The Semantic Spider Web - Getting a Clear Picture
(Page 4 of 4 )
I said before that the Semantic Web was in its early stages, but individual companies are doing their part. Metaweb Technologies has launched an effort called Freebase that is converting Wikipedia entries along with entries from other databases into formats that can be read by computers. The entries have been selected based on "the avid community." So far Freebase has gathered information on 30,000 movies and 580,000 celebrities.
IBM is also working on a project called Avatar Semantic Search, which focuses on a host company's email and messaging system. Say you want to find someone's home address in an email they sent, but you have hundreds of emails from that person. The IBM system works by identifying the text sequence as an address and deciphering the sentence to figure out who's address it is. This could end up being a highly useful application in the business world.
The last project I'll discuss is yet another one from Etzioni, called PanImages. It searches through word translations across hundreds of languages for images tagged with the appropriate word's meaning. It then shows the results from Google Images and Flickr on a split screen. It is especially useful for people that speak some of the world's least popular languages. Users can add their own translations, so it is susceptible to mischievous content. But the majority of translations are collected from automated readings of hundreds of Internet dictionaries and wiktionaries.
After a test run, I found the site a little bit lacking myself, but I think I just went in expecting too much. First you must type in a single word describing the image you want, not exactly what the image is (e.g. Ford Mustang GT Coupe). Then you click the translate button and the word will be displayed in multiple languages. After picking the language you want, you must choose which meaning or sense of the word you're looking for. Finally, click on the translation that best suits you. I suppose this method is a little broad for me, but I can see how it would be useful for someone speaking Croatian.
Whether the Semantic Web becomes a reality or not, the quality and transparency of information on the Internet is definitely on the rise. What we need next is the ability to better organize RSS feeds, blogs, and social networking sites so that we can get more out of our free time. And I appreciate you taking some of yours to read this article.
| DISCLAIMER: The content provided in this article is not warranted or guaranteed by Developer Shed, Inc. The content provided is intended for entertainment and/or educational purposes in order to introduce to the reader key ideas, concepts, and/or product reviews. As such it is incumbent upon the reader to employ real-world tactics for security and implementation of best practices. We are not liable for any negative consequences that may result from implementing any information covered in our articles or tutorials. If this is a hardware review, it is not recommended to open and/or modify your hardware. |