sitingGZ/german-bert-clinical-ner

---

Model Description

• **Finetuned from model: bert-base-german-cased

Model Sources

• **Repository: https://github.com/sitingGZ/bert-sner
• **Paper : BERT-SNER
• **Demo (Coming soon)

Uses

import sys
sys.path.append('modules')

import torch
from transformers import AutoConfig, AutoTokenizer, AutoModelForMaskedLM, EncoderDecoderConfig
from BERT2span_semantic_disam import BERT2span
from helpers import load_config, set_seed
from inference import final_label_results_rescaled

base_name =  "bert-base-german-cased"
configs = load_config('configs/step3_gpu_span_semantic_group.yaml')
tokenizer = AutoTokenizer.from_pretrained(base_name)
bertMLM = AutoModelForMaskedLM.from_pretrained(base_name)
bert_sner = BERT2span(configs, bertMLM, tokenizer)

checkpoint_path = "checkpoints/german_bert_ex4cds_500_semantic_term.ckpt"
state_dict = torch.load(checkpoint_path, map_location=torch.device('cpu'))
bert_sner.load_state_dict(state_dict)
bert_sner.eval()

suggested_terms = {'Condition': 'Zeichen oder Symptom',
               'DiagLab': 'Diagnostisch und Laborverfahren',
                'LabValues': 'Klinisches Attribut',
                 'HealthState': 'Gesunder Zustand',
                 'Measure': 'Quantitatives Konzept',
                 'Medication': 'Pharmakologische Substanz',
                 'Process': 'Physiologische Funktion',
                 'TimeInfo': 'Zeitliches Konzept'}

words = "Aktuell Infekt mit Nachweis von E Coli und Pseudomonas im TBS- CRP 99mg/dl".split()
words_list = [words]
heatmaps, ner_results = final_label_results_rescaled(words_list, tokenizer, bert_sner, suggested_terms, threshold=0.5)

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]