My chatbot is connected to Slack and the conversations a user has with the bot are stored in mongo db.
I’m wondering if anyone has suggestions on how to use the stored conversations as training data…
I don’t want to manually check all the events that are stored to see if there went something wrong at that moment. Because it would take a lot of time to go through all the events.
So is there an easy way to deal with this? Has someone else used stored conversation as input for training, how did you do it?
Do you store also predicted intent with the conversation texts? if yes, you can do two things:
Use predicted intents in the evaluation
Use unrecognized texts for generating new training data, but remember, that directly putting everything in the training data is a bad idea, it’s better to use this data to generate little bit different examples so that model correctly recognizes similar examples too
Unfortunately I don’t know how you can automatically evaluate this saved data, so at some point you still have manual work and overall I believe to improve bot, manual work is important, at least in the beginning.