We have relaunched: What's new at ZDNet Asia?

ZDNet / News / Software / Story

Microsoft aims to build a better thesaurus

By Ina Fried, CNET News.com on February 23, 2009

Summary

Borrowing techniques used in machine translation, a team of researchers in Redmond believes it has found a better way to serve up synonyms.

Topics

built-in, intranet, machine translation, microsoft surface, product development, researcher, team, techfest, web, wikipedia

Events

Microsoft MSDN/Developer Event
25 Mar 2010

One Marina Boulevard, Microsoft Singapore

IT Architect Regional Conference Singapore 2010
20 - 21 Apr 2010

Singapore Management University, Singapore

The Internet Show 2010
21-22 Apr 2010

Suntec Singapore

A team of researchers at Microsoft is looking to beat Roget at his own game.

Aiming to build a better thesaurus, the Writing Assistance project within Microsoft's research unit is tapping techniques developed to translate from one language to another.

Although thesauri are good at finding lots and lots of synonyms, they require the user to pick the right one because they aren't very good at understanding the context of what is being said. That's where the experience from doing machine translations comes in.

"We've taken the actual translation tables...and what we've done is we've taken those and said if a word in Chinese maps to two different English words maybe those two words are synonyms with some probability," said Christopher Brockett, a computational linguist and one of the Microsoft researchers leading the project.

The approach has two key benefits over a static thesaurus. First of all, the newer approach can do phrases, as opposed to single words. Also, it can draw on the context in which the phrase is used.

Brockett plans to show off a prototype of the tool at TechFest, Microsoft's annual internal science fair. It's just one of dozens of projects that will be shown as part of an effort to expose Microsoft's business units to the work being done in Microsoft's research labs.

TechFest is sort of like "The Dating Game" for Microsoft's research and product development arms. Research teams at Microsoft set up booths, somewhat like a high-school science fair, while product teams shuffle through looking for something that might give their efforts a leg up on the competition.

For the public, TechFest can also offer a glimpse at future product directions. For example, researcher Andy Wilson showed off a number of surface computing projects in the years leading up to the debut of Microsoft's Surface product.

As is the case with most of the projects, the thesaurus effort is still in its infancy.

"We're still working on the algorithms and how much work we give to the language pairs," Brockett said. "We have to get the quality up. There are usability issues that have to be looked into."

Over time, though, Brockett hopes the technique could be used to effectively translate whole sentences. Microsoft has a demonstration of that up on its Web site, but Brockett acknowledges such a treatment shows both the potential and the current limitations of the technology.

But would-be high-school plagiarists beware. Yes, the technology could someday translate the whole Wikipedia article for you, but it would likely translate the article the same way for all your classmates as well. And plagiarism detection software is evolving along with the science of machine translation.

As for the thesaurus itself, the technology would be a natural fit for Word, which already has a built-in traditional thesaurus. But the technology could also help Microsoft in another key area: search.

That's because while search engines are good at finding things like names, that have just one form, they have a harder time finding expressions that can be phrased in multiple ways.

That's less of an issue when searching across the whole Web. For example, searching "Who shot Abraham Lincoln?" "Who killed Abraham Lincoln" and "Who assassinated Abraham Lincoln" all direct you to a page with John Wilkes Booth.

However, when it comes to searching smaller universes, such as a company's intranet, that might not be the case.

"You might not find it if the words are different," Brockett said. In such cases, automatically searching using similar phrases might boost the likelihood of finding a result.

This article was first published as a blog post on CNET News.

Related stories

Microsoft is expanding and investing in Thailand

Microsoft gets 10,000th patent

Microsoft aims to show Windows 7 'readiness'

PC sales slump to bite even Microsoft

Talkback

Add your opinion

In order to post a comment, you need to be registered. (Sign In or register below)

Post your comment
Transform your business interactions with real-time voice, video and telepresence solutions.
Tech Vendor: Cisco

ZDNet Asia Live

RT @mistertechblog: I wrote about Nexus One and Touchdown, desktop dock, Bluetooth/USB tethering, ebooks here: http://bit.ly/bRdzx0

49 minutes ago by yklee13 on topsy

Read my blog post on getting the most from your Nexus One: http://www.zdnetasia.com/blogs/m...

Data Centre Operator (Fresh Graduates Welcome to Apply) in ... http://bit.ly/bagYuu

1 hour 19 minutes ago by intmasterfeed on topsy

#Cisco #Cloud Cloud on ZDNet Asia: Aussie university joins Cisco cloud ยท Early-adopter criminals embrace cloud... http://bit.ly/d93C8S #TCN

2 hours 22 minutes ago by thetechgang on topsy

www.3w.com.au has seen it's outsourced IT Contracting Business in Manila grow at 4 times the rate of its traditional Australian Based...

