News for hackers. Stuff that matters.
Re:Shirt Without Stripes by rhizome on Monday April 20, 2020 @03:54PM (#22927781)
>The model just needs to be able to understand the important meaning of "no" in here, in the context of the whole sentence

It's easy to say, isn't it? Unfortunately, sticking the word "just" in there doesn't affect the difficulty. I do it all the time, too.

That said, "meaning" is not statistical.

Re:Shirt Without Stripes by waltpad on Monday April 20, 2020 @06:15PM (#22929345)
> That said, "meaning" is not statistical.

Are you sure of that? After all, we don't have all the same interpretation for every word in the dictionary. Ask a hundred person in the street - well perhaps not these days - the meaning of the word "meaning", how many different explanations will you get? And will you be able to reduce them all to the same "fundamental" meaning?

Re:Shirt Without Stripes by hammock on Monday April 20, 2020 @04:27PM (#22928134)
Why is it hard? Honestly. Add a "t" to "no" and you get a basic Boolean query.
Re:Shirt Without Stripes by gnulinux on Monday April 20, 2020 @05:42PM (#22928947)
Boolean queries aren't statistically analyzed; they're parsed and algebraically evaluate. So your point seems to support the opposite thing you're supporting.
Re:Shirt Without Stripes by hammock on Monday April 20, 2020 @06:32PM (#22929522)
Yeah I don't really know how github works. When I click the OP link I see a tiny bit of text and then three screenshots. Is there a whole article on this topic I'm missing?