Translation API with Deep Learning

Deep Learning NLP Techniques for Advanced Translation

Automatic translation has been available for years thanks to services like Google translate, but results have never been completely satisfying. Thanks to the recent progress made on deep learning, it is now possible to reach a more advanced level of translation.

Deep learning NLP models make translation very fluent. Even for advanced technical topics, it's hard to detect that translation was performed by a machine. Now that translation is more reliable than ever, it creates tons of new possibilities.

Deep learning translation

Why Use Automatic Translation?

Potential applications for automatic translation are countless, but let's show 2 examples.

Multilingual Support

Many customers cannot or don't want to speak English. Instead of just ignoring them and potentially losing them, why not automatically translate all the discussions?

Multilingual Marketing

Targeting customers based in multiple countries with English content only is not optimal. Most customers prefer to read about you in their own language. It is also a great way to improve SEO. Leveraging machine translation is a great way to easily get more customers.

Translation with Hugging Face Transformers

Hugging Face transformers is an amazing library that has been recently released. It is based on either PyTorch or TensorFlow, depending on the model you're using. Transformers have clearly helped deep learning NLP make great progress in terms of accuracy. However this accuracy improvement comes at a cost: transformers are extremely demanding in terms of resources.

Hugging Face is a central repository regrouping all the newest open-source NLP transformer-based models. Some of them, based on Helsinki NLP's Opus MT are perfectly suited for automatic translation.

Translation Inference API

Building an inference API for translation is a necessary step as soon a you want to use deep learning translation in production. But building such an API is hard... First because you need to code the API (easy part) but also because you need to build a highly available, fast, and scalable infrastructure to serve your models behind the hood (hardest part). It is especially hard for machine learning models as they consume a lot of resources (memory, disk space, CPU, GPU...).

Such an API is interesting because it is completely decoupled from the rest of your stack (microservice architecture), so you can easily scale it independently, and you can access it using any programming language. Most machine learning frameworks are developed in Python, but it's likely that you want to access them from other languages like Javascript, Go, Ruby...

NLP Cloud's Translation API

NLP Cloud proposes a translation API that gives you the opportunity to perform machine translation out of the box, based on Hugging Face transformers' Helsinki NLP Opus MT, with excellent performances. The response time (latency) is very good for these models. You can either use all the pre-trained models available or upload your own custom models!

For more details, see our documentation about translation.

The 14 following pre-trained models have been added to the NLP Cloud API (more will be added in the future):

Testing deep learning translation locally is one thing, but using it reliably in production is another thing. With NLP Cloud you can just do both!

As for all our NLP models, you can use translation for free, up to 3 API requests per minute.