BERT句子嵌入:如何获取句子嵌入向量 [英] BERT sentence embeddings: how to obtain sentence embeddings vector

问题描述

我正在使用模块bert-for-tf2来将BERT模型包装为Tensorflow 2.0中的Keras层.我已经按照您的指南将BERT模型实现为Keras层. 我正在尝试从句子中提取嵌入内容；在我的情况下，句子是你好"

I'm using the module bert-for-tf2 in order to wrap BERT model as Keras layer in Tensorflow 2.0 I've followed your guide for implementing BERT model as Keras layer. I'm trying to extract embeddings from a sentence; in my case, the sentence is "Hello"

我对模型预测的输出有疑问；我已经写了这个模型:

I have a question about the output of the model prediction; I've written this model:

model_word_embedding = tf.keras.Sequential([
                tf.keras.layers.Input(shape=(4,), dtype='int32', name='input_ids'),
                bert_layer
])

model_word_embedding .build(input_shape=(None, 4))

然后我要提取上面写的句子的嵌入物:

Then I want to extract the embeddings for the sentence written above:

sentences = ["Hello"]
predict = model_word_embedding .predict(sentences)

对象预测包含4个数组，每个数组包含768个元素:

the object predict contains 4 arrays of 768 elements each:

print(predict)
print(len(predict))
print(len(predict[0][0]))
...

[[[-0.02768866 -0.7341324   1.9084396  ... -0.65953904  0.26496622
    1.1610721 ]
  [-0.19322394 -1.3134469   0.10383344 ...  1.1250225  -0.2988368
   -0.2323082 ]
  [-1.4576151  -1.4579685   0.78580517 ... -0.8898649  -1.1016986
    0.6008501 ]
  [ 1.41647    -0.92478925 -1.3651332  ... -0.9197768  -1.5469263
    0.03305872]]]
4
768

我知道那个4的每个数组代表我的原始句子，但是我想获得一个数组作为我的原始句子的嵌入. 因此，我的问题是:如何获得句子的嵌入?

I know that each array of that 4 represents my original sentence, but I want to obtain one array as the embeddings of my original sentence. So, my question is: How can I obtain the embeddings for a sentence?

在BERT源代码中，我读到了这篇文章:

In BERT source code I read this:

对于分类任务，第一个向量(对应于[CLS])用作句子向量".请注意，这仅是有意义的，因为对整个模型进行了微调.

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.

所以我必须从预测输出中提取第一个数组，因为它代表了我的句子矢量?

So I have to take the first array from the prediction output since it represents my sentence vector?

感谢您的支持

推荐答案

我们应该使用最后隐藏状态中的[CLS]作为BERT的句子嵌入.根据BERT论文，[CLS]代表维度768的编码语句.下图更详细地表示[CLS]的使用.考虑到你有2000个句子.

We should use [CLS] from the last hidden states as the sentence embeddings from BERT. According to the BERT paper [CLS] represent the encoded sentence of dimension 768. Following figure represents the use of [CLS] in more details. considering you have 2000 sentences.

#input_ids consist of all sentences padded to max_len. 
last_hidden_states = model(input_ids)
features = last_hidden_states[0][:,0,:].numpy() # considering o only the [CLS] for each sentences 
features.shape
# (2000, 768) dimension

这篇关于BERT句子嵌入:如何获取句子嵌入向量的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！