Why is this a Github repo? I can't get past the abuse of a git repository.
Shirt Without Stripes
321–330 of 639 posts
Re: Shirt Without Stripes
#322This 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…
I am little surprised with this result. When I worked on similar products we constantly look at our query stream, sorted the high volume queries and manually intervened to present better results to our users. I will not be surprised millions of dollars are being lost because of this substandard query result per year.
I think these hyper-companies are really attached to doing things "at scale" and sometimes, or even often times, they get carried away with that.
Re: Shirt Without Stripes
#323Not surprising. Also, "shirt -stripe" might product better results.
Re: Shirt Without Stripes
#324On a meta note, I am a bit tired of HN submissions being used more as "Writing Prompts" rather than as links to substantive material.
This thread is an excellent example. The author of the linked page didn't have the decency to actually make a substantive point, instead sharing three screenshots and posting the link here, chumming the HN waters with the kind of stuff that brings in the sharks from far and wide.
Bashing on big cos: Check
Vague pronouncements about AI: Check
Generic side-swipes about 'ad revenue': Check
This is why a coherent thesis is required to even initiate a proper discussion, because in the absence of that it invariably devolves to lowest-common-denominator shit-flinging.
Re: Shirt Without Stripes
#325Earlier quoted context omitted.
The point of the OP is that they claim they understand everything. Example: https://www.blog.google/products/search/search-language-unde...
OK, but what if an Amazon algorithm has actually learned that people who search for "shirt without stripes" are more likely to buy more things if the first image they see is a picture of a striped shirt?
It's a tricky balance between sales and relevance. If you don't watch for relevance you will end up showing only booze and porn in the commerce search results, border-line-porn in video search (true story), and so on.
edit: fixed typo born -> porn
Re: Shirt Without Stripes
#326Earlier quoted context omitted.
The point of the OP is that they claim they understand everything. Example: https://www.blog.google/products/search/search-language-unde...
OK, but what if an Amazon algorithm has actually learned that people who search for "shirt without stripes" are more likely to buy more things if the first image they see is a picture of a striped shirt?
OK, what if not?
See, your comment makes no sense
Re: Shirt Without Stripes
#327As others have pointed out, most search engines don't support natural language search in general, let alone natural language negation in particular.
There are several reasons for this, including the following:
1) Natural language understanding for search has gotten a lot better, but it is still not as robust as keyword matching. The upside of delighting some users with natural language understanding doesn't yet justify the downside of making the experience worse for everyone else.
2) Most users today don't use natural language search queries. That is surely a chicken-and-egg problem: perhaps users would love to use natural language search if it worked as well or better than keyword search. But that's where we are today. So, until there's a breakthrough, most search engine developers see more incremental gain from optimizing some form of keyword search than from trying to support natural language search.
3) Even if the search engine understands the search query perfectly, it still has to match that interpretation against the documentation representation. In general, it's a lot easier to understand a query like "shirt with stripes" than to reliably know which of the shirts in the catalog do or don't have stripes. No one has perfectly clean, complete, or consistent data. We need not just query understanding, but item understanding too.
4) Negation is especially hard. A search index tends to focus on including accurate content rather than exhaustive content. That makes it impossible to distinguish negation from not knowing. It's the classic problem of absence of evidence is not being evidence of absence. This is also a problem for keyword and boolean search -- negating a word generally won't negate synonyms or other variations of that word.
5) The people maintaining search indexes and searchers co-evolve to address -- or at least work around -- many of these issues. For example, most shoppers don't search for a "dress without sleeves"; they search for a "sleeveless dress". Everyone is motivated to drive towards a shared vocabulary, and that at least addresses the common cases.
None of this is to say that we shouldn't be striving to improve the way people and search engines communicate. But I'm not convinced that an example like this one sheds much light on the problem.
If you're curious to learn more about query understanding, I suggest you check out https://queryunderstanding.com/introduction-c98740502103
Re: Shirt Without Stripes
#328Earlier quoted context omitted.
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 n…
> The first 5 images were of Greta Thunberg. She must be the most representative person ever.
Well, she was the 2019 Time Person of the Year.
Likewise, Trump was the 2016 choice, and Crews and Gates have been featured as part of a group Person of the Year (“The Silence Breakers” and “The Good Samaritans” respectively).
Re: Shirt Without Stripes
#329This 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…
If the problem is that it didn't know where to apply the without, then why does it show me results from only a single entity? I would prefer so see an interleaved set of results containing all ambiguous entities.
I think that given the complexity of the problem they don't even try to parse the sentence and do attribution - they just shotgun with ML and hope for the best.
Re: Shirt Without Stripes
#330Earlier quoted context omitted.
The point of the OP is that they claim they understand everything. Example: https://www.blog.google/products/search/search-language-unde...
OK, but what if an Amazon algorithm has actually learned that people who search for "shirt without stripes" are more likely to buy more things if the first image they see is a picture of a striped shirt?
Isn't this just a version of "God works in mysterious ways" applied to AI?
"The AI works in mysterious ways. Trust it."