Also, I'm sure these have had nothing but positive effects in their testing. It'll make people Google more as opposed to just going to Wikipedia or some other site directly.

The Britney Spears one, because i can't find just "Lynn", neither in Wikipedia nor in one of the other structured sources.

On the other hand the result for "Justin Timberlakes mother" has been extracted from http://www.celebritywonder.com/html/justintimberlake.html (See the "aka. Lynn Harless, manager of the all-girl group Innosense; born on March 19, 1961" 'flaw'), whereas Britneys mother is also being mentioned with full name at Celebritywonder.

So either they expanded their parsing to more 'trusted sites' and obfuscate a little bit by pretending to have it from unstructured sources or they really started deriving this from freetesxt.

If they are the 'open' and 'transparent' company they claim to be, then they should be pro-active about answering the community when questions like these arise.

Imagine if the question was not about a potential neat new feature but rather about something more serious.

Anyway, not much to say. I can only hope that they fall asleep and end up behind us all ;)

Too much to ask? maybe...

Marshall, one small correction: tripple --> triple

It always seemed in line with their calculator/converter tool but it looks like they just enabled it for a broader range of queries.

http://www.pcworld.com/article/120362/google_intros_qanda_service.html

This was long in coming/making and I am not surprised. We've seen bits of it bubble up before and it seems like more and more is coming to the surface.

Certainly Google is a great position to deliver this 'light' semantic technology to the masses.

Alex

Some of the more popular ones I remember are for sporting events like the World Cup and Olympic schedules. I have to imagine that they used the same technology to parse the proper information from the respective sites for these events.

Flight Tracking

http://www.google.com/search?q=united+airlines+flight+89

Local Weather

http://www.google.com/search?q=walnut+creek+ca+weather

Conversion Counters

http://www.google.com/search?q=feet+to+meters

But these results look different. They're answering a question, not delivering information on your search. By that I mean, the result set doesn't have the keywords for your query - unlike the results above which all do.

Here, they're taking a set of data based on a query string and providing structured results meant to answer that query. Not just deliver relevance but to provide resolution. Big difference in my opinion.

The Jesus reference actually supports the idea of a semantic structure since Chris Ferguson is known as Jesus in poker circles. So the semantics actually work here, they've just delivered a different type of Jesus.

I'm a big proponent of microformats (it was one of my 2009 Internet Predictions) but Google has been slow (at best) to embrace them.

These instances might show the reason - they've figured out a way to get semantic data from sites without the additional structure. That would increase the ability to deliver and leverage semantic data since there would be no requisite coding.

Great find and interesting stuff. Please update us on what you learn.

Good find, but I'm be hesitant to hype it up as "semantic data" yet. I've seen this feature before but Google has definitely expanded it. Ask.com and 1

It seems like this is a simple expansion of this. Additionally, A9 - Amazon's now gutted search engine - used to have functionality similar to this and what Ask.com is trying to do today.

Heck, go on Ask.com and search for "Capital Oregon" and you'd get this:
http://www.ask.com/web?qsrc=2417&o=0&l=dir&q=capital+oregon

I wouldn't proclaim Ask.com semantic search engine all of sudden.

For awhile now, you could get quick answers for typing simple questions into Google like "Weather 94109", "define: email marketing" to "(100/.123)+123".

Daniel

===
Laura Bush — Spouse: Greatest President
According to http://www.wikiality.com/Laura_Bush

http://www.google.fr/search?hl=en&q=laura+bush+husband&btnG=Search
===

"The query "who is Jane Fonda?" triggers the answer "...is an Academy Award winning American actress, model, writer, producer, activist and philanthropist" and results in a link to the Wikipedia online encyclopedia's entry for the actress. "

That's not the case any more. Search now for "who is Jane Fonda's husband?" and you'll see the kind of results we discuss in this post.

Perhaps the parser is just a bit more aggressive and non search folk are beginning to see it more often.

http://bit.ly/1ftKbq

There are a couple interesting things about this:

1) I just put this information up yesterday and I am surprised at the indexing speed
2) I was using an email obfuscator http://bit.ly/147vo and Google decoded this with ease.
3) The vcard info was hidden with a display:none but this was ignored. Which kinda makes sense.

http://bit.ly/1ftKbq

There are a couple interesting things about this:

1) I just put this information up yesterday and I am surprised at the indexing speed
2) I was using an email obfuscator http://bit.ly/147vo and Google decoded this with ease.
3) The vcard info was hidden with a display:none but this was ignored. Which kinda makes sense.

"Where is Elvis?"

"Elvis" — Location: Us
According to http://www.chapters.indigo.ca/books/Elvis-N-A/9781848171053-item.html - More sources »

Now, if I could only get an exact map pin...

Google will be the semantic search engine of the future for 3 reasons:
1) They can: they have the money to build the best semantic search engine in the world.
2) they dominate search: meaning they can test like hell and can hand out semantic results only when needed.
3) this is their core business (and pretty much the only business where they make real money).

