transform_file.yml

sample_transform1:
  transform_func: snips_intent_ner
  read_file_names:
    - snips_train.txt
    - snips_dev.txt
    - snips_test.txt
  read_dir: snips_data
  save_dir: demo_transform

sample_transform2:
  transform_func: coNLL_pos_ner
  read_file_names:
    - coNLL_train.txt
    - coNLL_testa.txt
    - coNLL_testb.txt
  read_dir: coNLL_data
  save_dir: demo_transform

sample_transform3:
  transform_func: snli_entailment
  read_file_names:
    - snli_train.jsonl
    - snli_dev.jsonl
    - snli_test.jsonl
  read_dir : snli_data
  save_dir: demo_transform

sample_transform4:
  transform_func: bio_ner
  transform_params:
    save_prefix : sample
    tag_col : 1
    col_sep : " "
    sen_sep : "\n"
  read_file_names:
    - coNLL_train.txt
    - coNLL_testa.txt
    - coNLL_testb.txt

  read_dir: coNLL_data
  save_dir: demo_transform

sample_transform5:
  transform_func: fragment
  transform_params:
    data_frac : 0.2
    seq_len_right : 3
    seq_len_left : 2
    sep : "\t"
    query_col : 2
  read_file_names:
    - int_snips_train.tsv
    - int_snips_dev.tsv
    - int_snips_test.tsv

  read_dir: data
  save_dir: demo_transform

sample_transform6:
  transform_func: msmarco_query_type
  transform_params:
    data_frac : 0.2
  read_file_names:
    - train_v2.1.json
    - dev_v2.1.json
    - eval_v2.1_public.json

  read_dir: msmarco_qna_data
  save_dir: demo_transform