MQM/LQM examples batches & MQM/LQM test

AppraiseDev / Appraise

Appraise code used as part of WMT21 human evaluation campaign

BSD 3-Clause "New" or "Revised" License

22 stars 12 forks source link

MQM/LQM examples batches & MQM/LQM test #129

Closed zouharvi closed 8 months ago

zouharvi commented 8 months ago

As discussed in https://github.com/AppraiseDev/Appraise/pull/128#issuecomment-1953854730, this fixes the default batches (compatible with code in Examples/DirectMQM/README.md) and adds a basic test for MQM and LQM.

Btw I linted the MakeAnnotation.py with black -S -l 88 but it changed a lot of lines. Not sure if it just wasn't linted before?

zouharvi commented 8 months ago

Fixed also the two failing tests in 97c3c05. It was caused by changes in EvalView/views.py.

snukky commented 8 months ago

Thanks!

Btw I linted the MakeAnnotation.py with black -S -l 88 but it changed a lot of lines. Not sure if it just wasn't linted before?

This is weird, did you use black 22.3.0? Maybe another version by default is more strict about quotes than that one. Anyway, it seems black doesn't complain, so good to go for now. We can double check or improve this later.