BertSum
BertSum copied to clipboard
nlpyang
Code for paper Fine-tune BERT for Extractive Summarization
subprocess.CalledProcessError: Command '['/home/sfadmin/summarize/pyrouge/tools/ ROUGE-1.5.5/ROUGE-1.5.5.pl', '-e', '/home/sfadmin/summarize/pyrouge/tools/ROUGE- 1.5.5/data', '-c', '95', '-m', '-r', '1000', '-n', '2', '-a', '../temp/tmpgjaaa8 jv/rouge_conf.xml']' returned non-zero exit status 2. i am getting this error while running following...
Hi.when i am tring to reproduce the results using transformers,i got a problem. Traceback (most recent call last): File "train.py", line 341, in train(args, device_id) File "train.py", line 273, in...
In https://github.com/nlpyang/BertSum/blob/master/src/models/trainer.py#L325 , After sum(), the loss.numel() must be 1 , What different between ` (loss/loss.numel()).backward()` with ` loss.backward()` ? So, I guess, the loss.numel() may express the` n_docs` ?...
Order inconsistency of output candidate file with original test.json when testing bertSum Extractive
Under "test" mode, there will be two files output: xxx.candidate and xxx.gold. The texts in above two files are in the same order, but do not consistent with the original...
Hello! I appreciate and inspire by your great work on Extractive Summarization. So, i had run your script on your github and got Rouge following Rouge Scores: For Transformer On...
Hi, This might be a dumb question but I am not getting it. This model is supposed to perform an extractive summarization process. But when I look at the raw...
`raceback (most recent call last): File "preprocess.py", line 74, in eval('data_builder.'+args.mode + '(args)') File "", line 1, in File "D:\Text-Summarization-with-Pretrained-Encoders\PreSumm-master\src\prepro\data_builder.py", line 133, in tokenize subprocess.call(command) File "D:\ProgramData\Anaconda3\envs\py37-11-2\lib\subprocess.py", line 339, in...
xent started out aroud 40-50, rapidly decrease to 3-4 and seemed to stop deceasing, Is this normal or is there something wrong with my data? Pleases guys give me some...
While training my model on the Arabic language, I was logging some of the values that were getting processed and generated by the model. the following is a sample log...
Hi I wonder will you provide a pretrained extractive summarization model?
