Intents

Technology plays a major role, but the most significant performance gains are obtained by developing a good understanding of the fundamental NLU concepts.

Good to know: your product docs aren't just a reference of all your features! use them to encourage folks to perform certain actions and discover the value in your product.

Intents

An intent categorizes a customer's intention for one conversation turn. The intent general meaning of a sentence (or an utterance in the chatbots lingo). For example, the sentences below convey the intent of being hungry, let’s call it i_am_hungry:

• I am hungry

• I need to eat something

• I am starving

• My kingdom for a pizza

How do we teach our model that these utterances convey the i_am_hungry intent? We train it to distinguish them from sentences with other meanings. We create a dataset containing examples of different intents.

How can a program understand the meaning? Let’s just say that there’s a way to express the meaning of words with numbers (or vectors). The essential idea is that vectors can be compared (a distance can be calculated), and that a small distance indicates the words have similar meaning.

When you click the Train Phrases button, the conversational AI framework used by ThumbCrowd, will learn vectors from your examples, and learn how to distinguish intents.

Best practices

Add semantic variety to your model

Introducing variety is key to build a capable model.

GOOD

GOOD

• I want to book a flight from Paris to Montreal

• Is there a flight from Rome to London tomorrow?

• I wanna fly from The big apple to the city of light

But the following will only get you so far:

BAD

• I want to book a flight from Paris to Montreal

• I want to book a flight from Rome to London tomorrow?

• I want to book a flight from The big apple to the city of light