”
トークンが含まれていることに注意しよ。
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
vocab = d2l.Vocab(sentences, min_freq=10)
f'vocab size: {len(vocab)}'
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'vocab size: 6719'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
vocab = d2l.Vocab(sentences, min_freq=10)
f'vocab size: {len(vocab)}'
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'vocab size: 6719'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def subsample(sentences, vocab):
"""Subsample high-frequency words."""
# Exclude unknown tokens ('')
sentences = [[token for token in line if vocab[token] != vocab.unk]
for line in sentences]
counter = collections.Counter([
token for line in sentences for token in line])
num_tokens = sum(counter.values())
# Return True if `token` is kept during subsampling
def keep(token):
return(random.uniform(0, 1) <
math.sqrt(1e-4 / counter[token] * num_tokens))
return ([[token for token in line if keep(token)] for line in sentences],
counter)
subsampled, counter = subsample(sentences, vocab)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def subsample(sentences, vocab):
"""Subsample high-frequency words."""
# Exclude unknown tokens ('')
sentences = [[token for token in line if vocab[token] != vocab.unk]
for line in sentences]
counter = collections.Counter([
token for line in sentences for token in line])
num_tokens = sum(counter.values())
# Return True if `token` is kept during subsampling
def keep(token):
return(random.uniform(0, 1) <
math.sqrt(1e-4 / counter[token] * num_tokens))
return ([[token for token in line if keep(token)] for line in sentences],
counter)
subsampled, counter = subsample(sentences, vocab)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def subsample(sentences, vocab):
"""Subsample high-frequency words."""
# Exclude unknown tokens ('')
sentences = [[token for token in line if vocab[token] != vocab.unk]
for line in sentences]
counter = collections.Counter([
token for line in sentences for token in line])
num_tokens = sum(counter.values())
# Return True if `token` is kept during subsampling
def keep(token):
return(random.uniform(0, 1) <
math.sqrt(1e-4 / counter[token] * num_tokens))
return ([[token for token in line if keep(token)] for line in sentences],
counter)
subsampled, counter = subsample(sentences, vocab)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def subsample(sentences, vocab):
"""Subsample high-frequency words."""
# Exclude unknown tokens ('')
sentences = [[token for token in line if vocab[token] != vocab.unk]
for line in sentences]
counter = collections.Counter([
token for line in sentences for token in line])
num_tokens = sum(counter.values())
# Return True if `token` is kept during subsampling
def keep(token):
return(random.uniform(0, 1) <
math.sqrt(1e-4 / counter[token] * num_tokens))
return ([[token for token in line if keep(token)] for line in sentences],
counter)
subsampled, counter = subsample(sentences, vocab)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
d2l.show_list_len_pair_hist(['origin', 'subsampled'], '# tokens per sentence',
'count', sentences, subsampled);
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
d2l.show_list_len_pair_hist(['origin', 'subsampled'], '# tokens per sentence',
'count', sentences, subsampled);
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
d2l.show_list_len_pair_hist(['origin', 'subsampled'], '# tokens per sentence',
'count', sentences, subsampled);
.. figure:: output_word-embedding-dataset_85ec04_63_0.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
d2l.show_list_len_pair_hist(['origin', 'subsampled'], '# tokens per sentence',
'count', sentences, subsampled);
.. figure:: output_word-embedding-dataset_85ec04_66_0.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def compare_counts(token):
return (f'# of "{token}": '
f'before={sum([l.count(token) for l in sentences])}, '
f'after={sum([l.count(token) for l in subsampled])}')
compare_counts('the')
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def compare_counts(token):
return (f'# of "{token}": '
f'before={sum([l.count(token) for l in sentences])}, '
f'after={sum([l.count(token) for l in subsampled])}')
compare_counts('the')
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def compare_counts(token):
return (f'# of "{token}": '
f'before={sum([l.count(token) for l in sentences])}, '
f'after={sum([l.count(token) for l in subsampled])}')
compare_counts('the')
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'# of "the": before=50770, after=1929'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def compare_counts(token):
return (f'# of "{token}": '
f'before={sum([l.count(token) for l in sentences])}, '
f'after={sum([l.count(token) for l in subsampled])}')
compare_counts('the')
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'# of "the": before=50770, after=2004'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
compare_counts('join')
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
compare_counts('join')
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
compare_counts('join')
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'# of "join": before=45, after=45'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
compare_counts('join')
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'# of "join": before=45, after=45'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
corpus = [vocab[line] for line in subsampled]
corpus[:3]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
corpus = [vocab[line] for line in subsampled]
corpus[:3]
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
corpus = [vocab[line] for line in subsampled]
corpus[:3]
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
[[], [6697, 3228, 1773], [3922, 1922, 4743]]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
corpus = [vocab[line] for line in subsampled]
corpus[:3]
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
[[], [4127, 3228, 710], [3895, 993, 3922, 1922, 4743]]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def get_centers_and_contexts(corpus, max_window_size):
"""Return center words and context words in skip-gram."""