To beat Google here you don't have to be first mover, you have to have a significant and ownable advantage (algorithm anyone?), and you'd better have one that Google can't match in a number of years, since people won't "get" semantic search in a day, and I won't change my default search engine for a bunch of niche searches.
I just don't see any strategic advantage for a new comp

Um…don't you mean are being marked up in HTML? When I tried this, I got results whose HTML source was b elements.

Now, what would be really interesting is if Google returned such results inside a containing element with a well-known ID and marked up the contents with RDFa! That would turn Google's SERPs into even more of an API than they are now.

This query retrieves a list/array (of 2 names) and their corresponding details...

Who is Gandhi's wife? or Who is Mohandas Karamchand Gandhi's Wife?

This doesn't give a semantic result despite lots and lots of sources having this info explicitly.

Hmm.

Australia — Capital: +1hr, begins last Sunday in October; ends last Sunday in March

capital of bangladesh

Bangladesh — Capital: 23 43 N, 90 24 E

Is it really that hard to test all the world capitals before going live?

They have the community add/verify facts

For example, a few years ago I was looking up some science questions and it displayed them there, but I haven't seen anything like familial relations until recently. Whatever they're doing, they've been doing it for awhile, but it's growing.

Before you know it, you'll type in, "What should I do with my life" and Google will analyze your typing patterns and IP address to determine who you are, match you with an optimum life path that seems in line with your apparent goals, and put anyone who asks google of it onto the fast-track to glory, fame, or what-have-you.
Or it may just end up saying everyone should be an exotic dancer... only time will tell...

Check us out at http://headup.com - No registration required.

Feedback would be nice though...
: )

Cheers all,
Mike
"I tweet @headup"

very poorly written

http://en.wikipedia.org/wiki/HD_DVD has a template called infobox media:

{{Infobox media
|name=HD DVD
|logo=[[Image:HD-DVD.svg|200px|HD DVD logo]]
|image=
|type=High-density [[optical disc]]
|encoding=[[VC-1]], [[H.264]], and [[MPEG-2]]
|capacity=15 [[Gigabyte|GB]] (single layer)
30 [[Gigabyte|GB]] (dual layer)

|read=1× @ 36 [[Megabit per second|Mbit/s]] & 2× @ 72 Mbit/s
|write=
|standard=
|owner=[[DVD Forum]]
|use=Data storage, including [[high-definition video]]
|extended from=
|extended to=
}}

If you google any parameter from this list, you will get the output accordingly:

http://www.google.com/search?hl=en&q=capacity+HD-DVD&btnG=Google+Search&aq=f&oq=

HD DVD — Capacity: 15 GB (single layer) 30 GB (dual layer)

It is about as "semantic" as shooting with a shotgun is applied brain surgery.

http://hibbins.wordpress.com/2008/11/24/i-know-theres-an-answer/

This is clearly part of something bigger, glad that they've begun to expose smaller parts of their (no doubt-grand) scheme, to improve visibility on the topic that's had relatively zero attention so far..

http://www.google.com/search?q=who+is+Stanley+Kubrick%27s+wife%3F

Results suck.

But this is new since I remember running this same query a couple years ago and I did not get that "Stanley Kubrick: Wife" in the results.

A colon does not mean its semantic data or a proper triple!

This, I would guess, is a bit of pseudo NLP. You can form query format templates using the query data they already have. Using that it is easy to do something like this.

Link analysis and linking volume already would allow them to do this without any semantic data involved in it. Just that it won't work perfectly and it won't work all the time.

I led this project at Google for a long time - we originally launched in April 2005 (http://googleblog.blogspot.com/2005/04/just-facts-fast.html).

The efforts to add new data sources, especially unstructured data sources, have been going on for a long time. It looks like what you're seeing is a refresh of the data sources used.

One of the great things about extracting structured data from the entire web corpus is that each new extracted fact can form the basis of extracting thousands of more facts - similar to Sergey's Snowball system way back in 2000 (http://portal.acm.org/citation.cfm?id=336644).

Cheers,
Jonathan Betz

Actually I am sure they are using some aspect of it, but it would be interested which one and how.

Bye
Andraz Tori, Zemanta

I would like to see a score next to the fact that is some measure to figure out how trustable the fact is. Like if they see the same fact 1000 times across many trusted sources, then maybe the fact is 99.9% reliable. But if they see it 20 times, and 2 of the times it is actually something else, then maybe it is like 80%. You get the idea. Right now the way it's shown on the results page they are assuming it is 100% reliable, which doesn't seem right to me.

The biggest difference between this and just about every other semantic technology is the choice of when to use it. It is easy to produce semantic results for a query, but it is hard to know when to do so.

There is also a problem with time-sensitive data, such as "who is britney spears boyfriend"
http://www.google.com/search?num=100&hl=en&safe=off&q=who+is+britney+spears+boyfriend&btnG=Search

Similarly too, as to whether they're trying to 'dress up' link analysis and complex algorithm as being semantic technology - one of the most important observations Marshall made is that this is speculation based on limited observation - Google haven't announced this as Semantic Web tech.

It's integrated in a similar to other services they provide, such as measurement or currency conversion (try '100 GBP in EUR' or '1 km in miles') - it may just be another search feature.

