Training Prototype NLU

Tahsim Ahmed
Tahsim Ahmed
  • Updated

Training Your Prototype (NLU)? How do I train my assistant? How do I train the model?

You can ensure that your Voiceflow conversation prototype is trained with the model (utterances, intents, entities) in your Voiceflow assistant coupled with the analysis, handling & intent/task fulfilment, or NLU (Natural Language Understanding).

Voiceflow will prompt you if your Assistant needs training to create a high-fidelity testing experience. In entering Test mode, you will be prompted or see a display message in the Training window drop-down (above the Dialog window drop-down).

Tip: Always train your model after adding or modifying your Intents, Utterances and Entities. This ensures you’re testing with the most up-to-date model, and is best practice.

Training is important not only to understand where you can improve your design but also to navigate:

  1. the model structure
  2. the logic and sounds

The more you build, the more you should be training – and training your most recent model will be the most accurate depiction of your real user experience. Training your NLU is a critical part of creating a high-fidelity testing experience.

With Smart Prototyping & our native NLU/NLP, we now support various new use cases and testing opportunities, in combination with our Voice/Chat Voiceflow Assistants. This will make it easier for designers to test at a higher level of intelligence and teammates/user testers to experience a more representative version of your designs.

Best Practices with NLU Prototyping

If you edit the overall dialogue model (addition / change / deletion of sample utterances, addition / change / deletion of slots/entities, etc.), you will need Train Assistant again.

For optimal performance, you should have at least 5-10 Utterances for each Intent and at least 10 values for your Entities.

Was this article helpful?

4 out of 7 found this helpful

Have more questions? Submit a request

Comments

0 comments

Please sign in to leave a comment.