centers, contexts = [], []
for line in corpus:
# To form a "center word--context word" pair, each sentence needs to
# have at least 2 words
if len(line) < 2:
continue
centers += line
for i in range(len(line)): # Context window centered at `i`
window_size = random.randint(1, max_window_size)
indices = list(range(max(0, i - window_size),
min(len(line), i + 1 + window_size)))
# Exclude the center word from the context words
indices.remove(i)
contexts.append([line[idx] for idx in indices])
return centers, contexts
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def get_centers_and_contexts(corpus, max_window_size):
"""Return center words and context words in skip-gram."""
centers, contexts = [], []
for line in corpus:
# To form a "center word--context word" pair, each sentence needs to
# have at least 2 words
if len(line) < 2:
continue
centers += line
for i in range(len(line)): # Context window centered at `i`
window_size = random.randint(1, max_window_size)
indices = list(range(max(0, i - window_size),
min(len(line), i + 1 + window_size)))
# Exclude the center word from the context words
indices.remove(i)
contexts.append([line[idx] for idx in indices])
return centers, contexts
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def get_centers_and_contexts(corpus, max_window_size):
"""Return center words and context words in skip-gram."""
centers, contexts = [], []
for line in corpus:
# To form a "center word--context word" pair, each sentence needs to
# have at least 2 words
if len(line) < 2:
continue
centers += line
for i in range(len(line)): # Context window centered at `i`
window_size = random.randint(1, max_window_size)
indices = list(range(max(0, i - window_size),
min(len(line), i + 1 + window_size)))
# Exclude the center word from the context words
indices.remove(i)
contexts.append([line[idx] for idx in indices])
return centers, contexts
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def get_centers_and_contexts(corpus, max_window_size):
"""Return center words and context words in skip-gram."""
centers, contexts = [], []
for line in corpus:
# To form a "center word--context word" pair, each sentence needs to
# have at least 2 words
if len(line) < 2:
continue
centers += line
for i in range(len(line)): # Context window centered at `i`
window_size = random.randint(1, max_window_size)
indices = list(range(max(0, i - window_size),
min(len(line), i + 1 + window_size)))
# Exclude the center word from the context words
indices.remove(i)
contexts.append([line[idx] for idx in indices])
return centers, contexts
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
tiny_dataset = [list(range(7)), list(range(7, 10))]
print('dataset', tiny_dataset)
for center, context in zip(*get_centers_and_contexts(tiny_dataset, 2)):
print('center', center, 'has contexts', context)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
tiny_dataset = [list(range(7)), list(range(7, 10))]
print('dataset', tiny_dataset)
for center, context in zip(*get_centers_and_contexts(tiny_dataset, 2)):
print('center', center, 'has contexts', context)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
tiny_dataset = [list(range(7)), list(range(7, 10))]
print('dataset', tiny_dataset)
for center, context in zip(*get_centers_and_contexts(tiny_dataset, 2)):
print('center', center, 'has contexts', context)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
dataset [[0, 1, 2, 3, 4, 5, 6], [7, 8, 9]]
center 0 has contexts [1, 2]
center 1 has contexts [0, 2, 3]
center 2 has contexts [1, 3]
center 3 has contexts [2, 4]
center 4 has contexts [2, 3, 5, 6]
center 5 has contexts [4, 6]
center 6 has contexts [5]
center 7 has contexts [8, 9]
center 8 has contexts [7, 9]
center 9 has contexts [8]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
tiny_dataset = [list(range(7)), list(range(7, 10))]
print('dataset', tiny_dataset)
for center, context in zip(*get_centers_and_contexts(tiny_dataset, 2)):
print('center', center, 'has contexts', context)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
dataset [[0, 1, 2, 3, 4, 5, 6], [7, 8, 9]]
center 0 has contexts [1]
center 1 has contexts [0, 2]
center 2 has contexts [0, 1, 3, 4]
center 3 has contexts [1, 2, 4, 5]
center 4 has contexts [2, 3, 5, 6]
center 5 has contexts [4, 6]
center 6 has contexts [4, 5]
center 7 has contexts [8]
center 8 has contexts [7, 9]
center 9 has contexts [8]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
all_centers, all_contexts = get_centers_and_contexts(corpus, 5)
f'# center-context pairs: {sum([len(contexts) for contexts in all_contexts])}'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
all_centers, all_contexts = get_centers_and_contexts(corpus, 5)
f'# center-context pairs: {sum([len(contexts) for contexts in all_contexts])}'
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
all_centers, all_contexts = get_centers_and_contexts(corpus, 5)
f'# center-context pairs: {sum([len(contexts) for contexts in all_contexts])}'
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'# center-context pairs: 1495467'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
all_centers, all_contexts = get_centers_and_contexts(corpus, 5)
f'# center-context pairs: {sum([len(contexts) for contexts in all_contexts])}'
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
'# center-context pairs: 1500813'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
class RandomGenerator:
"""Randomly draw among {1, ..., n} according to n sampling weights."""
def __init__(self, sampling_weights):
# Exclude
self.population = list(range(1, len(sampling_weights) + 1))
self.sampling_weights = sampling_weights
self.candidates = []
self.i = 0
def draw(self):
if self.i == len(self.candidates):
# Cache `k` random sampling results
self.candidates = random.choices(
self.population, self.sampling_weights, k=10000)
self.i = 0
self.i += 1
return self.candidates[self.i - 1]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
class RandomGenerator:
"""Randomly draw among {1, ..., n} according to n sampling weights."""
def __init__(self, sampling_weights):
# Exclude
self.population = list(range(1, len(sampling_weights) + 1))
self.sampling_weights = sampling_weights
self.candidates = []
self.i = 0
def draw(self):
if self.i == len(self.candidates):
# Cache `k` random sampling results
self.candidates = random.choices(
self.population, self.sampling_weights, k=10000)
self.i = 0
self.i += 1
return self.candidates[self.i - 1]
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
class RandomGenerator:
"""Randomly draw among {1, ..., n} according to n sampling weights."""
def __init__(self, sampling_weights):
# Exclude
self.population = list(range(1, len(sampling_weights) + 1))
self.sampling_weights = sampling_weights
self.candidates = []
self.i = 0
def draw(self):
if self.i == len(self.candidates):
# Cache `k` random sampling results
self.candidates = random.choices(
self.population, self.sampling_weights, k=10000)
self.i = 0
self.i += 1
return self.candidates[self.i - 1]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
class RandomGenerator:
"""Randomly draw among {1, ..., n} according to n sampling weights."""
def __init__(self, sampling_weights):
# Exclude
self.population = list(range(1, len(sampling_weights) + 1))
self.sampling_weights = sampling_weights
self.candidates = []
self.i = 0
def draw(self):
if self.i == len(self.candidates):
# Cache `k` random sampling results
self.candidates = random.choices(
self.population, self.sampling_weights, k=10000)
self.i = 0
self.i += 1
return self.candidates[self.i - 1]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def get_negatives(all_contexts, vocab, counter, K):
"""Return noise words in negative sampling."""
# Sampling weights for words with indices 1, 2, ... (index 0 is the
# excluded unknown token) in the vocabulary
sampling_weights = [counter[vocab.to_tokens(i)]**0.75
for i in range(1, len(vocab))]
all_negatives, generator = [], RandomGenerator(sampling_weights)
for contexts in all_contexts:
negatives = []
while len(negatives) < len(contexts) * K:
neg = generator.draw()
# Noise words cannot be context words
if neg not in contexts:
negatives.append(neg)
all_negatives.append(negatives)
return all_negatives
all_negatives = get_negatives(all_contexts, vocab, counter, 5)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def get_negatives(all_contexts, vocab, counter, K):
"""Return noise words in negative sampling."""
# Sampling weights for words with indices 1, 2, ... (index 0 is the
# excluded unknown token) in the vocabulary
sampling_weights = [counter[vocab.to_tokens(i)]**0.75
for i in range(1, len(vocab))]
all_negatives, generator = [], RandomGenerator(sampling_weights)
for contexts in all_contexts:
negatives = []
while len(negatives) < len(contexts) * K:
neg = generator.draw()
# Noise words cannot be context words
if neg not in contexts:
negatives.append(neg)
all_negatives.append(negatives)
return all_negatives
all_negatives = get_negatives(all_contexts, vocab, counter, 5)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def get_negatives(all_contexts, vocab, counter, K):
"""Return noise words in negative sampling."""
# Sampling weights for words with indices 1, 2, ... (index 0 is the
# excluded unknown token) in the vocabulary
sampling_weights = [counter[vocab.to_tokens(i)]**0.75
for i in range(1, len(vocab))]
all_negatives, generator = [], RandomGenerator(sampling_weights)
for contexts in all_contexts:
negatives = []
while len(negatives) < len(contexts) * K:
neg = generator.draw()
# Noise words cannot be context words
if neg not in contexts:
negatives.append(neg)
all_negatives.append(negatives)
return all_negatives
all_negatives = get_negatives(all_contexts, vocab, counter, 5)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
generator = RandomGenerator([2, 3, 4])
[generator.draw() for _ in range(10)]
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
[2, 3, 3, 2, 1, 2, 3, 3, 3, 2]
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def batchify(data):
"""Return a minibatch of examples for skip-gram with negative sampling."""
