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

A new search engine

samuru.com

Post reply on HN
Print view View original

61–70 of 107 posts

Re: A new search engine

#61

Post by drakaal »

danso wrote: post #58
DanBC wrote: post #57

Earlier quoted context omitted.

Your Google link gives me "Searching for couk best ribs ". The 10 results give me: 2 hits for boat related stuff, with no food. 4 hits for restaurants, with no recipes. 1 hit about cervical ribs. And then, in positions 5, 8, and 9 there are recipes. So, even with all the smart people and computing power at Google this is still a very hard problem. It's great to have different people trying different approaches.

That's strange, I get links from amazingribs.com and food.com, which is more or less what I expect http://www.amazingribs.com/recipes/porknography/best_BBQ_rib... Either way, it's a deliberately contrived example to show that Google was more sophisticated than the GP indicates...I have no comment on whether amazingribs.com really does have the best ribs preparation tips

Hover over the Samuru Logo on the results. We will tell you a bit about what kind of search we think you are doing.

http://www.samuru.com/?q=python+list+comprehension

While we get the same top result for this, we also show that WikiHow.com linked to the Python Docs. So you can see closely related articles grouped together.

This is useful for things like http://www.samuru.com/?q=samsung+apple+patent+press+release

But Google requires the words or the synonyms to be on the results page. So do we, but we know that a search for http://www.samuru.com/?q=cook+bbq+ribs is not just about how to make BBQ Ribs, but to make the best BBQ ribs, because this is a subjective topic, I like honey BBQ, someone else likes Mesquite. That factors in to our results.

Re: A new search engine

#62

Post by drakaal »

danso wrote: post #60
joedevon wrote: post #56

Earlier quoted context omitted.

"I'm skeptical you'll achieve what you aim for if you're way off the mark in understanding how Google is so successful." Considering his comment drew out Matt Cutts, I'd bet he understands Google pretty well.

Right, but the success of a technical product is often based on results that can be tested and verified, and less on arguments through authority, though if Cutts is willing to say something like. "Wow, the OP has created something that surpasses Google in [whatever metric]", I'd admit I'd take his word on it. But the OP's claim stands on its own and makes assertions that can easily be verified. Are you arguing that G…

Google Brandon Wirtz Greatest Living American. I am pretty good at understanding how Google works.

While Google gets things right with out all of our language stuff a lot of that is because they have user data about what people are clicking on and which things they come back after reading.

That data means if they can get the stuff on to the front page they can "crowd source" the rest.

We don't have that user base for a feed back loop. We have to get our results entirely based on software.

Re: A new search engine

#63

Post by drakaal »

danso wrote: post #38
drakaal wrote: post #15

I didn't submit this. I didn't know anyone was submitting it. Or I would have written a post about why it is different than other search engines. Better is still up for grabs because it is new. Samuru doesn't use link authority, it analyzes pages and matches what you queried to the types of pages and picks the best matches. Let me give you an example. You search for "How to Make cupcakes" Google says give me the page…

Re: your portrayal of how Google works...An "over simplification"? It's just plain wrong. Google has, for quite awhile, not depended on sites containing all the words of a query...and natural language processing plays a huge part in analyzing intent of a query. I applaud this ambitious project but I'm skeptical you'll achieve what you aim for if you're way off the mark in understanding how Google is so successful...I…

We have that issue because it turns out many brand pages don't have any content. We are still balancing the domain bonus, but think how many home pages for brands have no text. No text means we have nothing to analyze.

Re: A new search engine

#64

Post by drakaal »

joedevon wrote: post #59
drakaal wrote: post #44

Earlier quoted context omitted.

Then you think wrong. Google can't tell that something is instructions. That's not something they do. It may know that ehow has a lot of pages with How To on them, but it doesn't know if those are pages with step by steps for how to do something, nor does it know that Rotten Tomatoes has pages with Opinions and Points, and conclusions that make up a review.

Well their move to semantic technologies e.g. Schema.org is a step in the direction of understanding these things better. Like if you mark up the page with http://schema.org/Review wouldn't you agree that they know it's a review? Are you using semantic web btw?

No. They know you tagged it a review.

I could tag it review and have it be a sales copy page for a product.

