2 replies to this topic

[garma]

Hello folks,

I'm looking for a way to match simple linguistic expressions such as:

1. The red light is on
2. A red sign is activated

I've looked into natural language processing but this might be over the top. I am not looking for an exact match per sé, a probability is good enough. My system will have to learn from correct or incorrect associations, so if a match between

1. The red light is on
2. The red light is activated

is correct, the association between 'on' and 'activated' will be stronger.

I can think of some ways to do it but I can't imagine I'm the first to try this so if you guys have any pointers for me that can get me started I'd be most thankful.

Thanks!

[monjardin]

I really don't know much about this field, but the old SHRDLU project is probably worth checking out. The source code is available too (written in LISP if I recall correctly).

[synd66]

monjardin said:

I really don't know much about this field, but the old SHRDLU project is probably worth checking out. The source code is available too (written in LISP if I recall correctly).

Nice link monjardin Thanks