Closed b3ade closed 2 years ago
Hi, we essentially propose a way to extract alignments from mBERT and propose objectives to fine-tune mBERT on parallel data for word alignment. For the table in README, Ours (w/o fine-tuning, softmax)
is the mBERT model performance using our alignment extraction method.
Do you have any statistics or model performance between mBERT, model_without_co and model_with_co? I see that you have alignment error rates on your models between aligners. So I'm wondering if you have any information on how your model is different from mBERT.