Artificial Intelligence Markup Language
This project was placed on a back burner soon after successful deployment of the first ChatBot. What became obvious: developing content (what the bot would say) would be the greatest challenge in developing an interactive tutor-bot. Content is King, even in the metaverse.
The development of an intelligent tutor-bot will require a thorough understanding of the structure and syntax of AIML. The following links lead to specific topics in the documentation for AIML, found at ALICE and AIML Documentation page at alicebot.org:
- AIML Primer
- Document by: Thomas Ringate, Contributing Authors: Dr. Richard S. Wallace; Anthony Taylor; Jon Baer; Dennis Daniels
- AIML Overview
- “AIML, describes a class of data objects called AIML objects and partially describes the behavior of computer programs that process them. AIML objects are made up of units called topics and categories, which contain either parsed or unparsed data.”
- AIML 1.0.1 Tag Set
- “The tags in this table correspond to the set of AIML Tags adopted by the AIML Architecture committee for the Artificial Intelligence Markup Language (AIML) Version 1.0.1 A.L.I.C.E. AI Foundation Working Draft, 18 February 2005 (rev 007).”
- AIML Reference Manual
- This document is a “work in progress”
- Symbolic Reductions in AIML
- This document assumes some working knowledge of AIML, [the] software XML language for writing chat robots.
- A Tutorial for adding knowledge to your robot
- “…short tutorial describing how to create and add knowledge to your Robot. A successful Robot will appear human. Your goal as the botmaster is simple: build content that induces the client to carry on conversations with your Robot as long as possible. Do this by creating a variety of potential answers to various questions, or re-directing a conversation to new topics that the client finds interesting – always with the goal of continuing the interactions as long as possible.”
- AIML Pattern Matching Simplified
- Here is an ongoing series of explanations of how the Graphmaster works, for those who want to build their own or simply want a deeper understanding of the approach.
Questions:
- What interactive behaviors – other than the textual response of a template – can be implemented in facilitating a learning session? Can the bot open a browser? …initiate a search in Google? …Wikipedia? …Dictionary.com? Can the bot launch an application, passing keywords to be used by that application? Is Program D the tool for this interactivity?
- Can the Pandorabots site be utilized to begin the development of a tutor-bot AIML set, and can that set then be imported into Program D?
- How does one attract users to cooperatively construct a worthy AIML-set for use in a tutor-bot?