cisnlp/simalign

Evaluation Scripts & Results Reproduction

Closed this issue · 4 comments

Thanks for the impressive work of SimAlign.

Currently I am working on reproducing the results in your paper, but I don't know how to compute the redefined precision and recall measures presented by Och & Ney, 2003, i.e., which labels should be S labels or P labels?

Could you please provide the eavluation scripts on the test sets used in paper?

Thanks.

Hi @qianliu0708 we plan to add the evaluation scripts soon.

Hi @pdufter, thanks a lot to you and your collaborators on this very interesting work. When your time permits, it would indeed be great if evaluation scripts are provided to reproduce the scores. -- Thanks.

Hi @spookyQubit,
We have added the evaluation script as well as some sample sentences with gold alignments.
If there are any issues with the code or the samples, please reach out to us.

@masoudjs thanks a lot. Really appreciate it.