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

41–50 of 639 posts

Re: Shirt Without Stripes

#41

Post by hrktb »

slaymaker1907 wrote: post #8

I think that this is actually really encouraging in showing that we still have a ways to go in improving search engines. A lot of people treat search engines as a solved problem, at least for non-question answering aspects.

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.

Re: Shirt Without Stripes

#42

Post by wkyle »

Vaguely similar to a joke from Ninotchka that Zizek often uses about the difference between 'coffee without cream' and 'coffee without milk'. He usually uses it to reference the concept of negation in the Hegelian dialectic, but he's also mentioned the difficulty of computers understanding negation in the context of the coffee/cream example.

The joke from Zizek: https://www.youtube.com/watch?v=wmJVsaxoQSw

Re: Shirt Without Stripes

#44

Post by leephillips »

Ugohcet wrote: post #37
enumjorge wrote: post #19

Earlier 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.

Exactly. Those who want the search engine to "understand" what they are asking for when they use words like "without" may not have thought through the unintended consequences. For there is no combination of search terms that might not be interpreted in a variety of ways that the searcher never imagined, because of the ambiguity of natural language. Better to learn and use search operators, and the strategies of careful choice of keywords.

Re: Shirt Without Stripes

#45

Post by alexpapworth »

Justin_K wrote: post #20
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.

I'd go as far as saying "AI" is only as good as someone has taken the time to program the use case.

So, it's really just a series of if statements?

Re: Shirt Without Stripes

#46

Post by 1f60c »

leephillips wrote: post #30
phalangion wrote: post #7

Earlier quoted context omitted.

Still includes some shirts with stripes, since the search is now just for shirts that don't explicitly mention stripes.

That's not what the - operator is supposed to do. It's supposed to suppress pages containing the keyword after the -.

And parent is saying it isn't working. (It doesn't work for me either.)

Re: Shirt Without Stripes

#47

Post by Ugohcet »

coldtea wrote: post #29
leephillips wrote: post #26

Earlier quoted context omitted.

Yes. I expect to get results that contain the keywords "shirt", "stripes", and "without", but perhaps with the last term ignored. Why, what would you expect? Would you search for "shirts that don't have stripes"? Or "shirts lacking stripes"?

> Why, what would you expect? I'd expect to see some of the much touted "search intelligence", NLP, term inference, vector term analysis, and AI in action...

Google started doing that with its regular search queries several years ago. There are thousands of complains on HN about how it's almost impossible now to find anything without "quoting" "every" "word" "of" "your" "query".

Re: Shirt Without Stripes

#48

Post by mabbo »

It's not enough to say "Oh, we should add a rule that 'without' means negate the next word" because that only applies to this one situation, in this one language. Let's generalize the problem: We aren't correctly translating from English (or other spoken languages) to Computer/Logic.

The state of the art in machine translation (from what I've read at least) is translating from language-A to a language-less "concept space" and then from there to language-B. Could that be done where the output language is something a search engine can use to find what you want correctly?

Given that pattern, I suspect we could see much better results in cases like this.

Re: Shirt Without Stripes

#49

Post by MattRix »

bentona wrote: post #28

To 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.

There are lots of things Google could do improve their search and ad revenue that they haven't done yet.
Post reply on HN