从 Keras 的 imdb 数据集中恢复原始文本

Question

从 Keras 的 imdb 数据集中恢复原始文本

我想从 Keras 的 imdb 数据集中恢复 imdb 的原始文本。

首先，当我加载 Keras 的 imdb 数据集时，它返回了单词索引序列。

>>> (X_train, y_train), (X_test, y_test) = imdb.load_data()
>>> X_train[0]
[1, 14, 22, 16, 43, 530, 973, 1622, 1385, 65, 458, 4468, 66, 3941, 4, 173, 36, 256, 5, 25, 100, 43, 838, 112, 50, 670, 22665, 9, 35, 480, 284, 5, 150, 4, 172, 112, 167, 21631, 336, 385, 39, 4, 172, 4536, 1111, 17, 546, 38, 13, 447, 4, 192, 50, 16, 6, 147, 2025, 19, 14, 22, 4, 1920, 4613, 469, 4, 22, 71, 87, 12, 16, 43, 530, 38, 76, 15, 13, 1247, 4, 22, 17, 515, 17, 12, 16, 626, 18, 19193, 5, 62, 386, 12, 8, 316, 8, 106, 5, 4, 2223, 5244, 16, 480, 66, 3785, 33, 4, 130, 12, 16, 38, 619, 5, 25, 124, 51, 36, 135, 48, 25, 1415, 33, 6, 22, 12, 215, 28, 77, 52, 5, 14, 407, 16, 82, 10311, 8, 4, 107, 117, 5952, 15, 256, 4, 31050, 7, 3766, 5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 12118, 1029, 13, 104, 88, 4, 381, 15, 297, 98, 32, 2071, 56, 26, 141, 6, 194, 7486, 18, 4, 226, 22, 21, 134, 476, 26, 480, 5, 144, 30, 5535, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65, 16, 38, 1334, 88, 12, 16, 283, 5, 16, 4472, 113, 103, 32, 15, 16, 5345, 19, 178, 32]

我找到了 imdb.get_word_index 方法()，它返回单词索引字典，如 {‘create’: 984, ‘make’: 94,…}。为了进行转换，我创建了索引词词典。

>>> word_index = imdb.get_word_index()
>>> index_word = {v:k for k,v in word_index.items()}

然后，我尝试恢复原始文本，如下所示。

>>> ' '.join(index_word.get(w) for w in X_train[5])
"the effort still been that usually makes for of finished sucking ended cbc's an because before if just though something know novel female i i slowly lot of above freshened with connect in of script their that out end his deceptively i i"

我英语不好，但我知道这句话很奇怪。

为什么会这样？如何恢复原文？

Answer 1

你的例子是胡言乱语，它比仅仅缺少一些停用词要糟糕得多。

如果您重新阅读 [keras.datasets.imdb.load_data](https://keras.io/datasets/#imdb-movie-reviews-sentiment-classification 的 start_char、oov_char 和 index_from 参数的文档 ) 方法他们解释发生了什么：

start_char: 整数。序列的开始将用这个字符标记。设置为 1，因为 0 通常是填充字符。

oov_char: 整数。由于 num_words 或 skip_top 限制而被删除的单词将替换为此字符。

index_from: 整数。使用此索引或更高索引来索引实际单词。

您反转的字典假定单词索引从 1 开始。

但是返回我的 keras 的索引有 <START> 和 <UNKNOWN> 作为索引 1 和 2。 （并且假设您将使用0 代替<PADDING>）。

这对我有用：

import keras
NUM_WORDS=1000 # only use top 1000 words
INDEX_FROM=3   # word index offset

train,test = keras.datasets.imdb.load_data(num_words=NUM_WORDS, index_from=INDEX_FROM)
train_x,train_y = train
test_x,test_y = test

word_to_id = keras.datasets.imdb.get_word_index()
word_to_id = {k:(v+INDEX_FROM) for k,v in word_to_id.items()}
word_to_id["<PAD>"] = 0
word_to_id["<START>"] = 1
word_to_id["<UNK>"] = 2
word_to_id["<UNUSED>"] = 3

id_to_word = {value:key for key,value in word_to_id.items()}
print(' '.join(id_to_word[id] for id in train_x[0] ))

标点符号不见了，但仅此而已：

"<START> this film was just brilliant casting <UNK> <UNK> story
 direction <UNK> really <UNK> the part they played and you could just
 imagine being there robert <UNK> is an amazing actor ..."