9 hours 32431 seconds ago by brucemills on Companies' outsourcing spend to increase

RT @3wconsulting: Whitepaper from http://3W.com.au "Outsourcing Your IT Requirements to Philippines" now on @zdnetaustralia & @zdnetasia http://ow.ly/1oY9f

Whitepaper from http://3W.com.au "Outsourcing Your IT Requirements to Philippines" now on @zdnetaustralia & @zdnetasia http://ow.ly/1oYbA

Whitepaper from http://3W.com.au "Outsourcing Your IT Requirements to Philippines" now on @zdnetaustralia & @zdnetasia http://ow.ly/1oYbz

Zdnetasia.com Estimated Worth $178,365 USD. Daily Ad Revenue:$244 USD, Daily Views:81,445 Pages... - http://www.haplog.com/www.zdneta...

recently estimated website net worth of zdnetasia.com - http://www.haplog.com/www.zdneta...

18 hours 53 minutes ago by haplog on topsy

When I create an event, I click on an approximate time during the day when I want the event to occur, then I click "edit event detail...

1 day 29 minutes ago by bessellbrowne on Google Calendar gets 'smart' rescheduling

ipads break alott i had one it broke three times in the month i had it so i got rid of the damn thing id just go for the laptop Top Grade...

1 day 30 minutes ago by bessellbrowne on Report: 'Hundreds of thousands' of iPad preorders

There are a number of websites that still require Internet Explorer to view and IE for Mac Stinks (it is really ies4osx which is the Wind...

1 day 32 minutes ago by bessellbrowne on Microsoft: Only minor tweaks in Windows 7 SP1

The receivers don't transmit back to the satellite. Unless there is a phone line attached to the receiver, they don't have any wa...

1 day 35 minutes ago by bessellbrowne on Apple to join the geolocation craze?

"Lead Cognos BI Developer Insurance - Jobs - ZDNet Asia" http://bit.ly/bRcxOG

1 day 30 minutes ago by rhrcognos on topsy

whatever little understanding I have we 'll only progress toward end of the world if we use HPCs to lenthen life of human being. Huma...

1 day 41 minutes ago by abhi32002@gmail.com on High computing promises elixir of life

Thanks for the knowledgeable article on SDDs. Allas...when all this reasearch will happen in Indian Universities. Hope the new bill on Fo...

1 day 54 minutes ago by abhi32002@gmail.com on APAC HPC users eye solid-state drives

It was a good article. This brings a good opportunity for Indian IT firms to come up with new solutions in this field. HPC can become a b...

1 day 13 minutes ago by abhi32002@gmail.com on High computing most-wanted job in Asia

COL KR DHARMADHIKARY(RETD) its very late to reply the link, but if it is still alive and looking for opportunity, i would like to know th...

2 days 10 minutes ago by deb021280 on Education takes off in rural India, helped by PCs

It was just a matter of time until google was marginalised anyway. I'm afraid this will be forgotten in China very quickly. Still, it...

2 days 15 minutes ago by robinsmith on Report: Google to leave China on April 10

High performance computing (HPC) most-wanted job in Asia http://bit.ly/9vFC3i (via @zdnetasia) #singapore

He doesn't care if her shoes are of glass, All he wants to see is a huge rack and nice a*s. Sleeping beauty's not awoken by true ...

2 days 44 minutes ago by warlowdavies on One pair of 3D glasses to rule them all

RT @zdnetasia: EMC COO, Pat Gelsinger, on bridging gaps in the organization and its cloud ambitions in Asia. (cont) http://tl.gd/i5jjd

EMC COO, Pat Gelsinger, on bridging gaps in the organization and its cloud ambitions in Asia. http://bit.ly/9etOZW

Asian SMBs need to pay more attention to disaster recovery planning http://bit.ly/bDet08 via @zdnetasia

Asian SMBs need to pay more attention to disaster recovery planning http://bit.ly/bDet08

[TECH] URL Shorteners slow Web redirection. - http://bit.ly/bySnWK @zdnetasia

URL shorteners are great but they can slow web redirection & you pray it would never go down http://bit.ly/bySnWK via @zdnetasia

URL shorteners slow Web redirection. http://bit.ly/bySnWK

Chinese agencies cry foul over Google. http://bit.ly/by6rwV

all of sg's isps have been practising compulsory invisible proxy for all home subscribers at their backend since many years back alre...

3 days 54 minutes ago by melvinchia on Web filters mean bad news for business

it is not to good for china.
Proactol

3 days 39 minutes ago by nathonastle on Chinese ad partners beg Google for information

Very good explanation of JMX

4 days 44 minutes ago by Babith B on Managing applications with JMX

The reaction to a report issued Tuesday by Flurry Analytics managed to completely overlook some interesting news--the Android-based Motorola Droid outsold the original iPhone over the same period of time following their respective launches--to focus instead on the sales numbers for the Nexus One.

4 days 47 minutes ago by lonemavericks on diggs

Another ZTE story....

4 days 49 minutes ago by Moderate Your Greed on Philippines opens bid for final 3G license

Keep up with ZDNet Asia

Linkedin Join our network

RSS Feeds Subscribe now

Newsletters Subscribe today

Twitter Follow us

Inside ZDNet Asia

Special Report: Tech Focus in 2010

Latest Videos on Tech Industry

Insight: Interviews with Newsmakers

Search for over 15,000 Tech Jobs in Asia

Find your Tech answers in TechGuides

IT Library: Over 60,000 IT papers at your fingertips

Download IT Priorities 2010 Report