2024-mcm-everitt-ryan/possible-bias

--- dataset_info: features: - name: document_id dtype: string - name: phrase_index dtype: int64 - name: phrase_series dtype: int64 - name: source dtype: string - name: country dtype: string - name: company dtype: string - name: position dtype: string - name: terms_count_total dtype: int64 - name: domain_terms dtype: string - name: provisional_terms dtype: string - name: synthetic_terms dtype: string - name: terms_count_age dtype: int64 - name: terms_list_age dtype: string - name: reasons_list_age dtype: string - name: suggestions_list_age dtype: string - name: terms_count_disability dtype: int64 - name: terms_list_disability dtype: string - name: reasons_list_disability dtype: string - name: suggestions_list_disability dtype: string - name: terms_count_general dtype: int64 - name: terms_list_general dtype: string - name: reasons_list_general dtype: string - name: suggestions_list_general dtype: string - name: terms_count_masculine dtype: int64 - name: terms_list_masculine dtype: string - name: reasons_list_masculine dtype: string - name: suggestions_list_masculine dtype: string - name: terms_count_feminine dtype: int64 - name: terms_list_feminine dtype: string - name: reasons_list_feminine dtype: string - name: suggestions_list_feminine dtype: string - name: terms_count_racial dtype: int64 - name: terms_list_racial dtype: string - name: reasons_list_racial dtype: string - name: suggestions_list_racial dtype: string - name: terms_count_sexuality dtype: int64 - name: terms_list_sexuality dtype: string - name: reasons_list_sexuality dtype: string - name: suggestions_list_sexuality dtype: string - name: phrase_character_count dtype: int64 - name: phrase_word_count dtype: int64 - name: phrase_max_word_count dtype: int64 - name: text dtype: string - name: html dtype: string splits: - name: train num_bytes: 22074704875 num_examples: 2519045 download_size: 5971226577 dataset_size: 22074704875 configs: - config_name: default data_files: - split: train path: data/train-* ---