IMPORTANT CHATBOT TERMS- UTTERANCE, INTENT, ENTITY AND NLP.
There are a couple of terms you are going to see/hear a lot if you are new to chatbot development.
Chatbot designing or development has a unique vocabulary. And it is easier for everyone to communicate about chatbots if these terms are known.
Here are some basic yet essential terms to know about chatbots:
Utterances:
Anything that a user says is an utterance.
For example-
“Can I have a pizza.”
“How is the weather in Delhi?”
These sentences are called utterances.
Intents:
These are the actions that users want to execute.
In simple words, intents are the intentions of the user that you can draw from the utterances.
In most of the cases, intents can be identified by looking for verbs in the dialogues of the users. But sometimes the complete sentence is used to determine the intent of it.
In the given sentence, the user wants to place an order for a pizza.
“Can I have a pizza?”
We can label the intent under an understandable name like ‘Order.food’.
Now, the above example shows us an intent that directly maps to the business of the bot, I.e., ordering food. Hence it falls under the category of business intent.
There is another type of intents named casual intents. These are mostly the openers and closers of the conversation like “hi” “bye” “thanks, bye” etc.
Casual intents can also be affirmative or negative. So, simple “yes” or “no” can also be intents with others like “no thanks”, “yeah, sure” etc.
Entities:
The business intents have metadata about the intents, and they are called entities.
For example-
“I want to order a cheese pizza.”
In the above example, the Entity is Cheese.
In simple words, the entity is the information provided about the intent in a dialogue.
An entity can also be a composite entity which can have multiple entities in it.
For example-
“I am looking for six-pack Maggi noodles.”
Here the intent is ‘Search-product”, and the entity is a composite one.
Entity:
Composite entity-
Product: Noodles
Size: six-pack
Brand: Maggi.
NLP:
Natural language processing.
Though it is something, we can have a separate post to talk about because there is a lot we can learn about how NLP works. Today I am only going to introduce this term to you.
So, NLP is a collective term referring to automatic computational processing of human languages. It is a field of Artificial Intelligence that gives the machines the ability to read, understand and derive meaning from human languages.
NLP examines an utterance and extracts the intent and entities. NLP software includes Amazon Lex, Facebook’s Wit.ai, and Microsoft’s LUIS.
