My Operating Systems professor (Tomasz Jordan Kruk, PhD) in college had an appropriate anecdote for this:
"Humans usually don't intuitively understand the word 'no'. Please imagine a non-pink elephant."
Shirt Without Stripes
81–90 of 639 posts
Re: Shirt Without Stripes
#82Re: Shirt Without Stripes
#83Proof that SELECT with GROUP BY doesn't work if your tags aren't correct.
Joking aside, it doesn't surprise me that this isn't being picked up — aren't most of these AI teams more R&D than actual public-facing? Maybe I'm just cynical though.
Re: Shirt Without Stripes
#84To me, the most interesting implication here is that this must not adversely affect Google's ad revenue. If it did, they would surely fix it. This, in turn, means that apparently we have been trained to interface with search engines such that this is not a problem. Sometimes I wonder how much my brain has changed to use search engines / how much of it is dedicated to effective googling. Makes me feel like a cyborg.
I suppose that's a base of why 'Google fu' and 'Googling skills' are such common phrases.
Knowing how the machine will interpret humans is just as important to finding your results.
Re: Shirt Without Stripes
#85I worked on an ingredient parser a few years ago. This exact kind of thing made things a lot more difficult than they seemed at first.
Re: Shirt Without Stripes
#86Re: Shirt Without Stripes
#87https://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
So the - is working, contrary to the claims of several people here. The bottom line is that it is super easy to get results with shirts that don't have stripes, if you don't expect your search engine to understand English (which it would be wildly unrealistic to expect, and, besides, is not what you want).
Re: Shirt Without Stripes
#88The point of this isn't asking how to apply boolean search operators, it's showing that the largest AI-focused companies in the world absolutely suck at NLP.
Why would you really apply NLP to a search engine though? Generally speaking a weighted keyword search is good enough 95% of the time and requires significantly less resources to perform.
Re: Shirt Without Stripes
#89My Operating Systems professor (Tomasz Jordan Kruk, PhD) in college had an appropriate anecdote for this: "Humans usually don't intuitively understand the word 'no'. Please imagine a non-pink elephant."
Maybe you mean, "Please don't imagine a pink elephant." Imagining a non-pink elephant seems pretty easy.
Re: Shirt Without Stripes
#90Earlier quoted context omitted.
When you search for “shirt without stripes” you expect and hope to get shirts and t-shirts with stripes?
I would prefer results containing words "shirt", "stripes" and "without". I don't want search engines to freely interpret my query and guess what I probably wanted to see while burying exact results in hundreds of pages of useless garbage.
> and guess what I probably wanted
How is interpreting "shirts without stripes" as "I wish to see shirts that don't have any stripes" guessing?
I would venture to say that most people (meaning your use case is in the minority) who type "shirts without stripes" want to see results showing shirts without stripes not results "containing words "shirt", "stripes" and "without".
I think what is happening here is that you know how search engines work and so you are conditioned to expect them to do what they're doing.