An effective named entity similarity metric for comparing data from multiple sources with varying syntax

This paper describes and demonstrates a names entity similarity metric developed for, and currentlyin use by, the FuzzyPhoto project. The presented metric is effective at comparing named entity datain and across syntax less data schemas such as are often encounter in GLAM collections. Theefficiency of the approach was compared to an existing named entity similarity metric and is shownto be a significant improvement when comparing messy named entity data. Publisher Statement: This is a pre-copyedited, author-produced version of an article accepted for publication in Digital Scholarship in the Humanities following peer review. The version of record Croft, D, Brown, S & Coupland, S 2016, 'An effective Named Entity similarity metric for use with syntax independent data' Digital Scholarship in the Humanities, vol 32, no. 4, pp. 779-787 is available online at: https://dx.doi.org/10.1093/llc/fqw035