Concepts We Work on

Because maths precedes the physics.

Dhee.AI is a vertically integrated stack of natural language processing and speech technologies which come together to work seamlessly as voice assisted chat-bots and voice bots - capable to concurrently engage with thousands of users.

To help you in training the bots better on our platform, we shall be giving you key insights on the components and concepts which are the building blocks of Dhee.AI.

Equipped with these insights, you shall be able to debug your bots faster and take quick and effective remedial actions to fix the bugs or gaps identified by your end users.

Natural Language Processing (NLP)

At the heart of what we do is Natural language processing. You can get a short introduction to it by visiting the below link. Also note that the components of NLP used extensively in Dhee.AI are introduced as sub-topics which you can access and read using the corresponding links.

pageWhat is NLP?

Natural Language Parsers

The first action done by Dhee.AI when a human speaks to it is to parse it using a natural language parser to get the parts of the speech, entities, and the general semantic relationship between entities and verbs in the spoken utterance.

Read more about this elaborate parsing pipeline using the below link.

pageNatural Language Parser Pipeline

Context Vectors (Word Embeddings)

Parsing and finding structure of a spoken utterance is only the beginning of the journey. The next step involves semantic analysis. Here we try to enrich the parse output with more semantic information. This is done by injecting the contextual vector of each word into the parse output.

Read more about word embedding by visiting the below link.

pageWord Embeddings