Intents, Utterances, and Entities

 

Define Intents, Utterances, and Entities

When a user interacts with an application that utilizes your language model, they may enter utterances. An intent, or more simply the meaning of an utterance, is a task or activity that the user want to carry out. By defining intents and linking them to one or more utterances, you can build a model.

For example, consider the following list of intents and associated utterances:

• GetTime:

"What time is it?"

"What is the time?"

"Tell me the time"

• GetWeather:

"What is the weather forecast?"

"Do I need an umbrella?"

"Will it snow?"

• TurnOnDevice

"Turn the light on."

"Switch on the light."

"Turn on the fan"

• None:

"Hello"

"Goodbye"

Spend some time thinking about the domain your model must cover and the kinds of activities or information that users might request. This will help you establish the intentions that you want your model to comprehend. Every model has a None intent in addition to the intents you define, which you should use to specifically identify utterances that a user might submit but for which no particular action is necessary (like conversational greetings like "hello") or that are outside the model's domain.

Once you've determined which intents your model needs to serve, it's critical to record a variety of distinct example utterances for each purpose. Gather statements that you anticipate users will make, including statements that have the same meaning but are worded differently. Keep these guidelines in mind:

• Capture multiple different examples, or alternative ways of saying the same thing

• Vary the length of the utterances from short, to medium, to long

• Vary the location of the noun or subject of the utterance. Place it at the beginning, the end, or somewhere in between

• Use correct grammar and incorrect grammar in different utterances to offer good training data examples

• The precision, consistency and completeness of your labeled data are key factors to determining model performance.
• Label precisely: Label each entity to its right type always. Only include what you want extracted, avoid unnecessary data in your labels.
• Label consistently: The same entity should have the same label across all the utterances.
• Label completely: Label all the instances of the entity in all your utterances

Entities are used to add specific context to intents. For example, you might define a TurnOnDevice intent that can be applied to multiple devices, and use entities to define the different devices.

You can split entities into a few different component types:

• Learned entities are the most flexible kind of entity, and should be used in most cases. You define a learned component with a suitable name, and then associate words or phrases with it in training utterances. When you train your model, it learns to match the appropriate elements in the utterances with the entity.

• List entities are useful when you need an entity with a specific set of possible values - for example, days of the week. You can include synonyms in a list entity definition, so you could define a DayOfWeek entity that includes the values "Sunday", "Monday", "Tuesday", and so on; each with synonyms like "Sun", "Mon", "Tue", and so on.

• Prebuilt entities are useful for common types such as numbers, datetimes, and names. For example, when prebuilt components are added, you will automatically detect values such as "6" or organizations such as "Microsoft". You can see this article for a list of supported prebuilt entities.

Conclusion

We have successfully learnt about basics of defining intents, utterances, and entities.