Difference between revisions of "Levenshtein distance"

From SurveyWiki
Jump to navigationJump to search
(added link to Cathryn's review of gabmap)
m (moved Levenshtein Distance to Levenshtein distance: internal links won't work if last word isn't capitalised which sucks...)
 
(No difference)

Latest revision as of 14:28, 4 July 2011

Levenshtein Distance is used all the time to compare words with each other. When you do a search in a web page for example, the Levenshtein method is used to compare what you search for with all the words in a page.

We can use this same principle for calculating the difference between varieties that we have word lists of. It's a relatively new area of application and there aren't many survey teams using this method. However, it holds a lot of promise, if you can figure out how to apply it.

Something that might make it easier for us to use it is a promising piece of dialect mapping software called Gabmap

Cathryn Yang has used it and has placed a review on the Software page.

For more info, read the paper by Karin Beijering, Charlotte Gooskens and Wilbert Heeringa online