Featured Research

from universities, journals, and other organizations

Linguistics researcher develops new system to help computers 'learn' natural language

Date:
August 24, 2013
Source:
University of Texas at Austin
Summary:
A linguistics researcher is developing new methods for helping computers 'learn' natural language.

For more than 50 years, linguists and computer scientists have tried to get computers to understand human language by programming semantics as software. Now, a University of Texas at Austin linguistics researcher, Katrin Erk, is using supercomputers to develop a new method for helping computers learn natural language.

Related Articles


Instead of hard-coding human logic or deciphering dictionaries to try to teach computers language, Erk decided to try a different tactic: feed computers a vast body of texts (which are a reflection of human knowledge) and use the implicit connections between the words to create a map of relationships.

"An intuition for me was that you could visualize the different meanings of a word as points in space," says Erk, a professor of linguistics who is conducting her research at the Texas Advanced Computing Center. "You could think of them as sometimes far apart, like a battery charge and criminal charges, and sometimes close together, like criminal charges and accusations ("the newspaper published charges…"). The meaning of a word in a particular context is a point in this space. Then we don't have to say how many senses a word has. Instead we say: 'This use of the word is close to this usage in another sentence, but far away from the third use.' "

To create a model that can accurately recreate the intuitive ability to distinguish word meaning requires a lot of text and a lot of analytical horsepower.

"The lower end for this kind of a research is a text collection of 100 million words," she explains. "If you can give me a few billion words, I'd be much happier. But how can we process all of that information? That's where supercomputers come in."


Story Source:

The above story is based on materials provided by University of Texas at Austin. Note: Materials may be edited for content and length.


Cite This Page:

University of Texas at Austin. "Linguistics researcher develops new system to help computers 'learn' natural language." ScienceDaily. ScienceDaily, 24 August 2013. <www.sciencedaily.com/releases/2013/08/130824131405.htm>.
University of Texas at Austin. (2013, August 24). Linguistics researcher develops new system to help computers 'learn' natural language. ScienceDaily. Retrieved February 1, 2015 from www.sciencedaily.com/releases/2013/08/130824131405.htm
University of Texas at Austin. "Linguistics researcher develops new system to help computers 'learn' natural language." ScienceDaily. www.sciencedaily.com/releases/2013/08/130824131405.htm (accessed February 1, 2015).

Share This


More From ScienceDaily



More Mind & Brain News

Sunday, February 1, 2015

Featured Research

from universities, journals, and other organizations


Featured Videos

from AP, Reuters, AFP, and other news services

NFL Concussions Down; Still on Parents' Minds

NFL Concussions Down; Still on Parents' Minds

AP (Jan. 30, 2015) The NFL announced this week that the number of game concussions dropped by a quarter over last season. Still, the dangers of the sport still weigh on players, and parents&apos; minds. (Jan. 30) Video provided by AP
Powered by NewsLook.com
Study Shows Newborn Chicks Count From Left to Right Just Like Humans

Study Shows Newborn Chicks Count From Left to Right Just Like Humans

Buzz60 (Jan. 30, 2015) Researchers for the first time identified human&apos;s innate preference for associating low and high numbers with the left and right respectively in another species. Jen Markham (@jenmarkham) explains. Video provided by Buzz60
Powered by NewsLook.com
Best Mood Elevating, Feel Good Shakes & Smoothies

Best Mood Elevating, Feel Good Shakes & Smoothies

Buzz60 (Jan. 30, 2015) You can elevate your mood by having a meal in a glass. Fitness and nutrition expert John Basedow (@JohnBasedow) offers the best &apos;feel good&apos; smoothies and shakes chock full of depression-relieving ingredients...including apples, berries, lemons, cucumbers, papaya, kiwi, spinach, kale, whey protein, matcha, ginger, turmeric and cinnamon. Video provided by Buzz60
Powered by NewsLook.com
Poll Says Firstborn Is Responsible, Youngest Is Funnier

Poll Says Firstborn Is Responsible, Youngest Is Funnier

Newsy (Jan. 30, 2015) According to a poll out of the U.K., eldest siblings feel more responsible and successful than their younger siblings. Video provided by Newsy
Powered by NewsLook.com

Search ScienceDaily

Number of stories in archives: 140,361

Find with keyword(s):
Enter a keyword or phrase to search ScienceDaily for related topics and research stories.

Save/Print:
Share:

Breaking News:

Strange & Offbeat Stories


Health & Medicine

Mind & Brain

Living & Well

In Other News

... from NewsDaily.com

Science News

Health News

Environment News

Technology News



Save/Print:
Share:

Free Subscriptions


Get the latest science news with ScienceDaily's free email newsletters, updated daily and weekly. Or view hourly updated newsfeeds in your RSS reader:

Get Social & Mobile


Keep up to date with the latest news from ScienceDaily via social networks and mobile apps:

Have Feedback?


Tell us what you think of ScienceDaily -- we welcome both positive and negative comments. Have any problems using the site? Questions?
Mobile: iPhone Android Web
Follow: Facebook Twitter Google+
Subscribe: RSS Feeds Email Newsletters
Latest Headlines Health & Medicine Mind & Brain Space & Time Matter & Energy Computers & Math Plants & Animals Earth & Climate Fossils & Ruins