Skip to content

Meta-Guide.com

Menu
  • Home
  • About
  • Directory
  • Videography
  • Pages
  • Index
  • Random
Menu

What’s the best way to start training my AIML chatbot?

Posted on 2016/07/222016/08/23 by mendicott

What’s the best way to start training my AIML chatbot?

> github.com/pandorabots/rosie

Typically, AIML “training” begins with monitoring the chat logs, which consist of question-answer pairs. Whenever you see inappropriate answers, or null answer types, you start entering correct, or better ones manually. For this reason, I call AIML “artisanal’, or in other words “handmade”. I am not aware of anyone who has successfully attached machine learning to AIML chat log question-answer pairs; however, theoretically it should be possible. Attaching machine learning to AIML chat logs would not improve the content quality, or add domain expertise.

Domain expertise , also known as “domain knowledge”, is basically the automation of human expert knowledge, which is somewhat related to the now largely antiquated “expert systems” of yore. Domain engineering is perhaps a subset of knowledge engineering. Applying domain expertise to AIML is more art than science. There is not a good way to apply decision trees to AIML (see also decision support system). If you are not careful with AIML, you can add a lot of knowledge that will be inaccessible due to looping at higher levels, in effect trapping your knowledge below more simple concepts.

Popular Content

New Content

 

Contents of this website may not be reproduced without prior written permission.

Copyright © 2011-2025 Marcus L Endicott

©2025 Meta-Guide.com | Design: Newspaperly WordPress Theme