But yes - there's _some_ natural language processing going on here.. transparently sourced, but those sources no doubt come from Google's large index - probably using site volume as the semantic web stack's 'Trust' - but it's not in that sense 'trustable', as proven by the inaccuracies.

It's very highly informed suggestion rather than understanding.

It seems to be restricted to city and celebrity family relationships from what I see.

http://www.freebase.com/view/en/britney_spears

I have no idea if Google uses this.

The problem with providing a definitive answer comes from the need to deal with inconsistencies, which is problematic when your source is the Web. When the source is human contributors incrementally developing the knowledge, this is easier: for example trueknowledge.com won't let you add a fact that contradicts what it already knows.

Google was working on extracting semantic data from text - I remember a talk at AAAI 2004 that mentioned they were extracting type information from text (e.g. "Tony Blair, the Prime-Minister of England" -> "Tony Blair ISA Prime-minister"). Adding capitals for countries, family for people, etc. seems like a natural progression.

In the research community, extracting triples from text has been around for a while (e.g. http://www.cs.washington.edu/research/textrunner/), but it's definitely encouraging to see Google trying it live.

My feel is that as soon as the semantic data is available on a large scale, there are going to be lots of niches to be filled by smaller players (e.g. "find me cheaper parking close to Hilton San Francisco").

Actually, many queries which used to work in the early days, including some fun ones, don't work anymore these days... like Google revealing superhero identities!
http://blogoscoped.com/archive/2006-06-07-n59.html

Obviously, there may be errors with some entity-attribute pairs,
but one advantage is that the table is not static, and if
in some time the capital of the country would move, Google would
eventually notice and the next viewer that opened the spreadsheet
would see the updated information.
http://docs.google.com/support/bin/answer.py?answer=54199&hl=en_US

Richm
IT Department
http://www.mypetvideos.tv/PublicWorks

It looks like it recognizes certain keywords around family relationships and returns a structured result for them. But it doesn't understand "mom" the same way as "mother".

Searching Britney Spears husband or Britney Spears spouse returns a spouse attribute with a list of two ex-husbands with dates of marriage and divorce. That's pretty nice. Britney Spears wife returns the same attribute. I guess in this case it's assuming you're asking who she's the wife of.

Let's say that Google has the same system that Calais does. Now compare the functionality to the data within their index. Once you compare the NLP of Calais with the data held by Google, then this new feature is not as big a leap. (Of course, what they both have is absolutly awesome but once the parts are built, you can put them together in interesting ways).

So my take is that Google has developed some form of NLP system (like Calais) and applied it to their data warehouse of pages.

The one issue with this is of course web page owners only like their page to be indexed by google becuase it usually results in more traffic to the page. However if google begins presenting the page's information to the surfer directly at google's search page then there is less reason for the surfer to click through to the page itself.

It probably also increases time spent on the google search page increasing their search page ad exposure and decreases time spent on the original index information pages decreasing the original page owners ad exposure time.

No, it's complicated. But it's all you need to know.

Wisdom. Ecclesiastes.

For God's sake, please delete this before too many see it.

I work as a mechanic wanna look for Britney:

Then come out Britney + Mechanical Algorithm such as 'Britney Crowbarr' or Britney's Exhaust Pipe or Britney Sludge Filter and not the Britney as in "Entertainment"

Or

I work as a botanist wanna look for Britney:

Then appeared ---> Britney Fertilizer or Britney Armoral Splicer Technique etc etc.

Or

I'm a student majoring in Software Engineering, am looking for something that might help my thesis regarding quantum packets technology... I'm not sure, but hey lets type "Britney" + "Software Engineering" then it comes out ---> Please specify either in application, formulation etc also expansive or none expansive and magnification tolerance.

Uh yuh something like that.

For example: "Weblogs Forum - What about a decorator module version 3.0?" - 5 posts - Last post: Dec 3, 2008 - http://www.artima.com/forums/flat.jsp?forum=106&thread=243843

Does anyone here know when it was introduced and point to more info on how it works?

(My guess: it scrapes HTML of forum pages to find semi-structured information about number of posts and their creation date. Unless a forum is already mirrored as a Google Group.)

Aditya Thatte

When you think about it, "semantic" refers to meaning, and "meaning" is not an absolute construct -- it is an abstraction constructed from popular wisdom. "Blue" means "blue" because the majority of people see that portion of hte spectrum the same way. If we took away the crowdsourcing element of "meaning," the semantic web would not exist.

They've also been working closely with the Cyc project for some time.

(1) Is it the right word?

So far, I have successfully tested these ones:

Capital
Mother
Spouse
Profession
Located in
Place of Birth
Date of Birth
Capacity
[to be continued]

1. movies calgary
2. weather calgary
3. 5 inches to cm

dictionary and calculator have been up for a while now too.

Google uses a so-called robot to surf the Internet. This robot is a simple software program that parses all web pages that it finds on the Internet and then stores the information it finds in Google’s database. When you search on Google, you’re actually searching the database that has been collected by that robot.

http://www.powerset.com/explore/go/who-was-marlene-dietrich-husband