Automated News Suggestions for Populating Wikipedia Entity Pages
- Submitting institution
-
The University of Leeds
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- UOA11-1461
- Type
- E - Conference contribution
- DOI
-
10.1145/2806416.2806531
- Title of conference / published proceedings
- Proceedings of the 24th ACM International Conference on Information and Knowledge Management - CIKM '15
- First page
- 323
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- October
- Year of publication
- 2015
- URL
-
-
- 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
-
2
- Research group(s)
-
B - AI (Artificial Intelligence)
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Although Wikipedia is one of the most used web sites and has many editors, completeness of information is usually restricted to popular entity pages. The paper suggests salient and non-redundant news articles for specific Wikipedia entity pages. Results on 350,000 news articles and 74,000 Wikipedia entity pages show that this method considerably outperforms standard salience. Has been used in subsequent work by Markert for finding fine-grained citations for Wikipedia statements (CIKM-2016 and EMNLP-2017). Work with the Wiki-foundation by Fetahu led to WWW-19 paper (https://dl.acm.org/doi/10.1145/3308558.3313618) and inspired work by Ridho et al, Nanni et al and Jana et al.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
