Toponym disambiguation in historical documents using semantic and geographic features
Authors:
Open Access
- 1 June 2017
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 175-180
Abstract
Historians are often interested in the locations mentioned in digitized collections. However, place names are highly ambiguous and may change over time, which makes it especially hard to automatically ground mentions of places in historical texts to their real-world referents. Toponym disambiguation is a challenging problem in natural language processing, and has been approached in two different yet related tasks: toponym resolution and entity linking. In this paper, we propose a weakly-supervised method that combines the strengths of both approaches by exploiting both geographic and semantic features. We tested our method against a historical toponym resolution benchmark and improved the state of the art. We also created five datasets and tested the performance of two state-of-the-art out-of-the-box entity linking methods and also improved on their performance when only locations are considered.Keywords
This publication has 16 references indexed in Scilit:
- Creating a Novel Geolocation Corpus from Historical Texts2016
- Improving efficiency and accuracy in multilingual entity extraction2013
- Approaches to disambiguating toponymsSIGSPATIAL Special, 2011
- You are where you tweet2010
- Learning to link with wikipedia2008
- Toponym resolution in textACM SIGIR Forum, 2007
- Incorporating non-local information into information extraction systems by Gibbs sampling2005
- Name Discrimination by Clustering Similar Contexts2005
- A confidence-based framework for disambiguating geographic terms2003
- Disambiguating Geographic Names in a Historical Digital Library2001