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

461–470 of 639 posts

Re: Shirt Without Stripes

#461

Post by kaetemi »

sonar_un wrote: post #270
seiferteric wrote: post #137

I 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…

I have also found that search results are getting frustratingly worse. Often even when I put in explicit search terms and quotes, and filter out words that I don't want, Google will return results that don't adhere to what I am looking for or just return no results at all. I remember when I would search for something and find much more relevant information. Now the first 5 or 6 search results are ad-sponsored and are…

Page 1: About 189,000 results (0.35 seconds)

Page 2: Page 2 of about 86 results (0.36 seconds)

It seems they're really just trimming the web.

Re: Shirt Without Stripes

#462

Post by bscphil »

DenisM wrote: post #311
js2 wrote: post #299

Earlier quoted context omitted.

I'd call it windowless: https://www.google.com/search?q=windowless+skyscraper&tbm=is...

You missed the Seattle Tower Building. It has windows, but very little in the way of visible glass. https://www.emporis.com/buildings/119453/seattle-tower-seatt... Windowless is a superset of glassless.

To be clear (for the benefit of anyone else who reads this), the windows in the Seattle Tower are made of glass, but the exterior of the building is not that modern all-glass-and-steel look[1]. This is a third interpretation of non-glass I hadn't thought of and it took me a minute to figure it out.

"non-glass skyscraper":

1. No glass used in the exterior construction at all -> implying no windows

2. No glass used in the exterior construction at all -> implying the windows are made out of something other than glass

3. A skyscraper in which glass is not a prominent architectural feature, but the building does contain features like windows and doors that contain glass. (This comment)

[1] https://en.wikipedia.org/wiki/Wilshire_Grand_Center

Re: Shirt Without Stripes

#463

Post by tcgv »

albertzeyer wrote: post #437
alberth wrote: post #409

Earlier quoted context omitted.

The # 1 google result for “Shirt without stripes” is this very own HN post https://www.google.com/search?q=%22Shirt+without+Stripes%22&

I guess, even in the original results, the problem is not really that Google search was not understanding the meaning of the search term (which is possible with today's models). Rather, it was a bit confused about what you are really searching for here. Maybe a comparison of shirts with and without stripes? The search query was just unusual, and it is not too unreasonable to guess that the query was not meant literal…

> the problem is not really that Google search was not understanding the meaning of the search term (...) Rather, it was a bit confused about what you are really searching for here. Maybe a comparison of shirts with and without stripes?

In this very specific case I don't buy it. Sure, it probably applies for other queries, but if you approach a salesperson and ask him for "shirts without stripes" it's pretty clear what you want, and he wont bring you any piece with stripes on it.

Re: Shirt Without Stripes

#464

Post by cfv »

While I'm sure this is A Hard Problem to solve by NLP I for whatever reason was under the impression that this is trivial to special-case.

As in, "X without Y" sounds like a common enough use case to have it's own little parser branch in places as big as Google or Amazon

Re: Shirt Without Stripes

#465

Post by aaron695 »

Not sure if people actually search for "Shirt Without Stripes" or this was picked for academia over what is actually needed

But make a script that scrapes the top X results for these sites. Get your own AI / humans to rate it.

Make it competitive for these large sites give them an incentive.

Re: Shirt Without Stripes

#466

Post by hbosch »

cfv wrote: post #464

While I'm sure this is A Hard Problem to solve by NLP I for whatever reason was under the impression that this is trivial to special-case. As in, "X without Y" sounds like a common enough use case to have it's own little parser branch in places as big as Google or Amazon

I mean, if I google the phrase "shirts -stripes" and click the Images tab I see mainly shirts without stripes.

So it's essentially the same input, and essentially the same expected output, but there must be quite a knot between understanding the word "without" and literally just using the - operator.

Re: Shirt Without Stripes

#467

Post by wooders »

We're a company coming out of the YC W20 batch working on the product attribution problem http://glisten.ai/.

There's too many products nowadays to be manually attributed (e.g. pattern=stripes), making it hard return good results even with entity resolution for queries. We train classifiers to categorize products, including what something is not, using their images and descriptions.

Re: Shirt Without Stripes

#468

Post by notatoad »

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.

all three of these search engines offer "voice assistant" platforms that encourage you to speak to them in natural language, and send your query to the search engine verbatim under a broad set of circumstances.

Re: Shirt Without Stripes

#470

Post by _bxg1 »

zerd wrote: post #446
pbhjpbhj wrote: post #414

Earlier quoted context omitted.

Lexical analysis is surely clever enough to make "no evidence" and "no cancer" the atoms used and should even differentiate "no cancer" from "no, cancer" pretty easily? Are we really still at 80s chatbot level functionality when it comes to string parsing? Related aside: It frustrates me no end that spellcheck still doesn't appear to use any probablistic considerations, like Markov chains, to determine the intended w…

The general problem is much harder than that. You need to understand double negatives, when do they invert the meaning and when do they underline it? "Ain't nobody got time for that" can be interpreted in different ways. And then you need to understand sarcasm. Then a later sentence can invert the meaning of an earlier one. E.g. "This is the best movie ever. Said no one". Using word-pairs as features is easy, but the…

It gets even harder than that: https://en.m.wikipedia.org/wiki/Winograd_Schema_Challenge

For example:

"The city councilmen refused the demonstrators a permit because they advocated violence."

Which party is "they"? There is no lexical information that can possibly answer this question. It depends entirely on an actual understanding of what "city councilmen" and "demonstrators" (in the context of city councilmen and permits!) are, and which one would be more likely to be advocating violence (and in which case that would lead to a permit denial).

Background: Until recently I worked at a symbolic AI company who was tackling this problem. I myself didn't work on this problem directly, but I became 100% convinced that their approach, while a long shot, was the only conceivable way of solving it in a fully generalized way.

Post reply on HN