| EPSRC Reference: |
EP/C536762/1 |
| Title: |
CRONOPATH: Timeline and Named Entity Extraction for Hyperlink Corpora |
| Principal Investigator: |
Wilks, Professor Y |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computer Science |
| Organisation: |
University of Sheffield |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 July 2005 |
Ends: |
31 December 2007 |
Value (£): |
294,632
|
| EPSRC Research Topic Classifications: |
| Artificial Intelligence |
Information & Knowledge Mgmt |
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
Have you ever had to go through hundreds of results when using a search engine to find what you are looking for? And then perhaps found that many results are outdated or just someone's latest blog entry? Imaging trying to collect from the web information on a famous person and being able to tie all the bits of information, together while discarding all the bits about someone else with the same name? Imaging, too, being able to find the latest information, concert locations and dates of your favourite music without being trapped in old information still up on the web after years?This research project, Cronopath, will lead to a new type of search engine that solves these common problems. Cronopath provides timely results in a friendly but informative manner, piecing together information about people, organisations and events automatically. Cronopath looks at different websites, spotting information about items that matter most. As it gathers information, Cronopath tries to determine the time and date when a particular item was created. This time and date information lets it piece information together in a chronological order, making it easy to identify the latest news and information about some subject or the latest gossip about some superstar.Much of this rests on Cronopath's core ability to distinguish between different people that have exactly the same name or very similar names - such as George Bush and George W. Bush. Cronopath also knows that people and organisations may change their name over time - if you are looking at Madonna's life before she launched her career, Cronopath will know that she was known as Louise Veronica Ciccone, and it will also know that she now wants to be called Esther.Currently, search engines work by working out which results are relevant by looking at the popularity of each web page that contains the result. The most popular web pages will have lots of links pointing to them, including some from other popular pages. However, the most popular kid on the block may not always be the most knowledgeable. Current search engines also lump everything on a single page together without trying to identify important pieces of meta information in the page itself. Thus, a site on Semiconductor Physics that mentions Britney Spears will get a very high placing if you search for Britney Spears. Cronopath should have the common sense to understand that you will probably be looking for songs or photos of Britney rather than Physics (unlike all other popular search engines!). Cronopath will thus let people around the world find more relevant, more up-to-date and more informative results quickly and efficiently.
|
|
Key Findings |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Potential use in non-academic contexts |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
|
Impacts |
|
| Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
| Summary |
|
| Date Materialised |
|
|
|
|
Sectors submitted by the Researcher |
|
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
| Project URL: |
|
| Further Information: |
|
| Organisation Website: |
http://www.shef.ac.uk |