Chatlayer Documentation
Get in touchAbout Chatlayer
  • Welcome
  • What's new
  • Send feedback
  • start quickly
    • Leadzy tutorial
      • 0. Introduction
      • 1. New bot, new block
      • 2. Understand your users
      • 3. Collect and display user input
      • 4. Steer the conversation with Conditions
      • 5. Empower your bot with Actions
      • 6. Set up a channel and publish your bot
    • Templates
      • Banking
      • E-Commerce Returns
      • E-Bike Shop
      • E-Scooter Support
      • Feedback
      • Find Nearest Location
      • GPT
      • 🆕Gym
      • Job applications
      • Knowledge base AI template
      • Lead generation
      • 🆕NPS
      • Restaurant
      • Retail
  • navigation
    • Analytics
      • Dashboard
      • Customers
      • Conversations
      • User flow
      • Intents
      • 🆕Funnels [Beta]
    • Bot builder
      • Flows
        • Canvas functionalities
        • Collaborate with team members
        • Manage your flows
        • 🆕[Beta] Export and import flows
      • Bot dialogs view
      • Translations
      • Events
    • NLP
      • Dashboard
      • Intents
      • Expressions
      • Entities
      • Train
      • NLP settings
      • Improve
    • Knowledge base AI
      • Add content to your KBAI
      • Build your KBAI flow
      • Use your KBAI source URL in a button
      • Use tags to limit your KBAI content
      • 🆕Use Tables to store your KBAI questions
      • 🆕Manage handover where KBAI is unsatisfactory
    • History
      • Conversations
      • Execution logs
      • Versions
    • Channels
    • Tables
      • Create a table with records
      • Column types
      • Operate on your records
        • Insert record
        • Update record
        • Retrieve record
        • Delete record
      • API
    • Settings
      • Bot settings
      • Offloading
      • Variables
      • Voice
      • Import/Export
  • build your bot
    • Conversation design
      • Plan your bot
      • Conversation design workflow
    • Flow logic
      • Blocks
        • Message
        • Condition
        • Collect input
        • Action
      • Go-to connections
    • 🆕Emulator
    • Tips & best practices
      • Route your flow depending on the time
      • Improve the Not understood block
        • How to create better not understood messages
        • Not understood counter
        • Not understood Google search
      • Go to previous block
      • Recognizing a returning user
      • Skip introduction message
      • Route your flow depending on the channel
      • Reuse flows
      • Connect two bots to each other
  • understand users
    • Natural language processing (NLP)
      • Basic NLP concepts
      • Detect information with entities
        • Match entities
        • Contextual entities
        • System entities
        • Composite entities
      • NLP best practices
        • Word order and diversity of expressions
      • AI intent booster
      • Train your NLP
      • Context
      • NLP import & export
      • Sentiment analysis
    • Languages
      • Supported languages
      • Make your bot multilingual
      • Change language within the conversation
  • set up channels
    • Add a channel to your bot
    • All channels
      • 🚨Facebook Messenger [Deprecated soon]
        • Facebook Admin Removal
        • Facebook Webview Whitelisting
        • Facebook Messenger API updates for Europe
      • 🚨Google Assistant [Deprecated soon]
      • Webhook
      • Web
        • 🚨Web V1 [Deprecated]
          • Customize web widget
          • Live example web widget
        • 🆕Web V2
          • 🆕From Web V1 to V2
          • 🆕Web V2 methods and options
    • Sinch Conversation API
      • Configure your Sinch Conversation API
      • 🆕 Make the most of RCS with Carousels
      • WhatsApp Business API
  • integrate & code
    • API calls
      • Configure your API integration
      • Advanced API features
      • V1 API Reference
      • Custom integrations 101
    • Code editor
      • [Example] Sending data to Airtable (POST)
      • [Example] Retrieving data from Airtable (GET)
      • [Example] Making SOAP requests
    • App integrations
      • Airtable
      • Freshdesk
      • Freshdesk Messaging
      • 🆕Gmail
      • Intercom
      • Mailgun
      • OpenAI: GPT-3, ChatGPT and GPT-4
      • Salesforce
      • 🆕Slack
      • Topdesk
      • Zendesk Support
      • Zendesk Sunshine (beta)
    • 🆕Expression syntax
    • Human handover & live chat
      • Sinch Contact Pro
      • #Interact
      • Genesys Cloud
      • Offloading Webhook
      • Salesforce Service Cloud
      • Sparkcentral by Hootsuite
      • Zendesk Chat
    • Chatlayer messages specifications
  • Publish
    • Publish your bot
      • Publish a flow
  • Analyze & maintain
    • Analytics definitions
    • Data retention
    • Maintenance
    • Session
    • Track events for analytics
  • VOICE
    • 🆕Send bot response as audio
    • Voicebots
      • Create a voicebot
      • Voicebot-specific actions
      • Test your voicebot
      • From chat to voice
  • access & support
    • Identity & Access
      • Single Sign-On (SAML SSO)
    • Billing & subscription
    • Get in touch
    • Chatlayer glossary
    • SaaS Regions & IP Ranges
    • Status
    • Debug your bot
      • No correct response
      • Collect input not working
      • Video isn't working
Powered by GitBook
On this page
  • How the Train page works
  • Expressions not included
  • Add customer expressions to your model
  • Good practices before adding expressions
  • Check that the labelled intent is correct
  • Scope the expressions

