Comment on page
Natural Language Processing (NLP)
The Natural Language Processing (NLP) engine is the underlying code that enables your bot to understand the natural language used by us humans.
Understanding natural language isn't easy: it takes us more than 12 years and hundreds of examples to understand the 20,000 most common words. Imagine how hard it must be for computers! To train the NLP engine, we need huge amounts of data. Luckily, we rely on pre-trained models that have a lot of smarts built in. Our NLP engine will take care of spelling mistakes, synonyms, slang, varying word order, etc ...
Whenever a user sends a message to the bot, the bot will check if that message is related to any of the expressions that are part of the NLP engine. For example, when a user types 'Get me a flight ticket,' the NLP will check if this sentence matches any of its expressions and check if this message contains similar words as the expressions. In the example above, the NLP gives a 93% confidence score that 'Get me a flight ticket' belongs to the intent 'Book flight'. Because this sentence is recognised above the NLP threshold, the response that is linked to this intent will be shown to the user.
An intent refers to the goal that a customer has in mind when talking to a bot, it's all about what the user wants to get out of the interaction.
Some examples of intents:
- Book train ticket
- Talk to a human
- Create support ticket
Expressions are example sentences of a specific intent: they're all the different ways a user can express their intent. It's crucial for an intent to contain diverse expressions so that the NLP can give more accurate results.
Here are a few expressions for the intent 'who are you'
- Who are you?
- What is your name?
- Do you have a name?
- Tell me more about yourself
- Please, I'd like to know who I am talking to
- How should I call you?
- who is choo choo?
- Tell me what your name is
- Who are ya?
- What do people call you?
Here are a few expressions for the intent 'order pizza'
- I'd like to order some pizza please
- Can I get a pizza to go?
- I want a pizza margherita
- I'd like to order some food
- Can you help me order pizza?
- I'm in the mood for some pizza tonight!
Please note that our NLP engine has a limit of 1000 characters. Messages with more than 1000 characters will always trigger the 'not understood' block. To guide the user, you can create a customized 'not understood' message for these long messages, as described here.
Entities are important pieces of information that can be found in expressions. In some cases, you'll want to save these as variables so you can re-use them later in the conversation.
Find out more about entities by clicking the link below:
In every section of our platform, you will find an 'update NLP' button available when you click the 'publish' button on the top navigation.
It's important to update the NLP model, especially after making significant changes such as adding new intents or modifying entities. Here's why:
- Reflect Changes: New changes made to the NLP model, such as adding intents or entities, won't take effect until the NLP is updated.
- Testing: By updating the NLP, you can easily test the impact of these changes on your chatbot's performance. This allows you to fine-tune and validate your bot's behavior.
- 1.After Updating NLP: Once you have initiated the NLP update process, you can check the status of the update.
- 2.Click Notifications: To check the status, click on the notification icon. This will display the progress and status of the NLP update.
- 3.Monitor Progress: You can monitor the progress and ensure that the update is successfully completed.
We've created a few intent packs so you can quickly get started and train your NLP model. You can add these pre-built intents directly in the platform by clicking on 'intents' in the NLP section and then on the top right, 'Add Prebuilt Intent'
Then you'll get a pop-up screen showing you all the pre-built intents you can add: