Press "Enter" to skip to content

TensorFlow2.0 代码实战专栏(四):Word2Vec (Word Embedding)

 

作者 |  Aymeric Damien

 

编辑 | 奇予纪

 

出品 | 磐创AI团队

 

W o rd2Vec (Word Embedding)

 

使用TensorFlow 2.0实现Word2Vec算法计 算单词的向量表示,这 个例子是使用一小部分维基百科文章来训练的。

 

更多信息请查看论文:

 

Mikolov, Tomas et al. “Efficient Estimation of Word Representations in Vector Space.”, 2013 [1]

 

from __future__ import division, print_function, absolute_import
import collections
import os
import random
import urllib
import zipfile
import numpy as np
import tensorflow as tf

 

learning_rate = 0.1
batch_size = 128
num_steps = 3000000
display_step = 10000
eval_step = 200000
# 训练参数
learning_rate = 0.1
batch_size = 128
num_steps = 3000000
display_step = 10000
eval_step = 200000
# 评估参数
eval_words = ['five', 'of', 'going', 'hardware', 'american', 'britain']
# Word2Vec 参数
embedding_size = 200 # 嵌入向量的维度 vector.
max_vocabulary_size = 50000 # 词汇表中不同单词的总数words in the vocabulary.
min_occurrence = 10  # 删除出现小于n次的所有单词
skip_window = 3 # 左右各要考虑多少个单词
num_skips = 2 # 重复使用输入生成标签的次数
num_sampled = 64 # 负采样数量

 

# 下载一小部分维基百科文章集
url = 'http://mattmahoney.net/dc/text8.zip'
data_path = 'text8.zip'
if not os.path.exists(data_path):
    print("Downloading the dataset... (It may take some time)")
    filename, _ = urllib.urlretrieve(url, data_path)
    print("Done!")
# 解压数据集文件,文本已处理完毕
with zipfile.ZipFile(data_path) as f:
    text_words = f.read(f.namelist()[0]).lower().split()

 

# 构建词典并用 UNK 标记替换频数较低的词
count = [('UNK', -1)]
# 检索最常见的单词
count.extend(collections.Counter(text_words).most_common(max_vocabulary_size - 1))
# 删除少于'min_occurrence'次数的样本
for i in range(len(count) - 1, -1, -1):
    if count[i][1] < min_occurrence:
        count.pop(i)
    else:
        #该集合是有序的,因此在当出现小于'min_occurrence'时停止
        break
# 计算单词表单词个数
vocabulary_size = len(count)
# 为每一个词分配id
word2id = dict()
for i, (word, _)in enumerate(count):
    word2id[word] = i
data = list()
unk_count = 0
for word in text_words:
     # 检索单词id,或者如果不在字典中则为其指定索引0('UNK')
    index = word2id.get(word, 0)
    if index == 0:
        unk_count += 1
    data.append(index)
count[0] = ('UNK', unk_count)
id2word = dict(zip(word2id.values(), word2id.keys()))
print("Words count:", len(text_words))
print("Unique words:", len(set(text_words)))
print("Vocabulary size:", vocabulary_size)
print("Most common words:", count[:10])

 

output:

 

Words count: 17005207
Unique words: 253854
Vocabulary size: 47135
Most common words: [('UNK', 444176), ('the', 1061396), ('of', 593677), ('and', 416629), ('one', 411764), ('in', 372201), ('a', 325873), ('to', 316376), ('zero', 264975), ('nine', 250430)]

 

data_index = 0
# 为skip-gram模型生成训练批次
def next_batch(batch_size, num_skips, skip_window):
    global data_index
    assert batch_size % num_skips == 0
    assert num_skips <= 2 * skip_window
    batch = np.ndarray(shape=(batch_size), dtype=np.int32)
    labels = np.ndarray(shape=(batch_size, 1), dtype=np.int32)
    # 得到窗口长度( 当前单词左边和右边 + 当前单词)
    span = 2 * skip_window + 1
    buffer = collections.deque(maxlen=span)
    if data_index + span > len(data):
        data_index = 0
    buffer.extend(data[data_index:data_index + span])
    data_index += span
    for i in range(batch_size // num_skips):
        context_words = [w for w in range(span) if w != skip_window]
        words_to_use = random.sample(context_words, num_skips)
        for j, context_word in enumerate(words_to_use):
            batch[i * num_skips + j] = buffer[skip_window]
            labels[i * num_skips + j, 0] = buffer[context_word]
        if data_index == len(data):
            buffer.extend(data[0:span])
            data_index = span
        else:
            buffer.append(data[data_index])
            data_index += 1
    #回溯一点,以避免在批处理结束时跳过单词
    data_index = (data_index + len(data) - span) % len(data)
    return batch, labels

 

# 确保在CPU上分配以下操作和变量
# (某些操作在GPU上不兼容)
with tf.device('/cpu:0'):
    # 创建嵌入变量(每一行代表一个词嵌入向量) embedding vector).
    embedding = tf.Variable(tf.random.normal([vocabulary_size, embedding_size]))
    # 构造NCE损失的变量
    nce_weights = tf.Variable(tf.random.normal([vocabulary_size, embedding_size]))
    nce_biases = tf.Variable(tf.zeros([vocabulary_size]))
def get_embedding(x):
    with tf.device('/cpu:0'):
       # 对于X中的每一个样本查找对应的嵌入向量
        x_embed = tf.nn.embedding_lookup(embedding, x)
        return x_embed
def nce_loss(x_embed, y):
    with tf.device('/cpu:0'):
        # 计算批处理的平均NCE损失
        y = tf.cast(y, tf.int64)
        loss = tf.reduce_mean(
            tf.nn.nce_loss(weights=nce_weights,
                           biases=nce_biases,
                           labels=y,
                           inputs=x_embed,
                           num_sampled=num_sampled,
                           num_classes=vocabulary_size))
        return loss
# 评估
def evaluate(x_embed):
    with tf.device('/cpu:0'):
         # 计算输入数据嵌入与每个嵌入向量之间的余弦相似度
        x_embed = tf.cast(x_embed, tf.float32)
        x_embed_norm = x_embed / tf.sqrt(tf.reduce_sum(tf.square(x_embed)))
        embedding_norm = embedding / tf.sqrt(tf.reduce_sum(tf.square(embedding), 1, keepdims=True), tf.float32)
        cosine_sim_op = tf.matmul(x_embed_norm, embedding_norm, transpose_b=True)
        return cosine_sim_op
# 定义优化器
optimizer = tf.optimizers.SGD(learning_rate)

 

# 优化过程
def run_optimization(x, y):
    with tf.device('/cpu:0'):
       # 将计算封装在GradientTape中以实现自动微分
        with tf.GradientTape() as g:
            emb = get_embedding(x)
            loss = nce_loss(emb, y)
        # 计算梯度
        gradients = g.gradient(loss, [embedding, nce_weights, nce_biases])
         # 按gradients更新 W 和 b
        optimizer.apply_gradients(zip(gradients, [embedding, nce_weights, nce_biases]))

 

# 用于测试的单词
x_test = np.array([word2id[w] for w in eval_words])
# 针对给定步骤数进行训练
for step in xrange(1, num_steps + 1):
    batch_x, batch_y = next_batch(batch_size, num_skips, skip_window)
    run_optimization(batch_x, batch_y)
    if step % display_step == 0 or step == 1:
        loss = nce_loss(get_embedding(batch_x), batch_y)
        print("step: %i, loss: %f" % (step, loss))
    # 评估
    if step % eval_step == 0 or step == 1:
        print("Evaluation...")
        sim = evaluate(get_embedding(x_test)).numpy()
        for i in xrange(len(eval_words)):
            top_k = 8  # 最相似的单词数量
            nearest = (-sim[i, :]).argsort()[1:top_k + 1]
            log_str = '"%s" nearest neighbors:' % eval_words[i]
            for k in xrange(top_k):
                log_str = '%s %s,' % (log_str, id2word[nearest[k]])
            print(log_str)

 

step: 1, loss: 504.444214
Evaluation...
"five" nearest neighbors: censure, stricken, anglicanism, stick, streetcars, shrines, horrified, sparkle,
"of" nearest neighbors: jolly, weary, clinicians, kerouac, economist, owls, safe, playoff,
"going" nearest neighbors: filament, platforms, moderately, micheal, despotic, krag, disclosed, your,
"hardware" nearest neighbors: occupants, paraffin, vera, reorganized, rename, declares, prima, condoned,
"american" nearest neighbors: portfolio, rhein, aalto, angle, lifeson, tucker, sexton, dench,
"britain" nearest neighbors: indivisible, disbelief, scripture, pepsi, scriptores, sighting, napalm, strike,
step: 10000, loss: 117.166962
step: 20000, loss: 65.478333
step: 30000, loss: 46.580460
step: 40000, loss: 25.563128
step: 50000, loss: 50.924446
step: 60000, loss: 51.696526
step: 70000, loss: 17.272142
step: 80000, loss: 32.579414
step: 90000, loss: 68.372032
step: 100000, loss: 36.026573
step: 110000, loss: 22.502020
step: 120000, loss: 15.788742
step: 130000, loss: 31.832420
step: 140000, loss: 25.096617
step: 150000, loss: 12.013027
step: 160000, loss: 20.574780
step: 170000, loss: 12.201975
step: 180000, loss: 20.983793
step: 190000, loss: 11.366720
step: 200000, loss: 19.431549
Evaluation...
"five" nearest neighbors: three, four, eight, six, two, seven, nine, zero,
"of" nearest neighbors: the, a, and, first, with, on, but, from,
"going" nearest neighbors: have, more, used, out, be, with, on, however,
"hardware" nearest neighbors: be, known, system, apollo, and, a, such, used,
"american" nearest neighbors: UNK, and, from, s, at, in, after, about,
"britain" nearest neighbors: of, and, many, the, as, used, but, such,
step: 210000, loss: 16.361233
step: 220000, loss: 17.529526
step: 230000, loss: 16.805817
step: 240000, loss: 6.365625
step: 250000, loss: 8.083097
step: 260000, loss: 11.262514
step: 270000, loss: 9.842708
step: 280000, loss: 6.363440
step: 290000, loss: 8.732617
step: 300000, loss: 10.484728
step: 310000, loss: 12.099487
step: 320000, loss: 11.496288
step: 330000, loss: 9.283813
step: 340000, loss: 10.777218
step: 350000, loss: 16.310440
step: 360000, loss: 7.495782
step: 370000, loss: 9.287696
step: 380000, loss: 6.982735
step: 390000, loss: 8.549622
step: 400000, loss: 8.388112
Evaluation...
"five" nearest neighbors: four, three, six, two, seven, eight, one, zero,
"of" nearest neighbors: the, a, with, also, for, and, which, by,
"going" nearest neighbors: have, are, both, called, being, a, of, had,
"hardware" nearest neighbors: may, de, some, have, so, which, other, also,
"american" nearest neighbors: s, british, UNK, from, in, including, first, see,
"britain" nearest neighbors: against, include, including, both, british, other, an, most,
step: 410000, loss: 8.757725
step: 420000, loss: 12.303110
step: 430000, loss: 12.325478
step: 440000, loss: 7.659882
step: 450000, loss: 6.028089
step: 460000, loss: 12.700299
step: 470000, loss: 7.063077
step: 480000, loss: 18.004183
step: 490000, loss: 7.510474
step: 500000, loss: 10.089376
step: 510000, loss: 11.404436
step: 520000, loss: 9.494527
step: 530000, loss: 7.797963
step: 540000, loss: 7.390718
step: 550000, loss: 13.911215
step: 560000, loss: 6.975731
step: 570000, loss: 6.179163
step: 580000, loss: 7.066525
step: 590000, loss: 6.487288
step: 600000, loss: 5.361528
Evaluation...
"five" nearest neighbors: four, six, three, seven, two, one, eight, zero,
"of" nearest neighbors: the, and, from, with, a, including, in, include,
"going" nearest neighbors: have, even, they, term, who, many, which, were,
"hardware" nearest neighbors: include, computer, an, which, other, each, than, may,
"american" nearest neighbors: english, french, s, german, from, in, film, see,
"britain" nearest neighbors: several, first, modern, part, government, german, was, were,
step: 610000, loss: 4.144980
step: 620000, loss: 5.865635
step: 630000, loss: 6.826498
step: 640000, loss: 8.376097
step: 650000, loss: 7.117930
step: 660000, loss: 7.639544
step: 670000, loss: 5.973255
step: 680000, loss: 4.908459
step: 690000, loss: 6.164993
step: 700000, loss: 7.360281
step: 710000, loss: 12.693079
step: 720000, loss: 6.410182
step: 730000, loss: 7.499201
step: 740000, loss: 6.509094
step: 750000, loss: 10.625893
step: 760000, loss: 7.177696
step: 770000, loss: 12.639092
step: 780000, loss: 8.441635
step: 790000, loss: 7.529139
step: 800000, loss: 6.579177
Evaluation...
"five" nearest neighbors: four, three, six, seven, eight, two, one, zero,
"of" nearest neighbors: and, with, in, the, its, from, by, including,
"going" nearest neighbors: have, they, how, include, people, however, also, their,
"hardware" nearest neighbors: computer, large, include, may, or, which, other, there,
"american" nearest neighbors: born, french, british, english, german, b, john, d,
"britain" nearest neighbors: country, including, include, general, part, various, several, by,
step: 810000, loss: 6.934138
step: 820000, loss: 5.686094
step: 830000, loss: 7.310243
step: 840000, loss: 5.028157
step: 850000, loss: 7.079705
step: 860000, loss: 6.768996
step: 870000, loss: 5.604030
step: 880000, loss: 8.208309
step: 890000, loss: 6.301597
step: 900000, loss: 5.733234
step: 910000, loss: 6.577081
step: 920000, loss: 6.774826
step: 930000, loss: 7.068932
step: 940000, loss: 6.694956
step: 950000, loss: 7.944673
step: 960000, loss: 5.988618
step: 970000, loss: 6.651366
step: 980000, loss: 4.595577
step: 990000, loss: 6.564834
step: 1000000, loss: 4.327858
Evaluation...
"five" nearest neighbors: four, three, seven, six, eight, two, nine, zero,
"of" nearest neighbors: the, first, and, became, from, under, at, with,
"going" nearest neighbors: others, has, then, have, how, become, had, also,
"hardware" nearest neighbors: computer, large, systems, these, different, either, include, using,
"american" nearest neighbors: b, born, d, UNK, nine, english, german, french,
"britain" nearest neighbors: government, island, local, country, by, including, control, within,
step: 1010000, loss: 5.841236
step: 1020000, loss: 5.805200
step: 1030000, loss: 9.962063
step: 1040000, loss: 6.281199
step: 1050000, loss: 7.147995
step: 1060000, loss: 5.721184
step: 1070000, loss: 7.080662
step: 1080000, loss: 6.638658
step: 1090000, loss: 5.814178
step: 1100000, loss: 5.195928
step: 1110000, loss: 6.724787
step: 1120000, loss: 6.503905
step: 1130000, loss: 5.762966
step: 1140000, loss: 5.790243
step: 1150000, loss: 5.958191
step: 1160000, loss: 5.997983
step: 1170000, loss: 7.065348
step: 1180000, loss: 6.073387
step: 1190000, loss: 6.644097
step: 1200000, loss: 5.934450
Evaluation...
"five" nearest neighbors: three, four, six, eight, seven, two, nine, zero,
"of" nearest neighbors: the, and, including, in, its, with, from, on,
"going" nearest neighbors: others, then, through, has, had, another, people, when,
"hardware" nearest neighbors: computer, control, systems, either, these, large, small, other,
"american" nearest neighbors: born, german, john, d, british, b, UNK, french,
"britain" nearest neighbors: local, against, british, island, country, general, including, within,
step: 1210000, loss: 5.832344
step: 1220000, loss: 6.453851
step: 1230000, loss: 6.583966
step: 1240000, loss: 5.571673
step: 1250000, loss: 5.720917
step: 1260000, loss: 7.663424
step: 1270000, loss: 6.583741
step: 1280000, loss: 8.503859
step: 1290000, loss: 5.540640
step: 1300000, loss: 6.703249
step: 1310000, loss: 5.274101
step: 1320000, loss: 5.846446
step: 1330000, loss: 5.438172
step: 1340000, loss: 6.367691
step: 1350000, loss: 6.558622
step: 1360000, loss: 9.822924
step: 1370000, loss: 4.982378
step: 1380000, loss: 6.159739
step: 1390000, loss: 5.819083
step: 1400000, loss: 7.775135
Evaluation...
"five" nearest neighbors: four, three, six, seven, two, eight, one, zero,
"of" nearest neighbors: and, the, in, with, its, within, for, including,
"going" nearest neighbors: others, through, while, has, to, how, particularly, their,
"hardware" nearest neighbors: computer, systems, large, control, research, using, information, either,
"american" nearest neighbors: english, french, german, born, film, british, s, former,
"britain" nearest neighbors: british, country, europe, local, military, island, against, western,
step: 1410000, loss: 8.214248
step: 1420000, loss: 4.696859
step: 1430000, loss: 5.873761
step: 1440000, loss: 5.971557
step: 1450000, loss: 4.992722
step: 1460000, loss: 5.197714
step: 1470000, loss: 6.916918
step: 1480000, loss: 6.441984
step: 1490000, loss: 5.443647
step: 1500000, loss: 5.178482
step: 1510000, loss: 6.060414
step: 1520000, loss: 6.373306
step: 1530000, loss: 5.098322
step: 1540000, loss: 6.674916
step: 1550000, loss: 6.712685
step: 1560000, loss: 5.280202
step: 1570000, loss: 6.454964
step: 1580000, loss: 4.896697
step: 1590000, loss: 6.239226
step: 1600000, loss: 5.709726
Evaluation...
"five" nearest neighbors: three, four, two, six, seven, eight, one, zero,
"of" nearest neighbors: the, and, including, in, with, within, its, following,
"going" nearest neighbors: others, people, who, they, that, far, were, have,
"hardware" nearest neighbors: computer, systems, include, high, research, some, information, large,
"american" nearest neighbors: born, english, french, british, german, d, john, b,
"britain" nearest neighbors: country, military, china, europe, against, local, central, british,
step: 1610000, loss: 6.334940
step: 1620000, loss: 5.093616
step: 1630000, loss: 6.119366
step: 1640000, loss: 4.975187
step: 1650000, loss: 6.490408
step: 1660000, loss: 7.464082
step: 1670000, loss: 4.977184
step: 1680000, loss: 5.658133
step: 1690000, loss: 5.352454
step: 1700000, loss: 6.810776
step: 1710000, loss: 5.687447
step: 1720000, loss: 5.992206
step: 1730000, loss: 5.513011
step: 1740000, loss: 5.548522
step: 1750000, loss: 6.200248
step: 1760000, loss: 13.070073
step: 1770000, loss: 4.621058
step: 1780000, loss: 5.301342
step: 1790000, loss: 4.777030
step: 1800000, loss: 6.912136
Evaluation...
"five" nearest neighbors: three, four, six, seven, eight, two, nine, zero,
"of" nearest neighbors: the, in, first, from, became, and, following, under,
"going" nearest neighbors: others, their, through, which, therefore, open, how, that,
"hardware" nearest neighbors: computer, systems, include, research, standard, different, system, small,
"american" nearest neighbors: b, d, born, actor, UNK, english, nine, german,
"britain" nearest neighbors: china, country, europe, against, canada, military, island, including,
step: 1810000, loss: 5.584600
step: 1820000, loss: 5.619820
step: 1830000, loss: 6.078709
step: 1840000, loss: 5.052518
step: 1850000, loss: 5.430106
step: 1860000, loss: 7.396770
step: 1870000, loss: 5.344787
step: 1880000, loss: 5.937998
step: 1890000, loss: 5.706491
step: 1900000, loss: 5.140662
step: 1910000, loss: 5.607048
step: 1920000, loss: 5.407231
step: 1930000, loss: 6.238531
step: 1940000, loss: 5.567973
step: 1950000, loss: 4.894245
step: 1960000, loss: 6.104193
step: 1970000, loss: 5.282631
step: 1980000, loss: 6.189069
step: 1990000, loss: 6.169409
step: 2000000, loss: 6.470152
Evaluation...
"five" nearest neighbors: four, three, six, seven, eight, two, nine, zero,
"of" nearest neighbors: the, its, in, with, and, including, within, against,
"going" nearest neighbors: others, only, therefore, will, how, a, far, though,
"hardware" nearest neighbors: computer, systems, for, network, software, program, research, system,
"american" nearest neighbors: born, actor, d, italian, german, john, robert, b,
"britain" nearest neighbors: china, country, europe, canada, british, former, island, france,
step: 2010000, loss: 5.298714
step: 2020000, loss: 5.494207
step: 2030000, loss: 5.410875
step: 2040000, loss: 6.228232
step: 2050000, loss: 5.044596
step: 2060000, loss: 4.624638
step: 2070000, loss: 4.919327
step: 2080000, loss: 4.639625
step: 2090000, loss: 4.865627
step: 2100000, loss: 4.951073
step: 2110000, loss: 5.973768
step: 2120000, loss: 7.366824
step: 2130000, loss: 5.149571
step: 2140000, loss: 7.846234
step: 2150000, loss: 5.449315
step: 2160000, loss: 5.359211
step: 2170000, loss: 5.171029
step: 2180000, loss: 6.106437
step: 2190000, loss: 6.043995
step: 2200000, loss: 5.642351
Evaluation...
"five" nearest neighbors: four, three, six, two, eight, seven, zero, one,
"of" nearest neighbors: the, and, its, see, for, in, with, including,
"going" nearest neighbors: others, therefore, how, even, them, your, have, although,
"hardware" nearest neighbors: computer, systems, system, network, program, research, software, include,
"american" nearest neighbors: english, french, german, canadian, british, film, author, italian,
"britain" nearest neighbors: europe, china, country, germany, british, england, france, throughout,
step: 2210000, loss: 4.427110
step: 2220000, loss: 6.240989
step: 2230000, loss: 5.184978
step: 2240000, loss: 8.035570
step: 2250000, loss: 5.793781
step: 2260000, loss: 4.908427
step: 2270000, loss: 8.807668
step: 2280000, loss: 6.083229
step: 2290000, loss: 5.773360
step: 2300000, loss: 5.613671
step: 2310000, loss: 6.080076
step: 2320000, loss: 5.288568
step: 2330000, loss: 5.949232
step: 2340000, loss: 5.479994
step: 2350000, loss: 7.717686
step: 2360000, loss: 5.163609
step: 2370000, loss: 5.989407
step: 2380000, loss: 5.785729
step: 2390000, loss: 5.345478
step: 2400000, loss: 6.627133
Evaluation...
"five" nearest neighbors: three, four, six, two, seven, eight, zero, nine,
"of" nearest neighbors: the, in, and, including, from, within, its, with,
"going" nearest neighbors: therefore, people, they, out, only, according, your, now,
"hardware" nearest neighbors: computer, systems, network, program, system, software, run, design,
"american" nearest neighbors: author, born, actor, english, canadian, british, italian, d,
"britain" nearest neighbors: china, europe, country, throughout, france, canada, england, western,
step: 2410000, loss: 5.666146
