 在 TensorFlow.org 上檢視
|
 在 Google Colab 中執行
|
 在 GitHub 上檢視
|
 下載筆記本
|
 查看 TF Hub 模型
|
這個 Colab 示範如何使用通用句子編碼器精簡版執行句子相似度任務。此模組與 通用句子編碼器 非常相似，唯一的區別在於您需要在輸入句子上執行 SentencePiece 處理。
通用句子編碼器讓取得句子層級嵌入變得非常容易，就像過去查詢個別單字的嵌入一樣。句子嵌入接著可以輕鬆用於計算句子層級的語意相似度，並在監督式訓練資料較少的情況下，提升下游分類任務的效能。
開始使用
設定
# Install seaborn for pretty visualizationspip3 install --quiet seaborn# Install SentencePiece package# SentencePiece package is needed for Universal Sentence Encoder Lite. We'll# use it for all the text processing and sentence feature ID lookup.pip3 install --quiet sentencepiece
from absl import logging
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import tensorflow_hub as hub
import sentencepiece as spm
import matplotlib.pyplot as plt
import numpy as np
import os
import pandas as pd
import re
import seaborn as sns
2023-12-08 13:03:51.535911: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2023-12-08 13:03:51.535969: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2023-12-08 13:03:51.537485: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.9/site-packages/tensorflow/python/compat/v2_compat.py:108: disable_resource_variables (from tensorflow.python.ops.variable_scope) is deprecated and will be removed in a future version. Instructions for updating: non-resource variables are not supported in the long term
從 TF-Hub 載入模組
module = hub.Module("https://tfhub.dev/google/universal-sentence-encoder-lite/2")
2023-12-08 13:03:56.973158: E external/local_xla/xla/stream_executor/cuda/cuda_driver.cc:274] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
input_placeholder = tf.sparse_placeholder(tf.int64, shape=[None, None])
encodings = module(
inputs=dict(
values=input_placeholder.values,
indices=input_placeholder.indices,
dense_shape=input_placeholder.dense_shape))
INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore
從 TF-Hub 模組載入 SentencePiece 模型
SentencePiece 模型方便地儲存在模組的資產中。必須載入模型才能初始化處理器。
with tf.Session() as sess:
spm_path = sess.run(module(signature="spm_path"))
sp = spm.SentencePieceProcessor()
with tf.io.gfile.GFile(spm_path, mode="rb") as f:
sp.LoadFromSerializedProto(f.read())
print("SentencePiece model loaded at {}.".format(spm_path))
INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore SentencePiece model loaded at b'/tmpfs/tmp/tfhub_modules/539544f0a997d91c327c23285ea00c37588d92cc/assets/universal_encoder_8k_spm.model'.
def process_to_IDs_in_sparse_format(sp, sentences):
# An utility method that processes sentences with the sentence piece processor
# 'sp' and returns the results in tf.SparseTensor-similar format:
# (values, indices, dense_shape)
ids = [sp.EncodeAsIds(x) for x in sentences]
max_len = max(len(x) for x in ids)
dense_shape=(len(ids), max_len)
values=[item for sublist in ids for item in sublist]
indices=[[row,col] for row in range(len(ids)) for col in range(len(ids[row]))]
return (values, indices, dense_shape)
使用幾個範例測試模組
# Compute a representation for each message, showing various lengths supported.
word = "Elephant"
sentence = "I am a sentence for which I would like to get its embedding."
paragraph = (
"Universal Sentence Encoder embeddings also support short paragraphs. "
"There is no hard limit on how long the paragraph is. Roughly, the longer "
"the more 'diluted' the embedding will be.")
messages = [word, sentence, paragraph]
values, indices, dense_shape = process_to_IDs_in_sparse_format(sp, messages)
# Reduce logging output.
logging.set_verbosity(logging.ERROR)
with tf.Session() as session:
session.run([tf.global_variables_initializer(), tf.tables_initializer()])
message_embeddings = session.run(
encodings,
feed_dict={input_placeholder.values: values,
input_placeholder.indices: indices,
input_placeholder.dense_shape: dense_shape})
for i, message_embedding in enumerate(np.array(message_embeddings).tolist()):
print("Message: {}".format(messages[i]))
print("Embedding size: {}".format(len(message_embedding)))
message_embedding_snippet = ", ".join(
(str(x) for x in message_embedding[:3]))
print("Embedding: [{}, ...]\n".format(message_embedding_snippet))
Message: Elephant Embedding size: 512 Embedding: [0.053387485444545746, 0.05319438502192497, -0.05235603451728821, ...] Message: I am a sentence for which I would like to get its embedding. Embedding size: 512 Embedding: [0.03533291816711426, -0.047149673104286194, 0.012305588461458683, ...] Message: Universal Sentence Encoder embeddings also support short paragraphs. There is no hard limit on how long the paragraph is. Roughly, the longer the more 'diluted' the embedding will be. Embedding size: 512 Embedding: [-0.004081661347299814, -0.08954867720603943, 0.03737194463610649, ...]
