自然语言处理实践Task6

基于Bert的文本分类

Bert Pretrain

class WhitespaceTokenizer(object):
    """WhitespaceTokenizer with vocab."""
    def __init__(self, vocab_file):
        self.vocab = load_vocab(vocab_file)
        self.inv_vocab = {v: k for k, v in self.vocab.items()}

    def tokenize(self, text):
        split_tokens = whitespace_tokenize(text)
        output_tokens = []
        for token in split_tokens:
            if token in self.vocab:
                output_tokens.append(token)
            else:
                output_tokens.append("[UNK]")
        return output_tokens

    def convert_tokens_to_ids(self, tokens):
        return convert_by_vocab(self.vocab, tokens)

    def convert_ids_to_tokens(self, ids):
        return convert_by_vocab(self.inv_vocab, ids)

def create_segments_from_document(document, max_segment_length):
    """Split single document to segments according to max_segment_length."""
    assert len(document) == 1
    document = document[0]
    document_len = len(document)

    index = list(range(0, document_len, max_segment_length))
    other_len = document_len % max_segment_length
    if other_len > max_segment_length / 2:
        index.append(document_len)

    segments = []
    for i in range(len(index) - 1):
        segment = document[index[i]: index[i+1]]
        segments.append(segment)

    return segments

(masked_lm_loss, masked_lm_example_loss, masked_lm_log_probs) = get_masked_lm_output(
    bert_config, model.get_sequence_output(), model.get_embedding_table(),
    masked_lm_positions, masked_lm_ids, masked_lm_weights)

total_loss = masked_lm_loss

详细配置

{
  "hidden_size": 256,
  "hidden_act": "gelu",
  "initializer_range": 0.02,
  "vocab_size": 5981,
  "hidden_dropout_prob": 0.1,
  "num_attention_heads": 4,
  "type_vocab_size": 2,
  "max_position_embeddings": 256,
  "num_hidden_layers": 4,
  "intermediate_size": 1024,
  "attention_probs_dropout_prob": 0.1
}

def convert_tf_checkpoint_to_pytorch(tf_checkpoint_path, bert_config_file, pytorch_dump_path):
    # Initialise PyTorch model
    config = BertConfig.from_json_file(bert_config_file)
    print("Building PyTorch model from configuration: {}".format(str(config)))
    model = BertForPreTraining(config)

    # Load weights from tf checkpoint
    load_tf_weights_in_bert(model, config, tf_checkpoint_path)

    # Save pytorch-model
    print("Save PyTorch model to {}".format(pytorch_dump_path))
    torch.save(model.state_dict(), pytorch_dump_path)

Bert Finetune

sequence_output, pooled_output = \
    self.bert(input_ids=input_ids, token_type_ids=token_type_ids)

if self.pooled:
    reps = pooled_output
else:
    reps = sequence_output[:, 0, :]  # sen_num x 256

if self.training:
    reps = self.dropout(reps)