Machine learning won't solve natural language understanding

Re:Machine learning won't solve natural language understanding by danielmarkbruce on Monday August 09, 2021 @10:08PM (#28124509)

I'm not a physicist or mechanical engineer and this is a genuine question - why would we not be able to reliably design anything if we only had statistical models? Empirical formulas are used in various places in science/engineering and seem to work well (with exceptions). As an example - would we not arrive at something like f = ma using statistics and then use it without really knowing why (or maybe all the implications of) f = ma?

[ Parent | on HN ]

Re:Machine learning won't solve natural language understanding by ivalm on Tuesday August 10, 2021 @03:18AM (#28125969)

I think the main issue is interpolation vs extrapolation. Statistical models work well within the domain where data is available but have trouble generalizing to where data is unavailable. The very cool thing with physics is that theory was able to make a lot of true but wild predictions that only much later were backed up with experiment. Such powerful theories are very useful for finding interesting phenomena to study/exploit

[ Parent | on HN ]

Re:Machine learning won't solve natural language understanding by danielmarkbruce on Saturday August 14, 2021 @12:32AM (#28177926)

I'm saying "does it matter how we arrive at a model?".

[ Parent | on HN ]