Updated by Lucas Agra
Intent classification and Entity extraction
The dataset is composed by training sentences and testing sentences. These sentences helds important components used to define your intelligence context: intents and entities.
Through this components, we have enough data to guide a rich conversation flow in a chatbot.
The intelligence usage is done through intent classifications and entity extractions:
Intents are what define the context of your intelligence. Upon receiving a sentence to classify, your intelligence will respond to which of the trained intents that sentence is most likely to belong to.
Therefore, it is crucial to make an early planning about the intelligence scope, so the intentions can be clearly and precisely defined.
By doing a detailed early planning, an eventual need of changing the intelligence's scope, removing or adding new intentions after launch is drastically reduced.
See here how to add intentions!
They are components used to extract additional information when sending a sentence to the intelligence, in addition to its labeled intention.
In Bothub, its usage is made by defining groups of words that belong to the same category, for example, by marking separately:
- pepperoni, mozzarella, margherita as flavor
- television, smartphone, tablet as product
Your intelligence will automatically try to search for flavors and products in the received sentences, extracting them and returning as a response along with the labeled intent.
It is important to note: the intelligence will try to extract even other words that were not explicitly marked by you, but that in its understanding has a high probability of belonging to that group of words (entity).
For example, considering the product entity above, using these three markings alone, should also extract words like computer, laptop and tv as product.
See here how to use entities!