Bert【1】-基础

def convert_single_example(ex_index, example, label_list, max_seq_length,
                           tokenizer):
    """Converts a single `InputExample` into a single `InputFeatures`."""

    if isinstance(example, PaddingInputExample):
        return InputFeatures(
            input_ids=[0] * max_seq_length,
            input_mask=[0] * max_seq_length,
            segment_ids=[0] * max_seq_length,
            label_id=0,
            is_real_example=False)

    label_map = {}
    for (i, label) in enumerate(label_list):
        label_map[label] = i

    tokens_a = tokenizer.tokenize(example.text_a)
    tokens_b = None
    if example.text_b:
        tokens_b = tokenizer.tokenize(example.text_b)

    if tokens_b:
        # Modifies `tokens_a` and `tokens_b` in place so that the total
        # length is less than the specified length.
        # Account for [CLS], [SEP], [SEP] with "- 3"
        _truncate_seq_pair(tokens_a, tokens_b, max_seq_length - 3)
    else:
        # Account for [CLS] and [SEP] with "- 2"
        if len(tokens_a) > max_seq_length - 2:
            tokens_a = tokens_a[0:(max_seq_length - 2)]

    # The convention in BERT is:
    # (a) For sequence pairs:
    #  tokens:   [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]
    #  type_ids: 0     0  0    0    0     0       0 0     1  1  1  1   1 1
    # (b) For single sequences:
    #  tokens:   [CLS] the dog is hairy . [SEP]
    #  type_ids: 0     0   0   0  0     0 0
    #
    # Where "type_ids" are used to indicate whether this is the first
    # sequence or the second sequence. The embedding vectors for `type=0` and
    # `type=1` were learned during pre-training and are added to the wordpiece
    # embedding vector (and position vector). This is not *strictly* necessary
    # since the [SEP] token unambiguously separates the sequences, but it makes
    # it easier for the model to learn the concept of sequences.
    #
    # For classification tasks, the first vector (corresponding to [CLS]) is
    # used as the "sentence vector". Note that this only makes sense because
    # the entire model is fine-tuned.
    tokens = []
    segment_ids = []
    tokens.append("[CLS]")
    segment_ids.append(0)
    for token in tokens_a:
        tokens.append(token)
        segment_ids.append(0)
    tokens.append("[SEP]")
    segment_ids.append(0)

    if tokens_b:
        for token in tokens_b:
            tokens.append(token)
            segment_ids.append(1)
        tokens.append("[SEP]")
        segment_ids.append(1)

    input_ids = tokenizer.convert_tokens_to_ids(tokens)

    # The mask has 1 for real tokens and 0 for padding tokens. Only real
    # tokens are attended to.
    input_mask = [1] * len(input_ids)

    # Zero-pad up to the sequence length.
    while len(input_ids) < max_seq_length:
        input_ids.append(0)
        input_mask.append(0)
        segment_ids.append(0)

    label_id = label_map[example.label]

    feature = InputFeatures(
        input_ids=input_ids,
        input_mask=input_mask,
        segment_ids=segment_ids,
        label_id=label_id,
        is_real_example=True)
    return feature

def create_model(bert_config, is_training, input_ids, input_mask, segment_ids,
                 labels, num_labels, use_one_hot_embeddings):
    """Creates a classification model."""
    model = modeling.BertModel(
        config=bert_config,
        is_training=is_training,
        input_ids=input_ids,
        input_mask=input_mask,
        token_type_ids=segment_ids,
        use_one_hot_embeddings=use_one_hot_embeddings)

    # In the demo, we are doing a simple classification task on the entire
    # segment.
    #
    # If you want to use the token-level output, use model.get_sequence_output()
    # instead.
    output_layer = model.get_pooled_output()

    hidden_size = output_layer.shape[-1].value

    output_weights = tf.get_variable(
        "output_weights", [num_labels, hidden_size],
        initializer=tf.truncated_normal_initializer(stddev=0.02))

    output_bias = tf.get_variable(
        "output_bias", [num_labels], initializer=tf.zeros_initializer())

    with tf.variable_scope("loss"):
        if is_training:
            # I.e., 0.1 dropout
            output_layer = tf.nn.dropout(output_layer, keep_prob=0.9)

        logits = tf.matmul(output_layer, output_weights, transpose_b=True)
        logits = tf.nn.bias_add(logits, output_bias)
        probabilities = tf.nn.softmax(logits, axis=-1)
        log_probs = tf.nn.log_softmax(logits, axis=-1)

        one_hot_labels = tf.one_hot(labels, depth=num_labels, dtype=tf.float32)

        per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
        loss = tf.reduce_mean(per_example_loss)

        return (loss, per_example_loss, logits, probabilities)

多标签分类
如输入 一件 L 尺寸的棉服，输出两个标签——型号：L，类型：冬装
BERT 模型解决多标签分类问题时，其输入与普通单标签分类问题一致，得到其 embedding 表示之后(也就是 BERT 输出层的 embedding)，
有几个 label 就连接到几个全连接层(也可以称为 projection layer)，然后再分别接上 softmax 分类层，最后再将所有的 loss 相加起来即可。
这种做法就相当于将 n 个分类模型的特征提取层参数共享，得到一个共享的表示(其维度可以视任务而定，由于是多标签分类任务，因此其维度可以适当
增大一些)，最后再做多标签分类任务。