Adapting the Edinburgh Geoparser for Historical Georeferencing
- Submitting institution
-
University of Edinburgh
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 58838653
- Type
- D - Journal article
- DOI
-
10.3366/ijhac.2015.0136
- Title of journal
- International Journal of Humanities and Arts Computing
- Article number
- -
- First page
- 15
- Volume
- 9
- Issue
- 1
- ISSN
- 1753-8548
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- 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
-
3
- Research group(s)
-
D - Language, Interaction and Robotics
- Citation count
- 22
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The open-source Edinburgh Geoparser automatically identifies placenames and grounds them to lat/long coordinates, enabling spatially-aware search and visualisation of large text collections. This paper adapts it to three datasets, exploring how historical digitised text presents particular difficulties not seen in modern text. Our work was at the forefront of historical geoparsing research (which has seen rapid uptake in Digital Humanities) and is frequently referenced as a benchmark for geotagging, georesolution and rigorous evaluation. The Geoparser has had over 700 downloads from across the world. This research has led to further funding for the authors (Palimpsest, LitLong, Plague.TXT, Alex's Turing Fellowship).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -