Bing

Local, Relevance, and Japan!

June 21, 2005, 03:17 PM by Bing | 24 Comments

We launched our MSN Search engine on February 1st and have remained hard at work to make it better every day.  Yesterday, we released some improvements we hope you’ll like.  Much of this work is targeted directly at feedback that our blog readers and other customers have given us, so please keep the comments coming!  We have a long way to go to achieve our vision of the perfect search engine – and we can’t do it without your continued feedback and support..

Our number one user request was to improve and expand upon our local search offering.  The ‘Near me’ feature we launched in February was missing something really important – the ability to look up yellow page and white page numbers.  Our new local search beta integrates maps, yellow pages, white pages, and web results. It also integrates satellite images from TerraServer to provide you with an overhead shot of where you want to go. This makes it much easier to find a local pizza place or art museum! You can access this beta by heading to our local search page or by entering a query term with local data (such as a zipcode or city, state) in our mainline search box.

Our team focuses obsessively on the relevance of the web results.  We want to get the most relevant result in the top position all of the time.  The ranker we released in February served us well, but had some flaws that we weren’t happy about.  In collaboration with Chris Burges and other friends from Microsoft Research, we now have a brand new ranker.  The new ranker has improved our relevance and perhaps most importantly gives us a platform we think we can move forward on quicker than before.  This new ranker also is based on technology with an awesome name – it’s a neural net, which we internally call "RankNet".  For you Star Trek fans out there – I keep thinking of the android Data powering our search engine.
 
Pictured below is an illustration of the relevance for the query “pbs evolution videos” over time. With the oldest on top, you can see that over the past few weeks we’ve brought high quality results into the top positions and moved the official PBS page to position 1.  The “correct” page is highlighted in green below and you can see it move into position #1.

Aided by our new ranker, we were able to produce particularly big relevance gains in Japan. The queries tsutaya (A Multimedia Entertainment Shopping Company), win2000, and kat-tun (a music band) all showed noticeable improvement.  The feedback we’ve received so far has been very positive so we think we are on the right track.

You’ll notice that we’ve expanded our sports instant answers too. You can now get instant answers for your favorite professional baseball teams and players. By using MSN Search, you can see that Ichiro’s batting average is back over .300 – whew.

We’ve also added a number of new operators that will enable you to narrow your search to exactly what you’re looking for. We’ve added FileType:, one of the most asked for operators, which restricts documents to a particular filetype. InAnchor:, InURL:, InTitle:, and InBody: are now available to find keywords in a particular part of the document, or in anchor text pointing to a document. We’ve augmented the Link: keyword that finds documents that link to a particular page with LinkDomain:<domain>, which finds documents that point to any page in a domain. Finally, we’ve added a new experimental operator called Contains:. Contains: returns documents that contain hyperlinks to documents with a particular file extension; for example, contains:wma returns documents that contain a link to a WMA file.

We hope you like these new improvements – please leave us a comment to tell us what you think.

 Ken Moss, MSN Search General Manager

subscribe

Comments

Netfo

Posted On June 21, 2005, 11:20 PM
Inurl doesn't work the way I intuitively expect it to - is the documentation going to be updated soon to include the new features?

Erik Selberg

Posted On June 22, 2005, 12:23 AM
How do you expect it to work? I'm having a lot of fun doing vanity searches with it now... heh.

Nektar

Posted On June 22, 2005, 01:38 AM
So what is the difference between the Near Me button and the Local Search Beta link. Don't they do the same thing? Don't they both carry out a local search? If so why put two methods of doing the same thing? Why not carry out a local search if the Near Me button is used? Why do you need a Local Search Beta tab as well? This confuses users. Keep the interface to a minimum please.
And what if I want to chck for local info in another place? What do I have to type in the search box? Why don't you provide a map from where I can click the localation in which I wish to restrict my web and/or local search. In my opion Local Search should not be separated from the web search. There should be no Local Search tab and users should be able to perform a local search by clicking ont he Near Me button or choosing a localation on a dynamic map. No Local Search tab confusion please.

Netfo

Posted On June 22, 2005, 01:51 AM
In google, you can constrain a search like mysearchterms inurl:site.domain.com/subsite/

but in msn search it gets no results.

same with mixed:

mysearchterms inurl:subsite site:site.domain.com

Erik Selberg

Posted On June 22, 2005, 02:48 AM
It does work (at least for me) separated out... for example, "Bill Gates inurl:msdn site:microsoft.com" works fine:
http://search.msn.com/results.aspx?q=Bill+Gates+inurl%3Amsdn+site%3Amicrosoft.com+&FORM=QBRE

It doesn't work quite like Google using a substring match, although that's a great suggestion. Instead, it's just a text match on individual terms somewhere in the url... e.g. inurl:some inurl:domain inurl:com

It is a bit more tedious, but allows a bit more flexibility, e.g. (inurl:dom1 OR inurl:dom2).

We'll post more on this later.

-e

StephenBauer

Posted On June 22, 2005, 02:22 PM
Is there a relation between MSN Search and Clusty Search? I see some similar things in the SERPs between the two (and Clusty results can actually change MSN results...shared cookie or something?)

Q

Posted On June 23, 2005, 02:03 AM
The Datapark Search Engine, http://www.dataparksearch.org/ , also uses neural network to rank search results, it has been appeared about two years ago, and, of course, works a bit different.

Joe

Posted On June 23, 2005, 03:06 PM
The relevance of the results is absolutely perfect. I noticed the more relevant results a few days before the buzz started. Now I just can't wait to try the new msn adcenter. I am very happy with msn search now. Thanks for a great product.

SemKing

Posted On June 27, 2005, 01:42 PM
Nice job on the relevance filter..it's a good change.

Thanks also for the fast listings. Recently I changed one of the directory names on a website (to kill the spammers stealing my content) and MSN2 picked it up ASAP. All the other search engines are still listing the outdated links. I don't believe this is related to lucky timing. I think the other guys are running me through their crappy filters. Keep up the good work MSN.

One thing I would suggest, though. Take a lesson from Google's easy GUI. If you want people to use MSN search as a homepage, create a simple customizable search homepage (optional links for TV, movies, map searches) that computer illiterate baby boomers wouldn't be threatened by. Once you have them you'll have them for life, because they'll always want to know what's on the TV that night.

Use psychology a little more instead of tech.

just my 2 cents

Glenn

Posted On June 30, 2005, 02:29 PM
Congrats on the new RankNet.

I look forward to a good stiff competition from MSN for top SE!

I do wish MSN would provide some type of page measurement similar to google pagerank and an API to the MSN engine! :)

Welcome

to the Microsoft Bing community

Remember, don't post your personal information!