| EPSRC Reference: |
GR/R55559/01 |
| Title: |
Structured Text Analysis: Addresssing Inconsistancy in Heterogeneous Information |
| Principal Investigator: |
Hunter, Professor A |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computer Science |
| Organisation: |
UCL |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
21 January 2002 |
Ends: |
20 March 2005 |
Value (£): |
160,576
|
| EPSRC Research Topic Classifications: |
| Artificial Intelligence |
Image & Vision Computing |
|
| EPSRC Industrial Sector Classifications: |
| Financial Services |
Pharmaceuticals and Biotechnology |
| Information Technologies |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
Professionals need to analyse information from multiple sources. Increasing amounts of information such as news reports are potentially available in the form of structured text (for example in XML or output in a template from an information extraction system) where text entries are words, or very short phrases, such as proper nouns, numbers, and technical terms. To help professionals analyse such information we want to develop techniques to merge the information and in so doing reduce redundancies and conflicts that may arise in the information. In particular we want to develop the theory for examining a repository or stream of structured news reports with the aim of aggregating some of these reports into merged news reports. Then we want to use this theory to implement the Logical Fusion Framework (LFF) which is a set of modules for identifying and acting on inconsistencies and for sythesizing the resulting information into merged reports. The modules in LFF need to draw on domain knowledge and meta-level rules for acting on inconsistency and for specifying the composition of merged reports. This domain knowledge and meta-level rules are specific to each application. To evaluate and demonstrate the utility of the LFF technology, we will develop a demonstrator called the NewsFusion Demonstration System that will contain domain knowledge and meta-level rules for handling news reports on companies on the London Stock Exchange. We have already published a number of papers on the theory underlying this proposal, and we have a clear understanding for the domain knowledge required for the demonstration system. We believe the resulting technology will offer users a more sophisticated way of merging news reports that is sensitive to the application context.
|
|
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: |
|