ghaddarAbs
ghaddarAbs
In order to reproduce the conll score reported in BERT paper (92.4 bert-base and 92.8 bert-large) one trick is to apply a truecaser on article titles (all upper case sentences)...
In order to reproduce the conll score reported in BERT paper (92.4 bert-base and 92.8 bert-large) one trick is to apply a truecaser on article titles (all upper case sentences)...
Hello, Is there a way to give a score for a gine sentence ??? say a perplexity score
In order to reproduce the conll score reported in BERT paper (92.4 bert-base and 92.8 bert-large) one trick is to apply a truecaser on article titles (all upper case sentences)...
It seem that cat can't handle the large number of *.gold_conll in the train portion. The script print this warning and continue: `./scripts/make_conll2012_data.sh: line 19: /bin/ls: Argument list too long`...
Hi, Thank you very much for the great work, and for sharing the fine-tuning data last week. I got an issue when I tried to fine-tune and evaluate the model...
Hi, Thank you very much for the great work, and for making your code publicly available. I am trying to run the code to reproduce the results, however, the pre-training...
In order to reproduce the conll score reported in BERT paper (92.4 bert-base and 92.8 bert-large) one trick is to apply a truecaser on article titles (all upper case sentences)...
I tested the code with tf 1.12 and it works well. It is helpful for people that use tf 1.12 because cudnn of tf 1.7 and 1.12 aren't compatible. This...
Hi, Thanks for sharing the code and models of your great paper. I think that you miss calculating the rouge scores for Text summarization task in your paper. The bug...