Using Rasa X to just evaluate NLU without Core


I currently using Rasa NLU with a different custom dialog manager and I was wondering if there is any way, or any plans to enable a way, to use Rasa X’s super cool conversation investigation/labeling stuff to just work with NLU snippets? Basically I’d like to present individual sentences to people and have them label intent and entities and save this to the .md file as updated training data.

EDIT: Actually, this is basically what i am after is there an easy way to server this as a web app so i can send links to people and they can edit/upload? I don’t really want to use the public one linked there

Hi Zylatis,

thanks for the question. If the rasa-nlu-trainer meets your needs, that’s awesome! When you say you want people to be able to edit & upload, I guess you mean you want to build a backend server that persists the data and manages authentication?

In that case you’ll have to fork the trainer repo and also build a small backend server to handle those things.

1 Like

Hi @amn41, thanks for the info. For now I have gone with this

which is pretty neat, though I maintain it would be really great to have something like this built into Rasa X, i.e. be able to annotate data that was externally generated (i.e. not coming from a Rasa Core convo) and then use that as training data for Rasa.

One of the drawbacks of doccanno is you cannot do NER and intent annotation on a bit of data at the same time :confused: (but there is an open issue on this)