| EPSRC Reference: |
GR/M76881/01 |
| Title: |
GENERATING SUMMARIES OF TIME-SERIES DATA |
| Principal Investigator: |
Reiter, Professor E |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computing Science |
| Organisation: |
University of Aberdeen |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 April 2000 |
Ends: |
31 December 2003 |
Value (£): |
215,311
|
| EPSRC Research Topic Classifications: |
| Human Communication in ICT |
|
|
| EPSRC Industrial Sector Classifications: |
| Financial Services |
Healthcare |
| Creative Industries |
Information Technologies |
| No relevance to Underpinning Sectors |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
There is a growing interest in natural-language generation (NLG) systems which produce English summaries of time-series data, such as weather reports and financial information. Previous systems have used sophisticated NLG techniques for creating fluent well-written reports, but have used simple time-series analysis techniques to determine what information should be in the report. We propose to improve summarisation technology by incorporating state-of-the-art time-series analysis and abstraction techniques, based on the work of Shahar. This will require adapting Shahar's theory and knowledge-acquisition techniques (developed for event detection and the production of graphical summaries) quite considerably. We also need to develop a representation of the meanings of words used in summaries (such as 'spike' and 'slowly decreasing') which maps onto the abstractions produced by Shahar's model; we believe prototype and exemplar models of word meaning will be useful for this.In terms of workplan, we will initially develop our theory in the context of two prototype systems built for our industrial collaborators; working on real-world systems will give us access to domain experts for knowledge acquisition, evaluation and feedback. We will test the generality of our theory by developing a third prototype in the last year of the project, in a to-be-chosen domain.
|
|
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.abdn.ac.uk |