Deriving Spelling Variants from User Queries to Improve Geocoding Accuracy

Konstantin Clemens

2019

Abstract

In previous research, to mimic user queries with typos and abbreviations, a statistical model was used. It was trained to generate spelling variants of address terms that a human would use. A geocoding system enhanced with these spelling variants proved to yield results with higher precision and recall. To train the statistical model, thus far, user queries and their expected results were required to be linked with each other. Such training data is very costly to obtain. In this paper, a novel approach to derive such spelling variants from user queries alone is proposed. A linkage between collected user queries and result addresses is no longer required. The experiment conducted proves that this approach is a reasonable way to observe, derive, and index spelling variants too, allowing to measurably improve the precision and recall metrics of a geocoder.

Paper Citation

in Harvard Style

Clemens K. (2019). Deriving Spelling Variants from User Queries to Improve Geocoding Accuracy.In Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management - Volume 1: GISTAM, ISBN 978-989-758-371-1, pages 53-59. DOI: 10.5220/0007685700530059

in Bibtex Style

@conference{gistam19,
author={Konstantin Clemens},
title={Deriving Spelling Variants from User Queries to Improve Geocoding Accuracy},
booktitle={Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management - Volume 1: GISTAM,},
year={2019},
pages={53-59},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007685700530059},
isbn={978-989-758-371-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management - Volume 1: GISTAM,
TI - Deriving Spelling Variants from User Queries to Improve Geocoding Accuracy
SN - 978-989-758-371-1
AU - Clemens K.
PY - 2019
SP - 53
EP - 59
DO - 10.5220/0007685700530059