Glossary term
Glossary term
Evaluation and Benchmarks
An edit distance metric that calculates the fewest delete, insert, and substitute operations required to change one word to another. For example, the Levenshtein distance between the words "heart" and "darts" is three because the following three edits are the fewest changes to turn one word into the other:
heart → deart (substitute "h" with "d")
deart → dart (delete "e")
dart → darts (insert "s")
Note that the preceding sequence isn't the only path of three edits.
Created for this library
A search team uses Levenshtein distance to suggest spelling corrections for misspelled product names in the search bar.
A data quality team uses Levenshtein distance to match noisy company names across vendor lists for deduplication.
An OCR team uses Levenshtein distance to compare model output against ground truth at the character level.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License