Internet people search made quicker

Posted on 24 Oct 2008 at 10:45

A scientist has developed a program that makes the process of finding a person's details on the internet, or across an organisation's network, quicker and more efficient.

Dutch based researcher Krisztian Balog said that although search engines are effective in searching for documents, they aren't quite as good at searching for entities, such as people.

He explained that the problem of searching for people is that a person is not a collection of words. Searching for text involves submission of words into an engine that then find texts that contain them. This type of search query is relatively uncomplicated, he asserted.

However, a person cannot be found in the same manner. Nonetheless, Balog claimed that each person does leave a digital trail because his or her name can be found in texts that they've contributed to or have been mentioned in.

Balog's program automatically links the information in these texts to a person. He has developed a method that uses these digital traces to compile a list of subjects for a person. The program accordingly selects the person that can satisfy the criteria of the search query.

Balog combines so-called generative language models with learning algorithms. The language models expose patterns in the language use with respect to persons and subjects. Learning algorithms recognise people and organisations in texts.

Krisztian Balog was a PhD student in the research group of Maarten de Rijke. De Rijke received a Pioneer subsidy from Netherlands Organization for Scientific Research in 2001 and used this to set up the project Computing with Meaning.

Author: Robert Jaques

Get more reviews, tutorials and in-depth advice, every month with Computer Shopper.
Click here to try 3 issues for £1

< Previous News : Software Next >

Be the first to comment on this article

You need to Login or Register to comment.