Explicit diversification of event aspects for temporal summarization
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-00753
- Type
- D - Journal article
- DOI
-
10.1145/3158671
- Title of journal
- ACM Transactions on Information Systems
- Article number
- 25
- First page
- -
- Volume
- 36
- Issue
- 3
- ISSN
- 1046-8188
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2018
- URL
-
http://eprints.gla.ac.uk/150135/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: Proposes an effective new framework enabling users to dynamically alter timeline content selection to focus on their information needs, while solving cold-start problems via learning from past events; RIGOUR: Four questions are evaluated on three standard NIST datasets across 46 representative real-world events; SIGNIFICANCE: Published in a top IR journal, invited to present at SIGIR’19 main conference. Enables users to customise their summary content, while enhancing conciseness and informativeness up to 13%. Validated within SUPER project (http://super-fp7.eu/) collating action reports during a Flooding Live Deployment (https://hubs.mymeedia.com/super-fp7/post/38012439) for Italian Civil Protection stakeholders.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -