用于语义相似性的 BERT 嵌入
Posted
技术标签:
【中文标题】用于语义相似性的 BERT 嵌入【英文标题】：BERT embedding for semantic similarity 【发布时间】：2020-07-14 17:16:26 【问题描述】：我之前发布了这个question。我想嵌入类似于youtube 视频，时间从 33 分钟开始。
1) 我不认为我从 CLS 令牌获得的嵌入与 youtube 视频中显示的类似。我试图执行语义相似性并得到可怕的结果。有人可以确认我得到的嵌入是否类似于视频 35.27 标记处提到的嵌入？
2) 如果上述问题的答案是“不相似”，那么我如何使用我编写的代码获得我正在寻找的嵌入？
3) 如果第一个问题的答案是“它们相似”，那么为什么我会得到可怕的结果？我需要使用更多数据进行微调吗？
更新 1
我用来微调的代码如下。它来自这个page。对该代码进行了少量更改以返回 CLS 嵌入。这些更改基于对我的question的回答
train_InputExamples = train2.apply(lambda x: run_classifier.InputExample(guid=None, # Globally unique ID for bookkeeping, unused in this example
text_a = x[DATA_COLUMN],
text_b = None,
label = x[LABEL_COLUMN]), axis = 1)
"""
test_InputExamples = test2.apply(lambda x: run_classifier.InputExample(guid=None,
text_a = x[DATA_COLUMN],
text_b = None,
label = x[LABEL_COLUMN]), axis = 1)
"""
# In[17]:
# This is a path to an uncased (all lowercase) version of BERT
BERT_MODEL_HUB = "https://tfhub.dev/google/bert_uncased_L-12_H-768_A-12/1"
# In[18]:
#Create tokenizer function using local albert model hub
def create_tokenizer_from_hub_module():
"""Get the vocab file and casing info from the Hub module."""
with tf.Graph().as_default():
bert_module = hub.Module(BERT_MODEL_HUB)
tokenization_info = bert_module(signature="tokenization_info", as_dict=True)
with tf.Session() as sess:
vocab_file, do_lower_case = sess.run([tokenization_info["vocab_file"],
tokenization_info["do_lower_case"]])
return tokenization.FullTokenizer(
vocab_file=vocab_file, do_lower_case=do_lower_case, spm_model_file=vocab_file)
tokenizer = create_tokenizer_from_hub_module()
#Test tokenizer on a sample sentence
tokenizer.tokenize("This here's an example of using the ALBERT tokenizer")
# In[19]:
# We'll set sequences to be at most 128 tokens long.
MAX_SEQ_LENGTH = 512
# Convert our train and test features to InputFeatures that BERT understands.
train_features = run_classifier.convert_examples_to_features(train_InputExamples, label_list, MAX_SEQ_LENGTH, tokenizer)
"""
test_features = run_classifier.convert_examples_to_features(test_InputExamples, label_list, MAX_SEQ_LENGTH, tokenizer)
"""
# In[20]:
# `create_model` builds a model. First, it loads the BERT tf hub module again (this time to extract the computation graph).
#Next, it creates a single new layer that will be trained to adapt BERT to our task
#(i.e. classifying text). This strategy of using a mostly trained model is called [fine-tuning](http://wiki.fast.ai/index.php/Fine_tuning).
def create_model(is_predicting, input_ids, input_mask, segment_ids, labels,
num_labels):
"""Creates a classification model."""
bert_module = hub.Module(
BERT_MODEL_HUB,
trainable=True)
bert_inputs = dict(
input_ids=input_ids,
input_mask=input_mask,
segment_ids=segment_ids)
bert_outputs = bert_module(
inputs=bert_inputs,
signature="tokens",
as_dict=True)
# Use "pooled_output" for classification tasks on an entire sentence.
# Use "sequence_outputs" for token-level output.
output_layer = bert_outputs["pooled_output"]
pooled_output = output_layer#added 25March
hidden_size = output_layer.shape[-1].value
# Create our own layer to tune for politeness data.
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"):
# Dropout helps prevent overfitting
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)
log_probs = tf.nn.log_softmax(logits, axis=-1)
probs = tf.nn.softmax(logits, axis=-1)#added 25March
# Convert labels into one-hot encoding
one_hot_labels = tf.one_hot(labels, depth=num_labels, dtype=tf.float32)
predicted_labels = tf.squeeze(tf.argmax(log_probs, axis=-1, output_type=tf.int32))
# If we're predicting, we want predicted labels and the probabiltiies.
if is_predicting:
return (predicted_labels, log_probs, probs, pooled_output)
# If we're train/eval, compute loss between predicted and actual label
per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
loss = tf.reduce_mean(per_example_loss)
#return (loss, predicted_labels, log_probs)
return (loss, predicted_labels, log_probs, probs, pooled_output)#added 25March
# In[ ]:
# In[21]:
# Next we'll wrap our model function in a `model_fn_builder` function that adapts our model to work for training, evaluation, and prediction.
# In[14]:
# model_fn_builder actually creates our model function
# using the passed parameters for num_labels, learning_rate, etc.
def model_fn_builder(num_labels, learning_rate, num_train_steps,
num_warmup_steps):
"""Returns `model_fn` closure for TPUEstimator."""
def model_fn(features, labels, mode, params): # pylint: disable=unused-argument
"""The `model_fn` for TPUEstimator."""
input_ids = features["input_ids"]
input_mask = features["input_mask"]
segment_ids = features["segment_ids"]
label_ids = features["label_ids"]
is_predicting = (mode == tf.estimator.ModeKeys.PREDICT)
# TRAIN and EVAL
if not is_predicting:
"""
(loss, predicted_labels, log_probs) = create_model(
is_predicting, input_ids, input_mask, segment_ids, label_ids, num_labels)
"""
# this should be changed in both places
(loss, predicted_labels, log_probs, probs, pooled_output) = create_model(
is_predicting, input_ids, input_mask, segment_ids, label_ids, num_labels)
train_op = optimization.create_optimizer(
loss, learning_rate, num_train_steps, num_warmup_steps, use_tpu=False)
# Calculate evaluation metrics.
def metric_fn(label_ids, predicted_labels):
accuracy = tf.metrics.accuracy(label_ids, predicted_labels)
f1_score = tf.contrib.metrics.f1_score(
label_ids,
predicted_labels)
auc = tf.metrics.auc(
label_ids,
predicted_labels)
recall = tf.metrics.recall(
label_ids,
predicted_labels)
precision = tf.metrics.precision(
label_ids,
predicted_labels)
true_pos = tf.metrics.true_positives(
label_ids,
predicted_labels)
true_neg = tf.metrics.true_negatives(
label_ids,
predicted_labels)
false_pos = tf.metrics.false_positives(
label_ids,
predicted_labels)
false_neg = tf.metrics.false_negatives(
label_ids,
predicted_labels)
return
"eval_accuracy": accuracy,
"f1_score": f1_score,
"auc": auc,
"precision": precision,
"recall": recall,
"true_positives": true_pos,
"true_negatives": true_neg,
"false_positives": false_pos,
"false_negatives": false_neg
eval_metrics = metric_fn(label_ids, predicted_labels)
if mode == tf.estimator.ModeKeys.TRAIN:
return tf.estimator.EstimatorSpec(mode=mode,
loss=loss,
train_op=train_op)
else:
return tf.estimator.EstimatorSpec(mode=mode,
loss=loss,
eval_metric_ops=eval_metrics)
else:
#(predicted_labels, log_probs) = create_model(is_predicting, input_ids, input_mask, segment_ids, label_ids, num_labels)
(predicted_labels, log_probs, probs, pooled_output)=create_model(is_predicting, input_ids, input_mask, segment_ids, label_ids, num_labels)
# return dictionary of all the values you wanted
predictions = 'log_probabilities': log_probs,'probabilities': probs,'labels': predicted_labels,'pooled_output': pooled_output
"""
predictions =
'probabilities': log_probs,
'labels': predicted_labels
"""
return tf.estimator.EstimatorSpec(mode, predictions=predictions)
# Return the actual model function in the closure
return model_fn
# In[22]:
# In[15]:
# Compute train and warmup steps from batch size
# These hyperparameters are copied from this colab notebook (https://colab.sandbox.google.com/github/tensorflow/tpu/blob/master/tools/colab/bert_finetuning_with_cloud_tpus.ipynb)
