News for hackers. Stuff that matters.
Re:Avoiding NLP At All Costs by dmoney on Wednesday November 19, 2008 @07:35PM (#370144)
> An interesting side question is just how do people parse natural language in real time so accurately.

We have hardware support for massive neural nets:) I would guess that as we read/listen we speculatively build several different parse trees that could represent the sentence, eliminating each one when its probability (based on the implied semantics) falls too low.

Re:Avoiding NLP At All Costs by jimbokun on Thursday November 20, 2008 @09:22AM (#370602)
That sounds cool.

Do you have any references to research arguing this, or is it just your personal idea?

Re:Avoiding NLP At All Costs by dmoney on Thursday November 20, 2008 @09:49PM (#371418)
Just my idle speculation.