361–370 of 639 posts
Earlier quoted context omitted.
It's a tricky balance between sales and relevance. If you don't watch for relevance you will end up showing only booze and porn in the commerce search results, border-line-porn in video search (true story), and so on. edit: fixed typo born -> porn
Could you explain the border-line-born bit? I don't get it.
Earlier quoted context omitted.
Ah, but you see, he specifically wants a shirt without stripes as dialectically opposed to a shirt with stripes. A plain shirt just won't do. See: https://www.youtube.com/watch?v=wmJVsaxoQSw
If there's a dialectic here, does that mean there is a synthesis state between stripes and non-stripes? Is it polka dots?
This problem is known as "attribution" - you have a "no" or "without" in the sentence, but you don't know where it belongs. One could (and one does) argue that the problem cannot be solved with statistical methods (ML), especially not in any domain where accuracy is required, such as medical recored analysis: "no evidence of cancer" and "evidence of no cancer" are very different things. Zooming out, the language fiel…
> "no evidence of cancer" and "evidence of no cancer" are very different things.
Why is it not as simple "no belongs to the word it precedes" ? like unary operator, ! (not), in typical computer languages.
This problem is known as "attribution" - you have a "no" or "without" in the sentence, but you don't know where it belongs. One could (and one does) argue that the problem cannot be solved with statistical methods (ML), especially not in any domain where accuracy is required, such as medical recored analysis: "no evidence of cancer" and "evidence of no cancer" are very different things. Zooming out, the language fiel…
less than lay person, but in your example > "no evidence of cancer" and "evidence of no cancer" are very different things. Why is it not as simple "no belongs to the word it precedes" ? like unary operator, ! (not), in typical computer languages.
Earlier quoted context omitted.
OK, but what if an Amazon algorithm has actually learned that people who search for "shirt without stripes" are more likely to buy more things if the first image they see is a picture of a striped shirt?
Isn't this just a version of "God works in mysterious ways" applied to AI? "The AI works in mysterious ways. Trust it."
https://www.google.com/search?q=plain+shirt https://www.amazon.com/s?k=plain+shirt on edit: https://www.google.com/search?q=shirt+-stripes
Yeah... As expected, negating the stripes on that last google search makes no apparent difference for me, and "plain shirt" has an entirely different meaning from "shirt without stripes".
not that there aren't a couple of striped shirts in there, but nothing like otherwise. So I mean, there is an extremely apparent difference from me, even though there is not the perfect result you might wish for.
This problem is known as "attribution" - you have a "no" or "without" in the sentence, but you don't know where it belongs. One could (and one does) argue that the problem cannot be solved with statistical methods (ML), especially not in any domain where accuracy is required, such as medical recored analysis: "no evidence of cancer" and "evidence of no cancer" are very different things. Zooming out, the language fiel…
less than lay person, but in your example > "no evidence of cancer" and "evidence of no cancer" are very different things. Why is it not as simple "no belongs to the word it precedes" ? like unary operator, ! (not), in typical computer languages.
You'd also have quite a bit of fun trying to parse the phrase "no means no" or other usages where "no" is being used as a noun... And for bonus points, folks talk to search engines in broken english all the time so "shirts no single striped" is a totally reasonable query to submit to a server and expect to be parse-able.
Earlier quoted context omitted.
"there is no evidence of cancer" and "there is evidence of no cancer" are two different statements with different meaning, so it's more complex a task than just understanding the importance of "no" in a sentence. It's involves semantic analysis of the sentence. The paper I linked to below describes a technique they call "deep parsing." Check it out for more context.
Yes, sure, exactly. It's a complex task. I'm just saying that there is no reason why a statistical model should not be able to solve the task. And you seem to agree on that. You even linked such a method.
Earlier quoted context omitted.
Isn't this just a version of "God works in mysterious ways" applied to AI? "The AI works in mysterious ways. Trust it."
It's the efficient markets hypothesis applied to AI. "If the AI could make more money by showing something else, it would be showing something else".
Why should it not be possible to solve this with statistical methods? The model just needs to be able to understand the important meaning of "no" in here, in the context of the whole sentence. I would guess that most modern NNs from the NLP area (Transformer or LSTM) would be able to correctly differentiate the meaning. The problem is, I think there is no fancy NN (yet) behind Google search, and the other web searche…
Chomsky: Statistical analysis of snowflakes falling outside the window may predict the next snowflake, but it will do very little for weather prediction, and nothing for climate analysis.
Norvig: Give us enough data and we will get close enough for all practical purposes.