如何在 Keras 中实现分层 Transformer 用于文档分类？

Posted 2023-02-16

【中文标题】如何在 Keras 中实现分层 Transformer 用于文档分类？

【英文标题】：How to implement hierarchical Transformer for document classification in Keras?

【发布时间】：2022-01-13 05:09:33

【问题描述】：

Yang 等人提出了文档分类的分层注意机制。 https://www.cs.cmu.edu/~./hovy/papers/16HLT-hierarchical-attention-networks.pdf

它的实现在https://github.com/ShawnyXiao/TextClassification-Keras上可用

另外，使用 Transformer 进行文档分类的实现在 https://keras.io/examples/nlp/text_classification_with_transformer 上可用

但是，它不是分层的。

我搜索了很多，但没有找到分层 Transformer 的任何实现。有谁知道如何在 Keras 中实现用于文档分类的分层转换器？

我的实现如下。请注意，该实现从 Nandan 实现扩展为文档分类。 https://keras.io/examples/nlp/text_classification_with_transformer.

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from keras.utils.np_utils import to_categorical


class MultiHeadSelfAttention(layers.Layer):
    def __init__(self, embed_dim, num_heads=8):
        super(MultiHeadSelfAttention, self).__init__()
        self.embed_dim = embed_dim
        self.num_heads = num_heads
        if embed_dim % num_heads != 0:
            raise ValueError(
                f"embedding dimension = embed_dim should be divisible by number of heads = num_heads"
            )
        self.projection_dim = embed_dim // num_heads
        self.query_dense = layers.Dense(embed_dim)
        self.key_dense = layers.Dense(embed_dim)
        self.value_dense = layers.Dense(embed_dim)
        self.combine_heads = layers.Dense(embed_dim)

    def attention(self, query, key, value):
        score = tf.matmul(query, key, transpose_b=True)
        dim_key = tf.cast(tf.shape(key)[-1], tf.float32)
        scaled_score = score / tf.math.sqrt(dim_key)
        weights = tf.nn.softmax(scaled_score, axis=-1)
        output = tf.matmul(weights, value)
        return output, weights

    def separate_heads(self, x, batch_size):
        x = tf.reshape(x, (batch_size, -1, self.num_heads, self.projection_dim))
        return tf.transpose(x, perm=[0, 2, 1, 3])

    def call(self, inputs):
        # x.shape = [batch_size, seq_len, embedding_dim]
        batch_size = tf.shape(inputs)[0]
        query = self.query_dense(inputs)  # (batch_size, seq_len, embed_dim)
        key = self.key_dense(inputs)  # (batch_size, seq_len, embed_dim)
        value = self.value_dense(inputs)  # (batch_size, seq_len, embed_dim)
        query = self.separate_heads(
            query, batch_size
        )  # (batch_size, num_heads, seq_len, projection_dim)
        key = self.separate_heads(
            key, batch_size
        )  # (batch_size, num_heads, seq_len, projection_dim)
        value = self.separate_heads(
            value, batch_size
        )  # (batch_size, num_heads, seq_len, projection_dim)
        attention, weights = self.attention(query, key, value)
        attention = tf.transpose(
            attention, perm=[0, 2, 1, 3]
        )  # (batch_size, seq_len, num_heads, projection_dim)
        concat_attention = tf.reshape(
            attention, (batch_size, -1, self.embed_dim)
        )  # (batch_size, seq_len, embed_dim)
        output = self.combine_heads(
            concat_attention
        )  # (batch_size, seq_len, embed_dim)
        return output

    def compute_output_shape(self, input_shape):
        # it does not change the shape of its input
        return input_shape


class TransformerBlock(layers.Layer):
    def __init__(self, embed_dim, num_heads, ff_dim, dropout_rate, name=None):
        super(TransformerBlock, self).__init__(name=name)
        self.att = MultiHeadSelfAttention(embed_dim, num_heads)
        self.ffn = keras.Sequential(
            [layers.Dense(ff_dim, activation="relu"), layers.Dense(embed_dim), ]
        )
        self.layernorm1 = layers.LayerNormalization(epsilon=1e-6)
        self.layernorm2 = layers.LayerNormalization(epsilon=1e-6)
        self.dropout1 = layers.Dropout(dropout_rate)
        self.dropout2 = layers.Dropout(dropout_rate)

    def call(self, inputs, training):
        attn_output = self.att(inputs)
        attn_output = self.dropout1(attn_output, training=training)
        out1 = self.layernorm1(inputs + attn_output)
        ffn_output = self.ffn(out1)
        ffn_output = self.dropout2(ffn_output, training=training)
        return self.layernorm2(out1 + ffn_output)

    def compute_output_shape(self, input_shape):
        # it does not change the shape of its input
        return input_shape


class TokenAndPositionEmbedding(layers.Layer):
    def __init__(self, maxlen, vocab_size, embed_dim, name=None):
        super(TokenAndPositionEmbedding, self).__init__(name=name)
        self.token_emb = layers.Embedding(input_dim=vocab_size, output_dim=embed_dim)
        self.pos_emb = layers.Embedding(input_dim=maxlen, output_dim=embed_dim)

    def call(self, x):
        maxlen = tf.shape(x)[-1]
        positions = tf.range(start=0, limit=maxlen, delta=1)
        positions = self.pos_emb(positions)
        x = self.token_emb(x)
        return x + positions

    def compute_output_shape(self, input_shape):
        # it changes the shape from (batch_size, maxlen) to (batch_size, maxlen, embed_dim)
        return input_shape + (self.pos_emb.output_dim,)



