Improve metric for candidate selection
R1j1t opened this issue · comments
At present we are using edit distance (Levenshtein distance) which is provided by editdistance package. For many languages (Japanese, Chinese and others) it is not a good similarity score. It was suggested to use strokes score does it have available material to read and implement or any open source package?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
It would be great help if someone can pick this task.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.