-> to BOTwiki - The Chatbot Wiki

Entities are used to extract user information from natural language.

This is usually done between System Entities and Custom Entities. System entities are entities already contained in the system for addresses, times, and numbers, for example.

Custom entities, on the other hand, can be defined by the user and, depending on the use case, contain product information or an employee directory, for example.

Entities in NLP Services

The Entity Recognition is already integrated in the current NLP Services [1][2][3] and is, besides the Intent Matching, the main component of the Natural Language Processing for chatbots.

Example for an Entity Extraction

I'd like to have small pizza Margherita into the Berliner Street 1 order.


small (Custom Entity pizza_size)

Margherita (Custom Entity pizza_type)

Berliner Street 1 (System Entity street_address)


> Back to the BOTwiki - The Chatbot Wiki


[1] https://dialogflow.com/docs/intents

[2] https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-utterance

[3] https://cloud.ibm.com/docs/services/assistant?topic=assistant-intents