Interview with Luisa Herrmann-Nowosielski, Head of Product Management at

We launched the Natural Language API (NL API) in July, giving users an opportunity to familiarize themselves with our symbolic approach to natural language processing (NLP) using a REST API. This API lets users input text to perform deep semantic and syntactic analyses to extract main topics, main phrases, entities, geographic locations, and many other types of information.

Where previously only customers with customized implementations could use this technology, now anyone with access to an API interface can leverage our NL API to easily analyze and extract meaningful information from their unstructured data. We see this approach unlocking limitless possibilities as to what users can do with data — be it within academic articles, news stories, emails, contracts, chats, or any unstructured text.

And this was only the first step in our journey towards offering a hybrid approach to NLP that uses our approach in conjunction with machine learning (ML).


How did you come up with the idea for  NL API?

The driving force behind the work we are doing with the NL API is to make our technology available to a broader audience of data scientists and software engineers. Previously, only large enterprises could access our technology, and this was through a customized deployment that could take weeks to months to implement. Now, it’s available to anyone who wants to use it at no cost and as we expand our solutions, we will always offer a free tier.


How has the need for  NL API evolved during the pandemic?

The pandemic has changed the way that so many businesses operate, but it doesn’t seem to have diminished the excitement about AI. In fact, we are seeing a broader usage of NLP in nearly every industry vertical as organizations are exploring uses of AI to make their operations more efficient to face the challenges of the pandemic.

What can we hope to see from NL API in the future?

We are planning to release a series of Extensions that will give users the ability to apply our technology to a variety of industry-specific uses cases without requiring any additional customization. In 2021, we will also release a new platform. The NL API will integrate with this platform and allow users to design, build, test, and operate their own NLP models.