Tried this on amazon.ca (instead of .com) and got quite a different, but also amazing, result...
https://www.amazon.ca/s?k=shirt+without+stripes&ref=nb_sb_no...
Shirt Without Stripes
401–410 of 639 posts
Re: Shirt Without Stripes
#402Earlier quoted context omitted.
Which part of "The paper I linked to below describes a technique they call "deep parsing." Check it out for more context." could you not parse? I mean if us humans have a difficulty parsing each other's statements, then why should machines do any better?
The number of humans that would have difficulty parsing "shirt without stripes" is very very low.
I keep trying to talk about the general problem and people keep focusing on this one example. I give up. :)
Re: Shirt Without Stripes
#403It seems to me that the problem isn't so much that this search performs incorrectly. Rather it is that many search engines have removed the tools that allowed a user to specify exactly what they are looking for (e.g. shirt -stripes).
Re: Shirt Without Stripes
#404Earlier quoted context omitted.
I disagree, "shirt without stripes" is an unusual word choice, not one that our ML models would be optimized for. Try "solid color shirt" and you'll see how much better the results are - at least on Google.
I searched "plain dress shirt" and similar terms on Amazon and Google, and they returned plenty of shirts with stripes and checkered patterns. How am I supposed to explicitly search for a shirt without stripes, then?
I would go in a store and search there. Not everything has to be solved by tech and AI. This is a prime example of a problem that requires insane amount of work and yet provide absolutely no value to the world.
People still think we will have self driving cars "in two years" yet here we are talking about dumb shirts. AI winter is coming
Re: Shirt Without Stripes
#405One time I ordered from stitch fix and asked for “a shirt which is not red, white, and blue” and got a red, white, and blue shirt.
Re: Shirt Without Stripes
#406I have noticed in the past few years google results have become noticeable worse for similar reasons. Google used to _surprise_ me with how good it was able to understand what I was really looking for even when I put in vague terms. I remember being shocked on several occasions when putting in half remembered sentences, lyrics, expressions from something I had heard years ago and it being the first! result. I almost…
Imagine if somehow it would be possible to pick any release and search with that.
Re: Shirt Without Stripes
#407Earlier quoted context omitted.
While this is indeed an example of the attribution problem, I'd argue that this particular query will never be solved. I don't search for a "shirt without stripes", I search for a "solid shirt, or a " hawai'ian shirt". I'd be curious to see how many sentences with attribution problems actually have other structural issues. If I want to write clearly and without ambiguity, I rewrite sentences that have these problems.…
>If I want to write clearly and without ambiguity, I rewrite sentences that have these problems. Why wouldn't I do the same for search queries? Ok, so imagine one online retailer follows your advice and expect the users to write clear and unambiguous queries, while another retailer puts extra effort into attribution. Which one will make more money?
Great question, but with potentially nonintuitive results.
A sales gimmick furniture store would use in the past was to offer customers a free gallon on ice cream for visiting the store. The value was to the store offering the promotion, as shoppers would be drawn to the "free" gift, but on receiving the ice cream -- too much to eat directly. -- would then have to go home to put the dessert in the freezer. And have less time to comparison shop at competing merchant's stores. Given limited shopping time (usually a weekend activity), this is an effective resource exhaustion attack.
Similar tricks to tie up time, patience, or cognitive reserve are common in sales. For a dominant vendor, tweaking the hassle factor of a site so long as defection rates are low could well be a net positive, if it makes the likelihood of a visitor going to other sites lower.
Re: Shirt Without Stripes
#408Interestingly, Google can handle these searches just fine... "birds without flight" "cars without wheels" "cats without tails" "dogs without hair" "intersections without lights" "poems without rhyme" "shirts without collars" (also "sleeves", "shoulders", "buttons", "logos", "pockets", and more)
That's because all these things are readily labelled by humans as such. So they don't have to understand the sentence. Just match it.
I somewhat agree, but for me personally, "car without wheels" and "shirt without stripes" are about equal in terms of usage regularity.
I'd also say nobody uses the phrase "birds without flight", but instead "flightless birds".
I'd imagine people say "hairless dogs" a lot more often than "dogs without hair".
And the shirt examples show that there are many uses of the lead phrase "shirts without" that work just fine, but for some reason "stripes" really stands out far beyond the others. "Shirts without shoulders" is kind of a bizarre term to match, when almost all search results show "off the shoulder" or "cold shoulder" as the thing being matched.
Re: Shirt Without Stripes
#409This 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…
The # 1 google result for “Shirt without stripes” is this very own HN post
https://www.google.com/search?q=%22Shirt+without+Stripes%22&
Re: Shirt Without Stripes
#410Earlier quoted context omitted.
At least this is relatively innocuous. Until recently if you did a Google Image Search for "person" or "people", it only showed white men.
I couldn't quite believe your comment when I read it so I did a Google image search for "person" and the results weren't a lot better than you'd suggested. Mostly white men, a few white women, a very few black women, a handful of Asians, and multiple instances of Terry Crews. The net result of that Google search, combined with the "Shirt Without Stripes" repo, leaves me even more unimpressed with the capabilities of…
I tried this as well in an incognito window on Firefox and got the results you mentioned. I notice, however, that virtually all of the results have associated text containing the word person. It seems likely that Google image search featurizes photographs to include surrounding document context.
(That's how I would do it if I wanted more accurate rather than more general results.)