BATCH_SIZE = 32
LEARNING_RATE = 2e-5
NUM_TRAIN_EPOCHS = 2.0
# Warmup is a period of time where hte learning rate
# is small and gradually increases--usually helps training.
WARMUP_PROPORTION = 0.1
# Model configs
SAVE_CHECKPOINTS_STEPS = 500
SAVE_SUMMARY_STEPS = 100
# In[23]:
# In[16]:
# Compute # train and warmup steps from batch size
num_train_steps = int((len(train_features) / BATCH_SIZE) * NUM_TRAIN_EPOCHS)
num_warmup_steps = int(num_train_steps * WARMUP_PROPORTION)
#epochs = steps * batch_size * worker_gpu / training_subwords
#effecive batch size is batch_size * worker_gpu
# In[17]:
# Specify outpit directory and number of checkpoint steps to save
run_config = tf.estimator.RunConfig(
model_dir=OUTPUT_DIR,
save_summary_steps=SAVE_SUMMARY_STEPS,
save_checkpoints_steps=SAVE_CHECKPOINTS_STEPS)
# In[18]:
model_fn = model_fn_builder(
num_labels=len(label_list),
learning_rate=LEARNING_RATE,
num_train_steps=num_train_steps,
num_warmup_steps=num_warmup_steps)
estimator = tf.estimator.Estimator(
model_fn=model_fn,
config=run_config,
params="batch_size": BATCH_SIZE)
# Next we create an input builder function that takes our training feature set (`train_features`) and produces a generator. This is a pretty standard design pattern for working with Tensorflow [Estimators](https://www.tensorflow.org/guide/estimators).
# In[24]:
# In[19]:
# Create an input function for training. drop_remainder = True for using TPUs.
train_input_fn = run_classifier.input_fn_builder(
features=train_features,
seq_length=MAX_SEQ_LENGTH,
is_training=True,
drop_remainder=False)
# ### Model Training
# In[46]:
print(f'Beginning Training!')
current_time = datetime.now()
estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)
print("Training took time ", datetime.now() - current_time)
"""
# ### Model Testing
# In[47]:
test_input_fn = run_classifier.input_fn_builder(
features=test_features,
seq_length=MAX_SEQ_LENGTH,
is_training=False,
drop_remainder=False)
# In[48]:
estimator.evaluate(input_fn=test_input_fn, steps=None)
"""
# In[25]:
# ### Prediction
# In[24]:
def getPrediction(in_sentences):
labels = ["Negative", "Positive"]
input_examples = [run_classifier.InputExample(guid="", text_a = x, text_b = None, label = 0) for x in in_sentences] # here, "" is just a dummy label
input_features = run_classifier.convert_examples_to_features(input_examples, label_list, MAX_SEQ_LENGTH, tokenizer)
predict_input_fn = run_classifier.input_fn_builder(features=input_features, seq_length=MAX_SEQ_LENGTH, is_training=False, drop_remainder=False)
predictions = estimator.predict(predict_input_fn)
#return predictions
return [(sentence, prediction['log_probabilities'],prediction['probabilities'], labels[prediction['labels']],prediction['pooled_output']) for sentence, prediction in zip(in_sentences, predictions)]
# In[25]:
pred_sentences = [
"They sold me something I didn't want",
]
视频中得到CLS嵌入的代码如下
# Put the model in evaluation mode--the dropout layers behave differently
# during evaluation.
model.eval()
with torch.no_grad():
# Forward pass, return hidden states and predictions.
# This will return the logits rather than the loss because we have
# not provided labels.
logits, encoded_layers = model(
input_ids = input_ids,
token_type_ids = None,
attention_mask = attn_mask)
# Retrieve our sentence embedding--take the `[CLS]` embedding from the final
# layer.
layer_i = 12 # The last BERT layer before the classifier.