# Lower level (produce a representation of each sentence):

embed_dim = 100  # Embedding size for each token
num_heads = 2  # Number of attention heads
ff_dim = 64  # Hidden layer size in feed forward network inside transformer
L1_dense_units = 100  # Size of the sentence-level representations output by the word-level model
dropout_rate = 0.1
vocab_size = 1000
class_number = 5
max_docs = 10000
max_sentences = 15
max_words = 60

word_input = layers.Input(shape=(max_words,), name='word_input')
word_embedding = TokenAndPositionEmbedding(maxlen=max_words, vocab_size=vocab_size,
                                           embed_dim=embed_dim, name='word_embedding')(word_input)
word_transformer = TransformerBlock(embed_dim=embed_dim, num_heads=num_heads, ff_dim=ff_dim,
                                    dropout_rate=dropout_rate, name='word_transformer')(word_embedding)
word_pool = layers.GlobalAveragePooling1D(name='word_pooling')(word_transformer)
word_drop = layers.Dropout(dropout_rate, name='word_drop')(word_pool)
word_dense = layers.Dense(L1_dense_units, activation="relu", name='word_dense')(word_drop)
word_encoder = keras.Model(word_input, word_dense)

word_encoder.summary()

# =========================================================================
# Upper level (produce a representation of each document):

L2_dense_units = 100

sentence_input = layers.Input(shape=(max_sentences, max_words), name='sentence_input')

sentence_encoder = tf.keras.layers.TimeDistributed(word_encoder, name='sentence_encoder')(sentence_input)

sentence_transformer = TransformerBlock(embed_dim=L1_dense_units, num_heads=num_heads, ff_dim=ff_dim,
                               dropout_rate=dropout_rate, name='sentence_transformer')(sentence_encoder)
sentence_pool = layers.GlobalAveragePooling1D(name='sentence_pooling')(sentence_transformer)
sentence_out = layers.Dropout(dropout_rate)(sentence_pool)
preds = layers.Dense(class_number , activation='softmax', name='sentence_output')(sentence_out)

model = keras.Model(sentence_input, preds)
model.summary()

模型总结如下：

Model: "model_1"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 word_input (InputLayer)     [(None, 60)]              0         
                                                                 
 word_embedding (TokenAndPos  (None, 60, 100)          106000    
 itionEmbedding)                                                 
                                                                 
 word_transformer (Transform  (None, 60, 100)          53764     
 erBlock)                                                        
                                                                 
 word_pooling (GlobalAverage  (None, 100)              0         
 Pooling1D)                                                      
                                                                 
 word_drop (Dropout)         (None, 100)               0         
                                                                 
 word_dense (Dense)          (None, 100)               10100     
                                                                 
=================================================================
Total params: 169,864
Trainable params: 169,864
Non-trainable params: 0
_________________________________________________________________
Model: "model_2"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 sentence_input (InputLayer)  [(None, 15, 60)]         0         
                                                                 
 sentence_encoder (TimeDistr  (None, 15, 100)          169864    
 ibuted)                                                         
                                                                 
 sentence_transformer (Trans  (None, 15, 100)          53764     
 formerBlock)                                                    
                                                                 
 sentence_pooling (GlobalAve  (None, 100)              0         
 ragePooling1D)                                                  
                                                                 
 dropout_9 (Dropout)         (None, 100)               0         
                                                                 
 sentence_output (Dense)     (None, 5)                 505       
                                                                 
=================================================================
Total params: 224,133
Trainable params: 224,133
Non-trainable params: 0

一切正常，你可以将这些代码复制粘贴到 colab 中查看模型的摘要。 但是，我的问题是句子级别的位置编码。 如何在句子级别应用位置编码？

【参考方案1】：

在您将变压器 x 的输出平均值视为变压器 x+1 的输入的意义上，该实现是递归的。

假设您的数据结构为（批次、章节、段落、句子、标记）。

在第一次转换后，您最终得到 (batch, chapter, paragraph, sentence, embedding)，然后平均得到 (batch, chapter, paragraph, sentence_embedding_in)。

应用另一个转换并获取（batch、chample、paragraph、sentence_embedding_out）。

再次平均并获得（批次、章节、段落嵌入）。冲洗并重复。

论文的实现实际上是在不同的存储库中： https://github.com/ematvey/hierarchical-attention-networks

他们实际上做了一些与我所描述的不同的事情，并在底部应用了转换器，在顶部应用了 RNN。从理论上讲，您可以做相反的事情或在每一层应用 RNN（那会非常慢）。就实现而言，您可以从中抽象出来 - 原理保持不变：您应用转换，平均输出并将其馈送到下一个更高级别的“层”（或使用火炬术语的“模块”）。

【讨论】：

非常感谢您的及时回复。我编辑了帖子并添加了我对该模型的实现。您能否查看这些代码并告诉我它是否已正确实施。我的问题是在句子级别的位置编码。根据实现的模型，你能告诉我如何在句子级别进行位置编码吗？

它应该以与单词完全相同的方式完成（您只需将每个句子视为一个单词） - 如果句子顺序很重要的话。在某些情况下它没有，所以你根本不添加任何东西

正如您在代码中看到的，TokenAndPositionEmbedding 将词汇大小作为输入之一。但在句子层面，我没有词汇量。所以我不知道如何应用句子级别的位置编码。有没有可能你看看我的模型并帮我完成它？

也许为每个句子创建一个虚拟标记（例如 0），以便您的 TokenAndPositionEmbedding 仅包含位置组件。然后将生成的嵌入添加到您的实际句子嵌入中。

你能告诉我代码吗？我的代码可以在 colab 中执行，没有任何错误。谢谢你。