Our stuff knows that a review expresses an opinion, backs that up with facts, and makes a conclusion.

Re: A new search engine

#65

Post by drakaal »

drakaal wrote: post #15

I didn't submit this. I didn't know anyone was submitting it. Or I would have written a post about why it is different than other search engines. Better is still up for grabs because it is new. Samuru doesn't use link authority, it analyzes pages and matches what you queried to the types of pages and picks the best matches. Let me give you an example. You search for "How to Make cupcakes" Google says give me the page…

Other features I should have mentioned: Threaded results. If a result is cited by other results, they will be grouped so that you can see the conversation across sites.

Better Social Media integration. We do Facebook, Twitter, Google Plus not just Google Plus for showing authors.

Voice Input if you are on Chrome 25 or higher.

Results are returned with Summaries not Snippets.

With that I am falling asleep. I have enjoyed answering questions on this an the https://news.ycombinator.com/item?id=5579336 thread but 5 hours of it has worn me out. If you leave comments I'll promise to get back to them.

Re: A new search engine

#66

Post by pilooch »

drakaal wrote: post #44
gibybo wrote: post #42

Earlier quoted context omitted.

>So you think Google knows if a piece of content is instructional? Yes. >Or know that it is a Review? (not just has a rating) Yes. >But more importantly Google doesn't know what kind of content something is. You don't think Google knows how to classify content?

Then you think wrong. Google can't tell that something is instructions. That's not something they do. It may know that ehow has a lot of pages with How To on them, but it doesn't know if those are pages with step by steps for how to do something, nor does it know that Rotten Tomatoes has pages with Opinions and Points, and conclusions that make up a review.

For the sake of realism only: any basic supervised machine learning algorithm does that with proper labeled dataset. I have built many. I can assure you this is so classic that Google has it, that many other companies have it. And there are much better and accuratd solutions in place for combining all signals of this kind.

Re: A new search engine

#67

Post by buro9 »

drakaal wrote: post #15

I didn't submit this. I didn't know anyone was submitting it. Or I would have written a post about why it is different than other search engines. Better is still up for grabs because it is new. Samuru doesn't use link authority, it analyzes pages and matches what you queried to the types of pages and picks the best matches. Let me give you an example. You search for "How to Make cupcakes" Google says give me the page…

Pre-Google, this is pretty much how search engines worked... by analysing page content and weighting that rather than the network of links around the page.

Having just played with it, it feels both backwards and refreshing to go back to that. The results are different enough to feel good for the terms I used.

Re: A new search engine

#68

Post by mrknmc »

drakaal wrote: post #15

I didn't submit this. I didn't know anyone was submitting it. Or I would have written a post about why it is different than other search engines. Better is still up for grabs because it is new. Samuru doesn't use link authority, it analyzes pages and matches what you queried to the types of pages and picks the best matches. Let me give you an example. You search for "How to Make cupcakes" Google says give me the page…

This is really strange. I just searched for "how to ride a bike" and the first links from Samuru are completely useless whereas the first link from Google is exactly what I wanted, instructions from wikihow. How do you explain that?

Re: A new search engine

#69

Post by pyre »

drakaal wrote: post #15

I didn't submit this. I didn't know anyone was submitting it. Or I would have written a post about why it is different than other search engines. Better is still up for grabs because it is new. Samuru doesn't use link authority, it analyzes pages and matches what you queried to the types of pages and picks the best matches. Let me give you an example. You search for "How to Make cupcakes" Google says give me the page…

Quick comment on the interface. Looks like the initial page is optimized for 1024x768. I'm on a netbook at 1024x600 (even less so since I'm not at fullscreen). While I realize that I'm in the minority, it looks like the issue is everything is position absolutely. The only reason that the bottom of the page is cut off is because there is a bunch of empty space between the top of the page and the logo: http://imgur.com/vDFwY8b

I realize that this is a bit of a nitpick, but I felt the need to mention it.

Re: A new search engine

#70

Post by kephra »

two suggestions:

- you need a favicon, so its possible to pull your site into an icon bar for bookmarking.

- you need a search engine registration, so its possible to use it from search engine tab in browser

Post reply on HN