A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching
Authors:
Open Access
- 3 November 2020
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 385-388
Abstract
Recognizing toponyms and resolving them to their real-world referents is required to provide advanced semantic access to textual data. This process is often hindered by the high degree of variation in toponyms. Candidate selection is the task of identifying the potential entities that can be referred to by a previously recognized toponym. While it has traditionally received little attention, candidate selection has a significant impact on downstream tasks (i.e. entity resolution), especially in noisy or non-standard text. In this paper, we introduce a deep learning method for candidate selection through toponym matching, using state-of-the-art neural network architectures. We perform an intrinsic toponym matching evaluation based on several datasets, which cover various challenging scenarios (cross-lingual and regional variations, as well as OCR errors) and assess its performance in the context of geographical candidate selection in English and Spanish.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Distant Learning for Entity Linking with Automatic Noise Detection2019
- Geographic Information Retrieval: Progress and Challenges in Spatial Search of TextFoundations and Trends® in Information Retrieval, 2018
- Geoparsing, GIS, and Textual Analysis: Current Developments in Spatial Humanities ResearchInternational Journal of Humanities and Arts Computing, 2015
- GeoBench2014
- Analyzing geographic query reformulation: An exploratory studyJournal of the Association for Information Science and Technology, 2013
- A Comparison of String Similarity Measures for Toponym Matching2013
- Evaluating Entity Linking with WikipediaArtificial Intelligence, 2013
- Determining the spatial reader scopes of news sources using local lexicons2010
- You are where you tweet2010
- Analysis of geographic queries in a search engine log2008