bert_document_classification

bert_document_classification copied to clipboard

While observing few predictions, I came across few examples where the model predicted [0,0,0,0]. In such cases, the micro-average F1-score is 0.75. For such cases how do we calculate FPR(False...

shaswatpatel123

Reading the way labels are being handled in the [training script](https://github.com/AndriyMulyar/bert_document_classification/blob/572883204cb1aca50d346979319905f698ad7049/examples/ml4health_2019_replication/predict_n2c2_2008.py) and [pred script](https://github.com/AndriyMulyar/bert_document_classification/blob/572883204cb1aca50d346979319905f698ad7049/examples/ml4health_2019_replication/predict_n2c2_2008.py), for each label (i.e. "Obesity" and the co-morbidities) the classes simply converted to binary (`if intuitive[name]...

bwang482

The paper claims that the threshold was 0.5 however in the code, specifically in the predict method in document_bert.py, the threshold's default value is 0. In the fit method, the...

zeinramadan

I am using a custom dataset for a multiclass classification problem where my data points only belong to one class (mutually exclusive case, only 1 label per sample and not...

zeinramadan

TypeError: forward() missing 2 required positional arguments: 'document_batch' and 'document_sequence_lengths'

2

I don't understand this error message that I am getting, did anybody experience anything similar? I am running the training script provided in examples on my own dataset, making sure...

zeinramadan

Target size (torch.Size([10])) must be the same as input size (torch.Size([10, 6]))

2

Another error occurs while running DocumentBertLSTM: _ValueError Traceback (most recent call last) in () 7 8 model = BertForDocumentClassification(args=args) ----> 9 model.fit((train_documents, train_labels), (dev_documents,dev_labels)) 3 frames /usr/local/lib/python3.7/dist-packages/bert_document_classification/document_bert.py in fit(self, train,...

basti97

forward() got an unexpected keyword argument 'device'

1

Hello, thanks for sharing your code. I am new to BERT and finetuning and I tried your code with costumn data. I recieved following error on running DocumentBertMaxPool/DocumentBertLinear: _` batch_predictions...

basti97

mean vs identity pooling?

4

Hi, The paper describes four pooling functions: 1. Mean, 2. Identity, 3. Transformer, and 4. LSTM. I am confused between ```mean``` and ```identity```. I follow that ```mean``` means simply average...

vr25

cannot import name '_VF'

2

Receiving following error on running ``` --------------------------------------------------------------------------- ImportError Traceback (most recent call last) in () ----> 1 from bert_document_classification.models import SmokerPhenotypingBert 2 from bert_document_classification.models import ObesityPhenotypingBert 3 4 smoking_classifier =...

Jheel-patel

I want to change the bert model, and I changed the config.ini in order to use my own model. but my model was training by transformers api and got the...

davendw49