Mutters

There are two types of chatbots -- unreliable freeform ones (e.g. GPT-3) and reliable script-based ones (e.g. Alexa). I believe that what you're looking to do (dynamic rewriting) is moreso an active research topic! The script-based chatbots are very similar to those in the 80s, with one major addition -- the options at each choice point are now "intents" instead of exact text (e.g. "the user intends to order a taxi"). Machine learning is then used to classify whatever the user says/writes as an "intent," then the script is followed to the next choice point. Here is a nice Java framework that uses Ink to drive a script-based chatbot similar to Alexa: https://github.com/rabidgremlin/Mutters

No technical write up but you can see how it all hangs together because we have open-sourced the core of what makes Oscar tick: https://github.com/rabidgremlin/Mutters

We use ML for Intent matching and NER and Ink to control the conversation state and flow. The core of this has been open sourced so you can see how we will the two together in practice here https://github.com/rabidgremlin/Mutters

I have been doing this with a large chatbot (350+ conversation topics,40k words of regionalized content) and it works fantastically well. Core of bot brain is open source https://github.com/rabidgremlin/Mutters

Check out https://github.com/rabidgremlin/Mutters It uses ML to figure out the "intent" of what the user has said (using a document classifier) and named entity recognition (NER) to extract data from the text (date, location etc). That is actually the easy part. The harder part is the conversation scripting and state handling. Mutters uses the Ink narration engine (originally designed for dialogue heavy games) for this. It works pretty well. IMHO :)

It's the "conversation" part that is really tricky... I have been working on a bot for a large Corp for the last few months and we have been using Inkle's Ink narration/dialog engine for this. Works very well. They let me open source the framework: https://github.com/rabidgremlin/Mutters it uses OpenNLP for intent identification and NER, Ink for conversation state and "scripting"