Skip to main content

Evaluation Metrics

Evaluation Metrics for NeuralSpace Transliteration Service​

Let us learn about the two different evaluation metrics that we use to examine the performance of Transliteration models!

  1. Jaro Similarity

The Jaro distance is a measure of edit distance between two strings; its inverse, called the Jaro similarity

It is a measure of two strings' similarity i.e, The higher the value, the more similar the strings are.

note

The score is normalized such that 0% equates to no similarities and 100% is an exact match.

  1. Levenshtein distance:

Levenshtein distance is a metric for calculating the dissimilarity between 2 strings. It is the minimum number of single characters that one needs to edit in one string (including insertions, deletions and alterations) to change it into the other.

note

When comparing 2 words, lower Levenshtein distance means they are more similar.

Last updated on