Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Shirt Without Stripes

github.com

Post reply on HN
Print view View original

571–580 of 639 posts

Re: Shirt Without Stripes

#571

Post by Hitton »

arcturus17 wrote: post #248
exhilaration wrote: post #181

Earlier 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?

Just searched same on google and first non-plain shirt was in the second hundred. Duckduckgo was similar. Considering that they classify images according to surrounding text, it seems like pretty good result.

Re: Shirt Without Stripes

#572

Post by zelphirkalt »

DenisM wrote: post #197

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…

> you have a "no" or "without" in the sentence, but you don't know where it belongs

Well, one could argue, that it belongs exactly where anyone entering the query put it. Before "stripes".

The problem is often, that search engines try to be too clever, while not offering any kind of switch "exactly those words in this order" and that is just a bad user interface.

Re: Shirt Without Stripes

#573

Post by V-2 »

I believe the future of AI, as showcased by this simple usecase, is not one central AI such as Google search engine recognizing the context, but rather each of us having a "smart assistant" with a personalized, trained understanding of the contexts that we mean.

And it's only that smart assistant that automates coping with the deficiencies of a one-size-fits-all central solution, finding me shirts with no stripes by using a rather dumb search engine. (Or "a pizza I would like", etc.)

Re: Shirt Without Stripes

#574

Post by disqard »

c3534l wrote: post #485

If you select "I don't like this recommendation" for a video on youtube, you will get to provide feedback on why you did so: either "I don't like this video" or "I've already watched this video." I've pressed the latter on literally thousands of videos at this point, and after well over a year of this, YouTube still hasn't figured out that I don't want to be recommended videos that I've already watched. Likewise, Goo…

My experience has been that most ads that "follow me around" peddle the exact same thing I purchased most recently. No, I will not buy a second electric kettle again, let alone the exact make and model that I now own. I'd rather have generic ads, so I might discover some new product that I could (at least in theory) actually buy.

Re: Shirt Without Stripes

#575

Post by disqard »

scabarott wrote: post #104
hrktb wrote: post #41

Earlier quoted context omitted.

I am amazed at the amount of things people are willing to treat as "solved problem". At a point there was a TED talk explaining social networks were a solved problem now that facebook was dominant. Recycling was seen as solved problem until it wasn't etc. I wonder how many actual "sovled problems" we have.

Reminds me of this: https://www.amazon.com/End-History-Last-Man/dp/0743284550

Thank you for that reference. It's astonishing how "experts" can construct complex frameworks for justifying their personal failure of imagination.

Re: Shirt Without Stripes

#576

Post by blauditore »

belorn wrote: post #443
Alex3917 wrote: post #212

Earlier 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.

One can play this game a lot and most results will return expected cultural biased results. A "kind person" is apparently a white girl. A "good person", a white woman. A "bad person", white men. A "evil person", white men. A "honest person", equal mix of white women and white men. "Dishonest person", white men in suits. "Generous person", hands of white women. "Happy person", women of color. "Unhappy person", old whi…

FWIW, this is most likely not a bias of the search engine, but just a reflection of its sources (mostly stock image platforms I suppose). So if most stock images of blue trolls would be labelled with "politician", you'd eventually find blue trolls when searching for "politician".

Re: Shirt Without Stripes

#577

Post by Myrmornis »

reubenmorais wrote: post #556
danielscrubs wrote: post #554

Earlier quoted context omitted.

Reminds me of the confusion with negatives and languages: -Vill du inte ha glass? [Don't you want ice cream?] -はい [Yes] Does she want ice cream? Answer: No, she doesn't. I added a not, so she's reversing the answer as Japanese people do. The number of times I've been dumbstruck by this is larger than I'd like to admit, and I'm a coder.

English has similar confusion even for plain, non negated questions. Q: "Do you mind if I sit here?" A1: "Not at all!" A2: "Sure!" Both are valid answers and mean the same thing, the person asking is welcome to sit there. This has always amused me.

Definitely what you say is the accepted meaning. But wouldn’t you say A1 is more correct than A2? Possibly relevant, there’s also

A3: “Sure I do, last time you sat next to me you wouldn’t shut up.”

Re: Shirt Without Stripes

#578

Post by pgcj_poster »

jedberg wrote: post #394
holler wrote: post #313

Earlier quoted context omitted.

I've noticed this too, and frequently wonder why there aren't new and better search startups...

There are, like DuckDuckGo. But the first complaint is usually "their results aren't as good as Google" and that's because Google in reality still gives better results because of their (lack of) privacy. People want better results but don't want to be tracked, and those things are in opposition to each other.

I think the only time Google still reliably gives better results than Duckduckgo is for non-English languges (which Qwant is good for), or when Google has something indexed and Bing/DDG does not.

But taking it as a given the Google's results are better, is that really because of lack of privacy, or just because of how Google has been pouring more money and talent into the problem longer than anyone else? Because I'm not convinced that personal data is particularly useful for generating search results. The example they always give is determining whether a search for "jaguar" means the cat or the car. But that always seemed silly to me, because most searches are going to give extra context to disambiguate ("jaguar habitat"), and even they don't, the user is smart enough to type "jaguar car" if they're not getting the right results. Further, Google doesn't actually know whether I'm more interested in cars or cats—it justs know that I'm a woman in college, so it guesses that I'm less interested in cars. Is that really so useful?

Does searching Google through Tor give noticeably worse results than searching google while logged in? I would be genuinely surprised if it did.

Re: Shirt Without Stripes

#579

Post by NumberCruncher »

joshspankit wrote: post #342
DenisM wrote: post #197

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…

Yes, you have points, but they break down here: “Shirt -stripes” is unambiguous to a system, yet the first result on Amazon(.ca) is a striped shirt, and the 3rd is sweatpants.

it works on google pretty well for me

Re: Shirt Without Stripes

#580

Post by dkdbejwi383 »

transreal wrote: post #220

Searching "men without pants" versus "men with pants" gives much better results. This is a case where, while it makes sense to say the sentence, it's not a common use of language, and at the end of the day, the search engine will find what's written down, it's not a natural language processor yet (despite any marketing). Shirt stores don't advertise "Shirts without stripes - 20% off", they describe them as "Solid shi…

Similarly, "sandwich with cheese" is probably going to return more relevant results than "sandwich without scorpions"
Post reply on HN