The NLU pipeline is a set of components that will successively process the user request to achieve the desired NLU tasks. In our situation, the most important tasks for our chatbots are
- the intent detection
- the entity extraction
NLU (Natural Language Understanding) is one of the most active in AI right now.
And while things are pretty clear for the goals to achieve, picking the right algorithm and making optimal and scalable for your needs is not easy. There is different technologies available, with associated pros and cons.
So here is our approach to offer you the best pipelines:
- Allow you to pick from our curated, validated and industrialized NLU pipelines.
- Allow you to plug your bot to an external NLU web service. As this is a bit custom, you will have to talk to our sales first.
In this documentation, we will focus on our reference pipelines, already available to all our customers.
The process is super easy.
First, open the settings of your bot
Then, in the NLU Algorithm section you can choose the desired NLU model for your chatbot.
If your bot is supporting multi language, you have the option to pick a pipeline for each language
Last but not least, train your bot
Please do it as your wont wont be able to handle any new requests until you train it on the new pipeline.
Here you go! 🚀
Updated about 2 months ago