batch_i = 0 # Only one input in the batch.
token_i = 0 # The first token, corresponding to [CLS]
# Grab the embedding.
vec = encoded_layers[layer_i][batch_i][token_i]
【问题讨论】：
你可以添加一些代码，问题是自包含的吗？当您在寻找问题的答案时，您当然不希望观看 5 分钟的视频来确定 SO 问题是否是您要寻找的。span> 您是否已经对模型进行了微调？如果是，怎么做？ 请检查更新 【参考方案1】：Google 的 BERT 模型由 12 层 Transformer Encoders 组成，每层有 12 个注意力头，每层嵌入大小（或隐藏大小）为 768。因此它在 TF hub 中的标签为：bert_uncased_L-12_H-768_A-12。 Uncased 表示 BERT 不区分大小写，即每个单词在处理之前都是小写的。
最后一层的输出是 512 (MAX_SEQ_LENGTH) x 768 (hidden_size)。第一个向量（索引零）对应于[CLS]。这就是你从bert_outputs["pooled_output"] 得到的。因此，您确实获得了与您想要的输出“相似”的输出（如果您的batch_size=1，如果它设置为其他值，您只需删除除第一个之外的所有句子的信息）。
layer_i = 12 # The last BERT layer before the classifier.
batch_i = 0 # Only one input in the batch.
token_i = 0 # The first token, corresponding to [CLS]
您的问题“为什么结果很糟糕”可能有很多答案。但在我看来，它处于微调过程中。在 BERT 之上，您添加了一个简单的 NN，称为“head”，它被训练用于执行下游任务。在您的情况下，您优化整个网络（BERT 和 top head）来解决情绪分析任务。之后，您尝试使用用作头部输入的特征来获得不同任务的答案 - 语义相似性。虽然有可能获得对语义相似度有用的特征，但这些（特征）针对区分情感进行了优化，对其他任务可能不是很有用。而且我在您的代码中没有看到任何表明对新任务进行了某种调整的内容。
所以你需要 (IMO) 做的是
-
找到一个标记为语义相似性任务的数据集，
将 BERT 顶部的头部更改为适合回归（语义相似性）而不是分类（情感分析），
并使用新数据微调您的新网络。
更新
根据您的代码，只是为了演示如何使用视频中的嵌入：
import scipy
for i in range(len(predictions)):
print(i, pred_sentences[i])
print()
for i in range(len(predictions)):
for j in range(i+1, len(predictions)):
print (f'i:j >> scipy.spatial.distance.cosine(predictions[i][-1],predictions[j][-1])')
将提供以下输出：
0 That movie was absolutely fantastic.
1 This film is creative and surprising.
2 Ford is an American multinational automaker that has its main headquarters in Dearborn, Michigan, a suburb of Detroit.
3 The Volkswagen Group with its headquarters in Wolfsburg, Germany is one of the world's leading manufacturers of automobiles and commercial vehicles.
0:1 >> 0.021687865257263184
0:2 >> 0.3452081084251404
0:3 >> 0.2836960554122925
1:2 >> 0.3700438141822815
1:3 >> 0.3061264753341675
2:3 >> 0.01616525650024414
如您所见，与预期的一样，句子 0 和 1 比句子 2 和 3 更接近。而 2 和 3 相似，距离 0 和 1 更远。
【讨论】：
但我链接的 youtube 视频也对未标记为相似性任务的数据执行分类 在视频中，他为 15000 个句子创建了 BERT 嵌入，并使用 k-NN 在嵌入空间中搜索最近的邻居。你不需要微调 BERT 来做到这一点，你也可以使用原始权重。 见this问题 我阅读了您提供的链接。它说：“对于语义相似性，我估计你最好微调（或训练）神经网络，因为你提到的大多数经典相似性度量都更突出地关注标记相似性（因此，句法相似性） ，尽管不一定如此）。”。所以也建议微调。我猜微调可以让模型学习特定领域的语言 如果您能提供示例代码或尝试我的代码并提出更正建议，我将不胜感激以上是关于用于语义相似性的 BERT 嵌入的主要内容，如果未能解决你的问题，请参考以下文章