[alicebot-general] assistance with an AIML idea

[traltixx]

Hi,
Im using python for my bots that use AIML and I was wondering about
something. I usually keep logs of what my bot says and its responses from
other people. Now what Im thinking is having another python script that goes
through these responses and generate or update its current AIML markups
based on reversing the roles of responses and the statements by and from the
responder (does this make sense?)
For example if someone asked if today is sunday and the bot's response is
that it doesnt know and the responder tells it to ignore it. The script will
update the AIML so that if someone tells the bot that they dont know what
day it is today, the bot will tell them to ignore it.
 
Has this been done before? Im just thinking in a very general manner here,
im sure there are alot of ways in which this can be improved.
Any comments or thoughts or obstacles with this aside from the obvious
overfitting/overspecialized AIML; but I intend to counter this with more
general chats.
Cheers
-- 
View this message in context: http://www.nabble.com/assistance-with-an-AIML-idea-tp15517177p15517177.html
Sent from the Alicebot General mailing list archive at Nabble.com.