beginners
You will learn to
- How to build and deploy a model based on BERT.
- Work with single-label text classification.
Create a project
First, click New project to create a project and name it so you know what kind of project it is.
A project combines all of the steps in solving a problem, from the pre-processing of datasets to model building, evaluation, and deployment. Using projects makes it easy to collaborate with others.
What is BERT?
BERT pushed the state of the art in Natural Language Processing (NLP), the techniques that aim to automatically process, analyze and manipulate (large amounts) of language data like speech and text.
BERT does this by combining two powerful technologies:
It is based on a deep Transformer network. A type of network that can process efficiently long texts by using attention.
It is bidirectional. Meaning that it takes into account the whole text passage to understand the meaning of each word.
If you want it could be a good idea to read about word embeddings and BERT’s attention mechanism, which are important concepts in NLP. For an introduction and overview material, check out the links below:
Add the IMDB data
After creating the project, you will be taken to the Datasets view, where you can import data.
There are several ways to import your data to the platform. This time we will use the Data library that is packed with free-to-use datasets.
Click the Data library button and look for the IMDB - tutorial data dataset in the list. Click on it to get more information. You can also read this article for more info on the IMDB dataset.
If you agree with the license, click Accept and import.
This will import the dataset in your project, and you will be taken to the dataset’s details where you can edit features and subsets.
The feature encoding determines the way in which example data is turned into numbers that a model can do calculations with. Verify that the default feature encoding is correct:
If a feature uses the wrong settings, click the Wrench icon to change it.
Subsets of the dataset
Keep these default values in this project, but you can use whatever subset split you want later.
Save the dataset
You’ve now created a dataset ready to be used in the platform.
Click Save version and then click Use in new experiment and the Experiment wizard will pop up.
Design a text classification model with the wizard
The Experiment wizard opens to help you set up your training experiment and to recommend snippets as prebuilt models. We’ll now go over each tab.
The platform selects the correct subsets by default.
Training uses 80% of the available examples.
Validation uses the 10% validation examples to check how the model generalizes to unseen examples.
Input(s) / target tab
The platform should select the correct features by default.
Input(s) column: make sure that only review () is selected.
Target column: make sure that sentiment (1) is selected.
Make sure the Problem type is Binary text classification, since we want to classify text into two possible categories (positive and negative). The platform recommends the appropriate Problem type and snippets based on the input and target features.
Select the English BERT uncased snippet.
All the training examples in the dataset are written in English, and for this tutorial we plan to use the model to only process English text.
Click Create to build the model.
Idea for later experiments
You can create another experiment later on and use the Multilingual BERT cased snippet instead. Multilingual models are useful:
When you want to work with other languages than English.
When your training dataset is only available in some languages that are different from the languages that you want to use your model for.
The model is now built in the Modeling view, and you can change some settings.
The model contain five blocks:
The Input block represents data coming into the model.
The English BERT encoder block implements the BERT network in its base size.
The Dense block represents a fully connected layer of artificial nodes.
It outputs a tensor of shape
1since the target feature sentiment is one out of two values (
The Target block represents the output that we are trying to learn with our model.
Change sequence length in BERT tokenizer block
Click on the BERT Tokenizer block in the modeling canvas.
Set the Sequence length to 256, since this is a good compromise between speed and the amount of text preserved. Smaller sequences compute faster, but they might cut some words from your text.
Sequence length is the number of tokens (roughly the number of words) kept during text tokenization. If there are fewer tokens in an example than indicated by this parameter the text will be padded. If there are more tokens, the text will be truncated, i.e., cut from the end to fit the sequence length.
In the dataset, a Sequence length of 512 will cut 8% of the review samples, a length of 256 will cut 30%, and 128 will cut 74%.
Check experiment settings & run the experiment
Click the Settings tab:
Set the Batch Size to 16.
Batch size is how many samples should be calculated at the same time. A larger batch size than 16 would run out of memory. For text processing models, we recommend keeping the product Sequence length x Batch size below 3000 to avoid running out of memory.
Check that Epochs is 2. BERT models are already pretrained, and a delicate fine-tuning generally gives the best results.
Keep the loss function in the Target block.
Loss is a number on how well the model performs. If the model predictions are totally wrong, the loss will be a high number. If they’re pretty good, it will be close to zero.
By default, we’ve also checked the Early stopped check-box. This means that the training will automatically be stopped when a chosen metric has stopped improving. Great to make sure you don’t train for too long.
The next step is simply to click Run. So let’s do that!
Click Run to start the training.
The training will take some time since BERT is a very large and complex model.
Expect about half an hour of training time per epoch with the Sequence length of 256.
Analyzing the first experiment
Navigate to the Evaluation view and watch the model train.
To evaluate the performance of the model, you can look at the Binary accuracy by clicking on its name under the plot.
Binary accuracy gives the percentage of predictions that are correct. It should be about 85-90% by the end of training.
The precision gives the proportion of positive predictions, i.e., examples classified as
positive, that was actually correct.
The recall gives the proportion of positive examples that are identified by the model.
The confusion matrix shows how often examples are correctly or incorrectly classified as another category. Correct predictions fall on the diagonal.
Since the problem is a binary classification problem, the ROC curve will also be shown.
The ROC curve is a nice way to see how good the model generally is. The closer the ROC curve passes to the top left corner, the better the model is performing.
Deploy your trained experiment
In the Deployment view click New deployment.
Select Experiment that you want to deploy for use in production.
In this tutorial we only trained one model so there is only one experiment in the list, but if you train more models with different tweaks, they will become available for deployment.
Select the Checkpoint marked with (best), since this is when the model had the best performance.
The platform creates a checkpoint after every epoch of training. This is useful since performance can sometimes get worse when a model is trained for too many epochs.
Click Create to create the new deployment from the selected experiment and checkpoint.
Click on Enable to deploy the experiment.
As soon as your deployment is enabled, you can start requesting predictions.
Test with our web app
Let’s test your model now when it’s deployed. Click the Test deployment button, and you’ll open the Image & Text Classifier API tester with all relevant data copied from your deployment.
Now write your own review, copy the example below, or simply copy a recent review from, e.g., IMDB:
I don’t want to complain about the movie, it was really just ok. I would consider it an epilogue to Endgame as opposed to a middle film in what I’m assuming is a trilogy (to match the other MCU character films). Anyhow, I was just meh about this one. I will say that the mid-credit scene was one of the best among the MCU movies.
Click [.guilabel]#Play# to get a result.
Note: The web app can be used for testing other single-label text classification models as well.
Tutorial recap and next steps
In this tutorial, you’ve created a text classification model that you first evaluated and then deployed. You have used all the tools you need to go from data to production — easily and quickly.
Continue to experiment with different hyperparameters and tweak your experiments to see if you can improve the accuracy of the model further. You may also want to experiment with datasets from different sources but note that the model in this tutorial works best with short text samples.
Navigate to the Modeling view.
Click New experiment and continue experimenting.
Next tutorial - Classify text in any language
We suggest that the next tutorial you should do is Classify text in any language. You will learn how to use the Multilingual BERT snippet to create a model that is able to work with multiple languages simultaneously!
This will unlock the AI possibilities to automatically identify relationships and context in text data in 100 languages.
You will learn to:
Build, train, and deploy a Multilingual BERT model, the state of the art AI in language processing.
Automatically classify text extracts depending on their topic.
Mix the available languages for training the model, and test it in any language.