Answer 2

您可以使用 keras.utils.data_utils 中的 get_file 获取不移除停用词的原始数据集：

path = get_file('imdb_full.pkl',
               origin='https://s3.amazonaws.com/text-datasets/imdb_full.pkl',
                md5_hash='d091312047c43cf9e4e38fef92437263')
f = open(path, 'rb')
(training_data, training_labels), (test_data, test_labels) = pickle.load(f)

学分 - Jeremy Howards fast.ai course lesson 5

Answer 3

这是因为基本的NLP 数据准备。大量所谓的停用词已从文本中删除，以使学习变得可行。通常——在预处理过程中，大部分的标点符号和不太常见的词也会从文本中删除。我认为恢复原始文本的唯一方法是使用例如在 IMDB 中找到最匹配的文本。 Google 的浏览器 API。

Answer 4

此编码将与标签一起使用：

from keras.datasets import imdb
(x_train,y_train),(x_test,y_test) = imdb.load_data()
word_index = imdb.get_word_index() # get {word : index}
index_word = {v : k for k,v in word_index.items()} # get {index : word}

index = 1
print(" ".join([index_word[idx] for idx in x_train[index]]))
print("positve" if y_train[index]==1 else "negetive")

如果有帮助，请点赞。 :)

Answer 5

索引偏移 3，因为 0、1 和 2 是“填充”、“序列开始”和“未知”的保留索引。以下应该可以工作。

imdb = tf.keras.datasets.imdb
(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)

word_index = imdb.get_word_index()
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])

review = [reverse_word_index.get(i-3, "?") for i in train_data[0]]

Answer 6

这对我有用：

word_index = imdb.get_word_index()                                    
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])            
decoded_review = ' '.join([reverse_word_index.get(i - 3, "") for i in train_data[0]])

Answer 7

要获得所有评论的等效数组：

def decode_imdb_reviews(text_data):
    result = [0 for x in range(len(text_data))]
    word_index = imdb.get_word_index()
    reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
    for review in range(0,len(text_data)):
        for index in enumerate(text_data[review]):
            decoded_review = ' '.join([reverse_word_index.get(index - 3, '#') for index in text_data[review]])
        result[review] = decoded_review
    return result

text_data = []
text_data = decode_imdb_reviews(train_data)

Answer 8

试试下面的代码。此代码有效。

# load dataset 
from tensorflow.keras.datasets import imdb 
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=500)


# vec 2 num 
imdb_vec2num = imdb.get_word_index(path="imdb_word_index.json")
# num 2 vec 
imdb_num2vec = {value+3:key for key, value in imdb_vec2num.items()}
imdb_num2vec[0] = "<PAD>"
imdb_num2vec[1] = "<START>"
imdb_num2vec[2] = "<UNK>"
imdb_num2vec[3] = "<UNUSED>"

# index-word table
imdb_num2vec = {value:key for key, value in imdb_index.items()}

# change encoded sentences to sentences
def restore_sentences(num2word, encoded_sentences): 
    sentences = []
    for encoded_sentence in encoded_sentences:
        sentences.append([num2word[ele] for ele in encoded_sentence])
    return sentences

# example 
sentences = restore_sentences(imdb_num2vec, x_train)

Answer 9

from keras.datasets import imdb
NUM_WORDS=1000 # only use top 1000 words

(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=NUM_WORDS)

获取索引详细信息：

word_to_id = keras.datasets.imdb.get_word_index()

构建键值对：

id_to_word = {value:key for key,value in word_to_id.items()}
print(' '.join(id_to_word[id] for id in x_train[0] ))