step: 2420000, loss: 5.316198
step: 2430000, loss: 5.129625
step: 2440000, loss: 5.247949
step: 2450000, loss: 5.741394
step: 2460000, loss: 5.833083
step: 2470000, loss: 7.704844
step: 2480000, loss: 5.398345
step: 2490000, loss: 5.089633
step: 2500000, loss: 5.620508
step: 2510000, loss: 4.976034
step: 2520000, loss: 5.884676
step: 2530000, loss: 6.649922
step: 2540000, loss: 5.002588
step: 2550000, loss: 5.072144
step: 2560000, loss: 5.165375
step: 2570000, loss: 5.310089
step: 2580000, loss: 5.481957
step: 2590000, loss: 6.104440
step: 2600000, loss: 5.339644
Evaluation...
"five" nearest neighbors: three, four, six, seven, eight, nine, two, zero,
"of" nearest neighbors: the, first, from, with, became, in, following, and,
"going" nearest neighbors: how, therefore, back, will, through, always, your, make,
"hardware" nearest neighbors: computer, systems, system, network, program, technology, design, software,
"american" nearest neighbors: actor, singer, born, b, author, d, english, writer,
"britain" nearest neighbors: europe, china, throughout, great, england, france, country, india,
step: 2610000, loss: 7.754117
step: 2620000, loss: 5.979313
step: 2630000, loss: 5.394362
step: 2640000, loss: 4.866740
step: 2650000, loss: 5.219806
step: 2660000, loss: 6.074809
step: 2670000, loss: 6.216953
step: 2680000, loss: 5.944881
step: 2690000, loss: 5.863350
step: 2700000, loss: 6.128705
step: 2710000, loss: 5.502523
step: 2720000, loss: 5.300839
step: 2730000, loss: 6.358493
step: 2740000, loss: 6.058306
step: 2750000, loss: 4.689510
step: 2760000, loss: 6.032880
step: 2770000, loss: 5.844904
step: 2780000, loss: 5.385874
step: 2790000, loss: 5.370956
step: 2800000, loss: 4.912577
Evaluation...
"five" nearest neighbors: four, six, three, eight, seven, two, nine, one,
"of" nearest neighbors: in, the, and, from, including, following, with, under,
"going" nearest neighbors: your, then, through, will, how, so, back, even,
"hardware" nearest neighbors: computer, systems, program, network, design, standard, physical, software,
"american" nearest neighbors: actor, singer, born, author, writer, canadian, italian, d,
"britain" nearest neighbors: europe, china, england, throughout, france, india, great, germany,
step: 2810000, loss: 5.897756
step: 2820000, loss: 7.194932
step: 2830000, loss: 7.430175
step: 2840000, loss: 7.258231
step: 2850000, loss: 5.837617
step: 2860000, loss: 5.496673
step: 2870000, loss: 6.173716
step: 2880000, loss: 6.095749
step: 2890000, loss: 6.064944
step: 2900000, loss: 5.560488
step: 2910000, loss: 4.966107
step: 2920000, loss: 5.789579
step: 2930000, loss: 4.525987
step: 2940000, loss: 6.704808
step: 2950000, loss: 4.506433
step: 2960000, loss: 6.251270
step: 2970000, loss: 5.588204
step: 2980000, loss: 5.423235
step: 2990000, loss: 5.613834
step: 3000000, loss: 5.137326
Evaluation...
"five" nearest neighbors: four, three, six, seven, eight, two, zero, one,
"of" nearest neighbors: the, including, and, with, in, its, includes, within,
"going" nearest neighbors: how, they, when, them, make, always, your, though,
"hardware" nearest neighbors: computer, systems, network, program, physical, design, technology, software,
"american" nearest neighbors: canadian, english, australian, british, german, film, italian, author,
"britain" nearest neighbors: europe, england, china, throughout, india, france, great, british,

 

[1] : https://arxiv.org/pdf/1301.3781.pdf

 

Be First to Comment

发表回复

您的电子邮箱地址不会被公开。 必填项已用*标注