Bert 相似度任务

class SimProcessor(DataProcessor):
  def __init__(self):
    self.language = "zh"

  def get_train_examples(self, data_dir):
    return self._create_examples(
        self._read_tsv(os.path.join(data_dir, "train.tsv")), "train")

  def get_dev_examples(self, data_dir):
    return self._create_examples(
        self._read_tsv(os.path.join(data_dir, "dev.tsv")), "dev")

  def get_test_examples(self, data_dir):
    return self._create_examples(
        self._read_tsv(os.path.join(data_dir, "test.tsv")), "test")

  def get_labels(self):
    # 所有标签
    return ["0", "1"]

  def _create_examples(self, lines, set_type):
    """Creates examples for the training and dev sets."""
    examples = []
    for (i, line) in enumerate(lines):
      if i == 0:
        continue
      guid = "%s-%s" % (set_type, i)
      label = tokenization.convert_to_unicode(line[2])
      text_a = tokenization.convert_to_unicode(line[0])
      text_b = tokenization.convert_to_unicode(line[1])
      examples.append( InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label))
      if set_type == "test":
        label = "1"
      else:
        label = tokenization.convert_to_unicode(line[2])
        examples.append(InputExample(guid=guid, text_a=text_a, label=label))
  return examples

export BERT_BASE_DIR=/deep_docs/deeps/chinese_L-12_H-768_A-12
export DATA_DIR=/deep_docs/deeps/data/sim
export OUTPUT_DIR=/deep_docs/deeps/output
export EXP_NAME=sim

CUDA_VISIBLE_DEVICES=3 python run_classifier.py \
  --task_name=sim \
  --do_train=true \
  --do_eval=true \
  --do_predict=true \
  --data_dir=$DATA_DIR\
  --vocab_file=$BERT_BASE_DIR/vocab.txt \
  --bert_config_file=$BERT_BASE_DIR/bert_config.json \
  --init_checkpoint=$BERT_BASE_DIR/bert_model.ckpt \
  --max_seq_length=16 \
  --train_batch_size=32 \
  --learning_rate=2e-5 \
  --num_train_epochs=5.0 \
  --output_dir=$OUTPUT_DIR/$EXP_NAME