max_len = max(len(c) + len(n) for _, c, n in data)
centers, contexts_negatives, masks, labels = [], [], [], []
for center, context, negative in data:
cur_len = len(context) + len(negative)
centers += [center]
contexts_negatives += [context + negative + [0] * (max_len - cur_len)]
masks += [[1] * cur_len + [0] * (max_len - cur_len)]
labels += [[1] * len(context) + [0] * (max_len - len(context))]
return (d2l.reshape(d2l.tensor(centers), (-1, 1)), d2l.tensor(
contexts_negatives), d2l.tensor(masks), d2l.tensor(labels))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def batchify(data):
"""Return a minibatch of examples for skip-gram with negative sampling."""
max_len = max(len(c) + len(n) for _, c, n in data)
centers, contexts_negatives, masks, labels = [], [], [], []
for center, context, negative in data:
cur_len = len(context) + len(negative)
centers += [center]
contexts_negatives += [context + negative + [0] * (max_len - cur_len)]
masks += [[1] * cur_len + [0] * (max_len - cur_len)]
labels += [[1] * len(context) + [0] * (max_len - len(context))]
return (d2l.reshape(d2l.tensor(centers), (-1, 1)), d2l.tensor(
contexts_negatives), d2l.tensor(masks), d2l.tensor(labels))
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def batchify(data):
"""Return a minibatch of examples for skip-gram with negative sampling."""
max_len = max(len(c) + len(n) for _, c, n in data)
centers, contexts_negatives, masks, labels = [], [], [], []
for center, context, negative in data:
cur_len = len(context) + len(negative)
centers += [center]
contexts_negatives += [context + negative + [0] * (max_len - cur_len)]
masks += [[1] * cur_len + [0] * (max_len - cur_len)]
labels += [[1] * len(context) + [0] * (max_len - len(context))]
return (d2l.reshape(d2l.tensor(centers), (-1, 1)), d2l.tensor(
contexts_negatives), d2l.tensor(masks), d2l.tensor(labels))
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def get_negatives(all_contexts, vocab, counter, K):
"""Return noise words in negative sampling."""
# Sampling weights for words with indices 1, 2, ... (index 0 is the
# excluded unknown token) in the vocabulary
sampling_weights = [counter[vocab.to_tokens(i)]**0.75
for i in range(1, len(vocab))]
all_negatives, generator = [], RandomGenerator(sampling_weights)
for contexts in all_contexts:
negatives = []
while len(negatives) < len(contexts) * K:
neg = generator.draw()
# Noise words cannot be context words
if neg not in contexts:
negatives.append(neg)
all_negatives.append(negatives)
return all_negatives
all_negatives = get_negatives(all_contexts, vocab, counter, 5)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
x_1 = (1, [2, 2], [3, 3, 3, 3])
x_2 = (1, [2, 2, 2], [3, 3])
batch = batchify((x_1, x_2))
names = ['centers', 'contexts_negatives', 'masks', 'labels']
for name, data in zip(names, batch):
print(name, '=', data)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
x_1 = (1, [2, 2], [3, 3, 3, 3])
x_2 = (1, [2, 2, 2], [3, 3])
batch = batchify((x_1, x_2))
names = ['centers', 'contexts_negatives', 'masks', 'labels']
for name, data in zip(names, batch):
print(name, '=', data)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
x_1 = (1, [2, 2], [3, 3, 3, 3])
x_2 = (1, [2, 2, 2], [3, 3])
batch = batchify((x_1, x_2))
names = ['centers', 'contexts_negatives', 'masks', 'labels']
for name, data in zip(names, batch):
print(name, '=', data)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
centers = tensor([[1],
[1]])
contexts_negatives = tensor([[2, 2, 3, 3, 3, 3],
[2, 2, 2, 3, 3, 0]])
masks = tensor([[1, 1, 1, 1, 1, 1],
[1, 1, 1, 1, 1, 0]])
labels = tensor([[1, 1, 0, 0, 0, 0],
[1, 1, 1, 0, 0, 0]])
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def batchify(data):
"""Return a minibatch of examples for skip-gram with negative sampling."""
max_len = max(len(c) + len(n) for _, c, n in data)
centers, contexts_negatives, masks, labels = [], [], [], []
for center, context, negative in data:
cur_len = len(context) + len(negative)
centers += [center]
contexts_negatives += [context + negative + [0] * (max_len - cur_len)]
masks += [[1] * cur_len + [0] * (max_len - cur_len)]
labels += [[1] * len(context) + [0] * (max_len - len(context))]
return (d2l.reshape(d2l.tensor(centers), (-1, 1)), d2l.tensor(
contexts_negatives), d2l.tensor(masks), d2l.tensor(labels))
.. raw:: html
.. raw:: html