FeersumNLU is the Natural Language Understanding component of Feersum Engine. It helps us determine what language a user is speaking, what they are asking us to do and how they are feeling. If we do that well, we can respond to them in a way that helps them perform their task.
FeersumNLU provides Natural Language solutions for chat-based interactions, where messages from the end-user are especially short. Our product is also designed to be language-agnostic, which means it can be scaled to work with any language, even in markets where large bodies of labelled data do not exist. Our Natural Language Understanding models are developed locally, and can be modified to provide solutions for specialised industries like finance or health.
FeersumNLU makes use of open-source building blocks like NLTK, sklearn, PyTorch and Duckling, as well as algorithms we've developed in-house. We build on all elements to support a growing list of local and international languages.
Current features include Natural Language FAQ's, detection of the user's intent and sentiment, information extraction, entity extraction, and text-based language identification.
A playground instance of our FeersumNLU service is available to experiment with. All of the details are on our Github page. Please give us feedback.
You'll need an authentication token to access the service, so email us on firstname.lastname@example.org and we'll send you one. The API documentation is available and there is a Python language wrapper on the Github page, including examples of how to use the various NLP models with Python or curl http requests.