Machine learning innovations in address matching: A practical comparison of word2vec and CRFs



Comber, S and Arribas-Bel, D
(2019) Machine learning innovations in address matching: A practical comparison of word2vec and CRFs. Transactions in GIS, 23 (2). 334 - 348.

This is the latest version of this item.

[img] Text
Comber_et_al-2019-Transactions_in_GIS.pdf - OA Published Version

Download (674kB)

Abstract

© 2019 The Authors. Transactions in GIS published by John Wiley & Sons Ltd Record linkage is a frequent obstacle to unlocking the benefits of integrated (spatial) data sources. In the absence of unique identifiers to directly join records, practitioners often rely on text-based approaches for resolving candidate pairs of records to a match. In geographic information science, spatial record linkage is a form of geocoding that pertains to the resolution of text-based linkage between pairs of addresses into matches and non-matches. These approaches link text-based address sequences, integrating sources of data that would otherwise remain in isolation. While recent innovations in machine learning have been introduced in the wider record linkage literature, there is significant potential to apply machine learning to the address matching sub-field of geographic information science. As a response, this paper introduces two recent developments in text-based machine learning—conditional random fields and word2vec—that have not been applied to address matching, evaluating their comparative strengths and drawbacks.

Item Type: Article
Depositing User: Symplectic Admin
Date Deposited: 24 Apr 2019 10:57
Last Modified: 27 May 2022 15:10
DOI: 10.1111/tgis.12522
Open Access URL: https://onlinelibrary.wiley.com/doi/epdf/10.1111/t...
URI: https://livrepository.liverpool.ac.uk/id/eprint/3038194

Available Versions of this Item