bert_ner

bert_ner copied to clipboard

Data download link invalid

4

The data download link is invalid. can you upload another connection? tank you very much

zhouliping03

Cuda out of memory error for finetuning

1

I'm getting the following error when i try to run the finetuning example: RuntimeError: CUDA out of memory. Tried to allocate 85.00 MiB (GPU 0; 4.00 GiB total capacity; 3.04...

n525

Data download link invalid

1

Data download link invalid. thank you！！！

cs-liangchen-work

Update download.sh

1

Hi Kyubyong, Thanks for the amazing work. The directory structure of NeuroNER's repository seems to have changed. This commit is to point train/valid/test.txt files to the correct location.

spookyQubit

The ##word should not be predicted

1

In bert paper, it seems that the words start with '##' should not be predicted. And you did compute is_head variable, but why this variable is not used when computing...

AnblueWang

JianLiu91

F1, recall and precision calculation

1

Hi, I was wondering how you are actually calculating your scores. y_true = np.array([hp.tag2idx[line.split()[1]] for line in open(f, 'r').read().splitlines() if len(line) > 0]) y_pred = np.array([hp.tag2idx[line.split()[2]] for line in open(f,...

rahul-1996

I don't see you do truncate when the sequence longer than 512 lengths?

1

We know that when loading pretrained bert, max_seqence=512, but when you are dealing with the sentences from data set, each sentence is padding based on the longest sentence of the...

Louis-udm

can not find the file pytorch_pretrained_bert.py

1

hi, Thank you for sharing the code. But I can not find the file 'pytorch_pretrained_bert.py', hence I could not run the code. Please tell how can I find the file...

Yuanpengli

Can I use other datasets on this model?

AddSix