tian312 / pico_parser Goto Github PK

Hi, I've used BERT Parser as you said and tried to get a prediction on test data you provided but I got nothing except, exceptionlist.txt in the output directory.
I replaced downloadedbluebert_pretrained_ori.tar.gz with the same folder in the directory and put the NCBI_BERT's files in the bert_init_models folder and just modified bluebert_dir = "bluebert_pretrained_ori" am I right?
I would be grateful if you could help me.

Hi,

Could you please share 170 annotated publications? https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6852618/

Best regards,
Elena

In your documentation for LSTM parser you mention that LSTM_Parser/cluster/model/download.txt contains a link for the context vector download. This download link is broken:

https://drive.google.com/open?id=1Qs0--7eX9dMq4ngQQRpG_VnYGygGdIaF

Is there another download link that would work? Thanks!

Hi, I've tried to evaluate your model with scibert pico data set, but the tokenization wasn't the same, could you please share the F1 score you get?

Hi Tian,

I'm interested in your work and have some questions.

• Did you use PubMed abstracts to train the model? if so, how large is it?
• Could you provide performance of model on your test data, such as f1 score?

Thanks a lot in advance.

Hi Tian,
Would you be able to share pubmed_util_batch.py script please?It's currently a soft link to your local dir. Thank you in advance!
https://github.com/Tian312/PICO_Parser/blob/master/BERT_Parser/text_processing/pubmed_util_batch.py

Hi!

I've already installed the requirements but if I try to run the example I have the next error:

'tensorflow' has no attribute 'flags'

Loading customized config and text tokenizer...
2020-11-10 21:26:21.042753: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcudart.so.10.1'; dlerror: libcudart.so.10.1: cannot open shared object file: No such file or directory
2020-11-10 21:26:21.042783: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
ln: failed to create symbolic link 'QuickUMLS': File exists
Traceback (most recent call last):
File "run_bluebert_ner_predict.py", line 34, in
flags = tf.flags
AttributeError: module 'tensorflow' has no attribute 'flags'

How can I solve that problem?