henryk/bert-base-multilingual-cased-finetuned-dutch-squad2

Using the mtranslate Python module, SQuAD2.0 was machine-translated . The model was trained on cased text in the top 104 languages with the largest Wikipedias. The model is the multilingual model provided by the Google research team with a fine-tuned dutch Q&A downstream task. This is a potential problem where errors can occur in the data set. The answer could not always be found in the text, and thus a loss of question-answer examples occurred . The question-answering was trained using a Tesla V100 GPU with the following command: --train_file $SQUAD_DIR/nl_squadv2_,