Model Card for Cardioner Model --Disease

This a ufal/robeczech-base base model finetuned for span classification. For this model we used IOB-tagging. Using the IOB-tagging schema facilitates the aggregation of predictions over sequences. This specific model is trained on a batch of 240 span-labeled documents.

Expected input and output

The input should be a string with Dutch cardio clinical text.

CardioNER model --disease is a multilabel-multiclass span classification model. The classes that can be predicted are ['disease'].

Extracting span classification from CardioNER model --disease

The following script converts a string of <512 tokens to a list of span predictions.

from transformers import pipeline

le_pipe = pipeline('ner',
                    model=model,
                    tokenizer=model, aggregation_strategy="simple",
                    device=-1)

named_ents = le_pipe(SOME_TEXT)

To process a string of arbitrary length you can split the string into sentences or paragraphs using e.g. pysbd or spacy(sentencizer) and iteratively parse the list of with the span-classification pipe. You can also use the strider built in the transformer pipeline, although this is limited to non-overlapping strides plus it requires a FastTokenizer and it does not work for aggregation_strategy=None;

named_ents = le_pipe(SOME_TEXT, stride=256)

Data description

50/50 Train/validation split on CardioCCC, a manually labeled cardiology corpus

Acknowledgement

This is part of the DT4H project.

Doi and reference

For more details about training/eval and other scripts, see CardioNER github repo. and for more information on the background, see Datatools4Heart Huggingface/Website