To achieve good classification accuracy, it’s important to provide your agent with enough data. The greater the number of natural language examples in the Training Phrases section of Intents, the better the classification accuracy. We encourage you to use Example Mode for your Training Phrases instead of Template Mode, since the former provides better data for machine learning.

When you create a new intent, start with examples that have the most number parameters. This way you will define what entities should be used in this intent and name all the parameters the right way. Having annotated the first few long examples, it will be easier for you to continue with shorter ones, as the system will start suggesting the correct entities for new examples.

When you save an intent, Dialogflow will begin training your agent with the new data you've added. Until the training is complete, the updates may not be reflected in the agent.

To make the training process more efficient, we have created a Training tool that allows you to analyze conversation logs with your agent and add annotated examples to relevant intents in bulk.

How it works

As you and your users chat with your agent, you can access the conversation logs by clicking Training in the left side menu.

The logs are presented in two views:

  • Training - This view shows conversations with the agent for review and performance improvements. Each user request is a list item, showing the intent that will be used for processing, as well as the current parameter annotation. You can reassign inputs to correct intents and fix annotations. Every time you approve changes, the agent is trained, and the results in the tab are updated.
  • History - This view displays the conversations in a plain mode. This way you can see latest conversations with your agent in chronological order.

Assigning an input to an intent adds the example as a Training Phrases entry for that intent. Training your agent using this method is good for adding specific examples from users' interactions.

Disabling interaction logs

Depending on your agent, conversation logs could include personally identifiable or confidential information and your agent may need to comply with legal or other restrictions. To help with this, you can disable logging for your agent in its settings.

  1. Click on the gear icon next to your agent's name.
  2. Click the General tab.
  3. Under Log Settings, check Disable interaction logs.
  • logging that may occur with fulfillment, such as webhooks
  • logging that may occur with one-click integration platforms such as Actions on Google, Facebook, Slack

If you don't need to disable all logging, you can delete individual log entries.

Uploading Training Phrases

You can upload sample user inputs in a .txt file or in a .zip archive with multiple (up to 10) .txt files. Each input should start from a new line.

Just click the Upload button in the right upper corner.

Adding via API

You can add more Training Phrases using the POST and PUT API methods for the /intents endpoint.

Any changes made via the API to alter the agent's behavior, initiate the training in the same way when you save an intent. This trains the agent with the changes delievered through the API.

How to train your agent

Click on a dialog (dialogs are named by the first user input in the session). You may see that some inputs don’t match to any intent or have incorrect annotations.

Handle unmatched inputs

Unmatched inputs are marked by an exclamation mark error_outline. You can assign unmatched inputs to intents in two ways:

  • Add inputs to one of the existing intents.
  • Create a new intent with this input.

Fix annotations

In the case of incomplete or incorrect annotations, you can fix it the same way as adding or editing examples in intents.

To add an annotation, highlight the word that should be annotated and select an entity from the list.

To edit an existing annotation, click on an annotated word and select a different entity from the list.

If an entity used for annotation doesn’t contain the annotated word/phrase, it’ll be automatically added to this entity as a new entry unless the 'Allow automated expansion' option is checked.

Add examples to intents

When you edit an input, a green check mark check appears on the right. It means that the input will be added to the assigned intent.

If you don’t want to add the input, click on the cancel icon not_interested right below the check button.

Once you’ve reviewed all the inputs in the session, click the Approve button to add all the fixed inputs to the respective intents. Your agent will start training immediately. It’ll show a notification when the training has been completed.

Delete interaction log entries

You can delete interaction log entries from either the Training or History tab, on the Training page. Since they're linked, deleting an entry in the Training tab will also delete it from the History tab, and vice versa.

You can also disable logging for your agent, if you don't want anything logged.

Training tab

To delete one or more entries, click on the trashcan icon for the entries you want to delete and then click on the Approve button to remove them.

History tab

To delete an entry, hover over the listing and click on the Remove link.