Shirt Without Stripes • Hacker News Board

Re: Shirt Without Stripes

#241

Post by MadWombat » Mon, Apr 20, 2020, 6:15 PM UTC

bartread wrote: post #221

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.

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 just did a google image search for "person". The first 5 images were of Greta Thunberg. She must be the most representative person ever.

The next few images contained Donald Trump, Terry Crews, Bill Gates and a French politician named Pierre Person.

After that it was actually quite a varied mix of men/women and color/white people.

I am still not very impressed with Google's search engine in this aspect, but it is not biased in the way you suggest.

At least it is not biased that way for me. As far as I am aware, and I might be completely wrong here, Google, in part, bases its search results on your prior search history and other stored profile information. It is entirely possible that your search results say more about your online profile than about Google engine :)

Re: Shirt Without Stripes

#242

Post by skewart » Mon, Apr 20, 2020, 6:16 PM UTC

binarymax wrote: post #115

packetlost wrote: post #88

Earlier quoted context omitted.

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.

I work specifically in this field with clients, and deliver training on applying NLP to search. You’d be surprised how effective NLP is for use when identifying query intent, and pulling out modifiers that should apply as metadata filters. Weighted keyword search works a lot, but it fails hard for many long tail queries (especially in e-commerce and other attribute heavy domains). IMO there really isn’t a good excuse…

If it's technically possible then presumably it's a deliberate product choice to not have better search results for "shirt without stripes". And that seems entirely plausible.

Google is already by far the most widely used search engine, so they don't really need to innovate or improve the search product very much in order to attract and retain users. Presumably capturing more advertising spending from the companies paying for ads is a bigger priority.

Microsoft under Satya Nadella has been all about enterprise and cloud, and I doubt Bing is a strategic priority any more, so it's not surprising that they wouldn't put a lot of resources into making it better.

Amazon is a little surprising. You'd think they'd have a lot to gain from making it easier for people to find what they're looking for. But maybe less than perfect search results are deliberate? Maybe it's like how supermarkets put basic items in the back of the store and high-margin impulse buys in the front - so you have to walk past chocolates and chips if you want to buy a carton of milk.

If Amazon is deliberately nerfing search results then maybe Google would stand to benefit from having better shopping-related results - people would get frustrated trying to find a shirt without stripes on Amazon and just use Google instead, letting Google profit from advertising in the process. But maybe people selling shirts aren't willing to pay much for ads, so there isn't much money for Google to make by getting better at finding specific types of shirts.

I dunno if any of these conjectures are anywhere near accurate, but it's interesting to think about.

Re: Shirt Without Stripes

#243

Post by albertzeyer » Mon, Apr 20, 2020, 6:16 PM UTC

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 searches.

To extend on that, you can think of the human brain as just another (powerful) statistical model.

Re: Shirt Without Stripes

#244

Post by uoaei » Mon, Apr 20, 2020, 6:17 PM UTC

packetlost wrote: post #88

meritt wrote: post #13

The 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.

I agree, I think it's a better idea to improve the knowledge management (in terms of a relational hypergraph) before trying to create the bridge between the natural/digital knowledge representations. I have a hunch a good knowledge management system would be more amenable to being queried using natural language since relations are probably constructed similarly to the patterns we see in natural language syntax.

Re: Shirt Without Stripes

#245

Post by uoaei » Mon, Apr 20, 2020, 6:18 PM UTC

binarymax wrote: post #115

packetlost wrote: post #88

Earlier quoted context omitted.

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.

I work specifically in this field with clients, and deliver training on applying NLP to search. You’d be surprised how effective NLP is for use when identifying query intent, and pulling out modifiers that should apply as metadata filters. Weighted keyword search works a lot, but it fails hard for many long tail queries (especially in e-commerce and other attribute heavy domains). IMO there really isn’t a good excuse…

I feel like that's stretching the definition of NLP though. Technically you are processing natural language but it seems like you've found that doing essentially a keyword match but using certain keywords as more advanced filters rather than just search terms.

Re: Shirt Without Stripes

#246

Post by 6gvONxR4sf7o » Mon, Apr 20, 2020, 6:18 PM UTC

Lammy wrote: post #231

6gvONxR4sf7o wrote: post #153

Earlier quoted context omitted.

I suspect their job has gotten way harder. It's easy to forget that they aren't just passively indexing. The web is basically google's adversary, with every page trying to be top ranked regardless of whether it "should" be.

I think it's disingenuous to say "the web is basically google's adversary" when Google AdWords is the reason so many pages fight for top ranking.

Well sure, but I was hoping my narrow meaning would be clear: the search team operates in an adversarial environment.

Re: Shirt Without Stripes

#247

Post by wwarner » Mon, Apr 20, 2020, 6:19 PM UTC

I thought the minus prefix instead of "without" would exclude "stripes", but it doesn't (any more).

Re: Shirt Without Stripes

#248

Post by arcturus17 » Mon, Apr 20, 2020, 6:19 PM UTC

exhilaration wrote: post #181

rgovostes wrote: post #23

The point that the author is making, in a very understated way, is that all three companies have PR websites that breathlessly describe their advanced AI capabilities, yet they cannot understand a very simple query that young children can.

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?

Re: Shirt Without Stripes

#249

Post by arcturus17 » Mon, Apr 20, 2020, 6:20 PM UTC

shawnz wrote: post #162

michelpp wrote: post #144

Earlier quoted context omitted.

Because you want to sell shirts without stripes to customers who want them.

I expect most users genuinely looking for such a product would just search "plain shirt"

Like I said in another comment, this yields plenty of results that are not in fact plain shirts. Try for yourself on Amazon or Google.

Re: Shirt Without Stripes

#250

Post by paganel » Mon, Apr 20, 2020, 6:20 PM UTC

aerovistae wrote: post #123

This comment would go from "unreadable" to "interesting" if you had phrased it as: "Vaguely similar to a joke from _the movie_ Ninotchka that _the Slovenian philosopher_ Zizek often uses...." Give people context. Don't assume people know what you know.

People on an website like this should at least have a general idea of who Zizek is. I've never yet read any of his books but as a guy living in the Balkans this short clip [1] of Zizek explaining the geography that separates Central Europe from the Balkans is one of the best things on YT.

[1] https://www.youtube.com/watch?v=bwDrHqNZ9lo