Training task
After building a flow, you have to make sure that they are connected to the right answers and that sentences are tied to the right meanings.
The training process is the same as a person learning a new language. The more you train, the better the results.
To do so, you train your Intents and Entities using a Natural Language Processing engine. In eva you can use our internal NLP or use external ones.
Training using eva NLP
After building a flow, you have to make sure that they are connected to the right answers. Here, you will learn the best way to do this.
If you are using NTT DATA eva NLP, you will have to train your Intents and Entities using the eva cockpit. Every time an Intent, Entity, document, or question is changed, the button “Train” will appear in the training section. Just click it.Training a virtual agent is very easy! You'll just have to go to the training repository:
View all trained versions (valid and invalid) in the repository. The latest trained version will be automatically published.
To enable the
Trainingbutton you must have at least five intents with at least five examples each.If you delete an intent or example in the repository, you'll need to retrain your content.
Entities don’t have minimum number of values to be trained.
After training, you can check the details of the training.
Click on “(view details)” to review what went wrong on that specific training.
Other Connectors
If you want to use other external NLPs, please continue to the next section:
pageOther NLP and LLM ConnectorsLast updated
