iwan-rg/conll2003_translated_AR

--- dataset_info: features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC '7': B-MISC '8': I-MISC splits: - name: train num_bytes: 2770570 num_examples: 10216 - name: validation num_bytes: 695191 num_examples: 2377 - name: test num_bytes: 641211 num_examples: 2543 download_size: 1086541 dataset_size: 4106972 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* ---