語意文本相似度 (STS) 任務範例
通用句子編碼器產生的嵌入已大致正規化。兩個句子的語意相似度可以輕鬆地計算為編碼的內積。
def plot_similarity(labels, features, rotation):
corr = np.inner(features, features)
sns.set(font_scale=1.2)
g = sns.heatmap(
corr,
xticklabels=labels,
yticklabels=labels,
vmin=0,
vmax=1,
cmap="YlOrRd")
g.set_xticklabels(labels, rotation=rotation)
g.set_title("Semantic Textual Similarity")
def run_and_plot(session, input_placeholder, messages):
values, indices, dense_shape = process_to_IDs_in_sparse_format(sp,messages)
message_embeddings = session.run(
encodings,
feed_dict={input_placeholder.values: values,
input_placeholder.indices: indices,
input_placeholder.dense_shape: dense_shape})
plot_similarity(messages, message_embeddings, 90)
相似度視覺化
這裡我們在熱圖中顯示相似度。最終圖表是 9x9 矩陣，其中每個項目 [i, j] 都根據句子 i 和 j 的編碼內積著色。
messages = [
# Smartphones
"I like my phone",
"My phone is not good.",
"Your cellphone looks great.",
# Weather
"Will it snow tomorrow?",
"Recently a lot of hurricanes have hit the US",
"Global warming is real",
# Food and health
"An apple a day, keeps the doctors away",
"Eating strawberries is healthy",
"Is paleo better than keto?",
# Asking about age
"How old are you?",
"what is your age?",
]
with tf.Session() as session:
session.run(tf.global_variables_initializer())
session.run(tf.tables_initializer())
run_and_plot(session, input_placeholder, messages)
評估：STS (語意文本相似度) 基準
STS 基準 針對使用句子嵌入計算出的相似度分數與人類判斷的一致程度，提供內在評估。基準要求系統傳回各種句子對的相似度分數。然後使用 皮爾森相關係數 來評估機器相似度分數相對於人類判斷的品質。
下載資料
import pandas
import scipy
import math
def load_sts_dataset(filename):
# Loads a subset of the STS dataset into a DataFrame. In particular both
# sentences and their human rated similarity score.
sent_pairs = []
with tf.gfile.GFile(filename, "r") as f:
for line in f:
ts = line.strip().split("\t")
# (sent_1, sent_2, similarity_score)
sent_pairs.append((ts[5], ts[6], float(ts[4])))
return pandas.DataFrame(sent_pairs, columns=["sent_1", "sent_2", "sim"])
def download_and_load_sts_data():
sts_dataset = tf.keras.utils.get_file(
fname="Stsbenchmark.tar.gz",
origin="http://ixa2.si.ehu.es/stswiki/images/4/48/Stsbenchmark.tar.gz",
extract=True)
sts_dev = load_sts_dataset(
os.path.join(os.path.dirname(sts_dataset), "stsbenchmark", "sts-dev.csv"))
sts_test = load_sts_dataset(
os.path.join(
os.path.dirname(sts_dataset), "stsbenchmark", "sts-test.csv"))
return sts_dev, sts_test
sts_dev, sts_test = download_and_load_sts_data()
Downloading data from http://ixa2.si.ehu.es/stswiki/images/4/48/Stsbenchmark.tar.gz 409630/409630 [==============================] - 1s 2us/step
建構評估圖
sts_input1 = tf.sparse_placeholder(tf.int64, shape=(None, None))
sts_input2 = tf.sparse_placeholder(tf.int64, shape=(None, None))
# For evaluation we use exactly normalized rather than
# approximately normalized.
sts_encode1 = tf.nn.l2_normalize(
module(
inputs=dict(values=sts_input1.values,
indices=sts_input1.indices,
dense_shape=sts_input1.dense_shape)),
axis=1)
sts_encode2 = tf.nn.l2_normalize(
module(
inputs=dict(values=sts_input2.values,
indices=sts_input2.indices,
dense_shape=sts_input2.dense_shape)),
axis=1)
sim_scores = -tf.acos(tf.reduce_sum(tf.multiply(sts_encode1, sts_encode2), axis=1))
INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore
評估句子嵌入
選擇基準的資料集
def run_sts_benchmark(session):
"""Returns the similarity scores"""
scores = session.run(
sim_scores,
feed_dict={
sts_input1.values: values1,
sts_input1.indices: indices1,
sts_input1.dense_shape: dense_shape1,
sts_input2.values: values2,
sts_input2.indices: indices2,
sts_input2.dense_shape: dense_shape2,
})
return scores
with tf.Session() as session:
session.run(tf.global_variables_initializer())
session.run(tf.tables_initializer())
scores = run_sts_benchmark(session)
pearson_correlation = scipy.stats.pearsonr(scores, similarity_scores)
print('Pearson correlation coefficient = {0}\np-value = {1}'.format(
pearson_correlation[0], pearson_correlation[1]))
Pearson correlation coefficient = 0.7856484921513689 p-value = 1.0657791693e-314