Was this helpful?

  1. navigation
  2. NLP

Train

The NLP Train tab is where you can train your NLP model using real incoming user expressions.

PreviousEntitiesNextNLP settings

Last updated 11 months ago

Was this helpful?

After you your bot, you want to keep training the NLP model with real user input. By doing so, your bot becomes smarter over time and can support more diverse expressions too. To do so, you can use the NLP Train tab to add real user expressions to your NLP model.

NLP terms and concepts seem unfamiliar to you? Make sure to read our detailed page.

How the Train page works

All user messages are labeled by the NLP model. Each message gets a suggested intent and a confidence score so that you can evaluate these messages. The NLP also identifies possible entities and values.

Expressions not included

  • If two users use the exact same expression, it will only show up once in the Train page.

  • If an expression from a user is an exact match with an expression already included in your model, it will not be included in the Train tab.

  • In the Score column you will see the score of the NLP model at the time the expression was said. This might differ from the score that the current NLP model gives this expression

Add customer expressions to your model

To add a user expression to your NLP model:

  1. Find the line of the expression.

  2. There are 2 possibilities:

    • If you're satisfied with the expression and intent suggested, click on +.

    • If you're not satisfied with the expression and intent, you can edit them by clicking on the Edit button before adding that expression to your model.

Good practices before adding expressions

The image below summarizes the good practice to have when using the Train page and adding user expressions to your NLP expressions.

Check that the labelled intent is correct

Before you add an expression, you need to make sure that it's a relevant one. Not all things said by a user are qualitative enough for the bot to train on.

For example, consider the following expression, said by a user to your bot:

Even though our NLP is really smart, it doesn't always suggest the correct intent. In this case, the bot did not contain an intent referring to the date or time, which is why the NLP classified the expression under a wrong intent. This is why you should always check an expression before adding it to the NLP.

Never add all suggested expressions without checking them as this can confuse your bot and mess up its training.

Scope the expressions

We also recommend scoping expressions in case they contain unnecessary information. Let's look at the following example:

In this case, the NLP did find the correct intent, but the confidence score is rather low because the expression contains a lot of unnecessary information. It's best practice to delete this information from the expression before adding it to the intent, so that the bot trains on relevant info only.

Delete the unnecessary information in an expression before adding it to your NLP.

To be able to use the Train tab, your bot needs to be first.

Expressions from the window will not be included in the Train page.

In the draft environment, you can see expressions from both the environment. Make sure you add the expressions to your DRAFT environment so that the next published version on the LIVE environment contains these new expressions as well.

published
DRAFT and LIVE
published
Natural language processing (NLP)
The NLP train tab.
Train page best practices (click on the image to enlarge it).
Example of incoming user expression.
Example of incoming user expression.
Emulator