Eval mean median - Githubissues

alan-turing-institute / ARC-MTQE

Critical Error Detection for Machine Translation

MIT License

1 stars 0 forks source link

Eval mean median #92

Closed joannacknight closed 5 months ago

joannacknight commented 6 months ago

This PR updates the evaluation script eval_ced.py to calculate the mean and median MCC values for each threshold strategy, language pair and data split.

review-notebook-app[bot] commented 6 months ago

Check out this pull request on

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

joannacknight commented 5 months ago

Updated code to simplify the median calculation! Thought I was missing something. Did it a slightly different way to your suggestion as I wanted to record other values, such as the random seed with the median MCC. If you can think of a(nother) better way to do it then do let me know!