转换天赋语言模型张量，以便在 TensorBoard 投影仪中查看

Question

我想转换"向量，">

vectors = [token.embedding for token in sentence]
print(type(vectors))
<class 'list'>
print(vectors)
[tensor([ 0.0077, -0.0227, -0.0004,  ...,  0.1377, -0.0003,  0.0028]),
...
tensor([ 0.0003, -0.0461,  0.0043,  ..., -0.0126, -0.0004,  0.0142])]

自

0.0077 -0.0227 -0.0004 ... 0.1377 -0.0003 0.0028
...
0.0003 -0.0461 0.0043 ... -0.0126 -0.0004 0.0142

并将其写入 TSV。

旁白：这些嵌入来自flair(https://github.com/zalandoresearch/flair(：我怎样才能获得完整的输出，而不是-0.0004 ... 0.1377的缩写输出？

Answer 1

好吧，我挖了...

1. 事实证明，这些是PyTorch张量(Flair使用PyTorch(。 对于到NumPy数组的简单转换(根据PyTorch文档在 https://pytorch.org/docs/stable/tensors.html#torch.Tensor.tolist 和这个StackOverFlow答案使用tolist()，一个PyTorch方法。

   >>> import torch
   >>> a = torch.randn(2, 2)
   >>> print(a)
   tensor([[-2.1693,  0.7698],
   [ 0.0497,  0.8462]])
   >>> a.tolist()
   [[-2.1692984104156494, 0.7698001265525818],
   [0.049718063324689865, 0.8462421298027039]]
   

---

2. 根据我最初的问题，这里是如何将这些数据转换为纯文本并将它们写入 TSV 文件的方法。

   from flair.embeddings import FlairEmbeddings, Sentence
   from flair.models import SequenceTagger
   from flair.embeddings import StackedEmbeddings
   embeddings_f = FlairEmbeddings('pubmed-forward')
   embeddings_b = FlairEmbeddings('pubmed-backward')
   sentence = Sentence('The RAS-MAPK signalling cascade serves as a central node in transducing signals from membrane receptors to the nucleus.')
   tagger = SequenceTagger.load('ner')
   tagger.predict(sentence)
   embeddings_f.embed(sentence)
   stacked_embeddings = StackedEmbeddings([
   embeddings_f,
   embeddings_b,
   ])
   stacked_embeddings.embed(sentence)
   # for token in sentence:
   #     print(token)
   #     print(token.embedding)
   #     print(token.embedding.shape)
   tokens = [token for token in sentence]
   print(tokens)
   '''
   [Token: 1 The, Token: 2 RAS-MAPK, Token: 3 signalling, Token: 4 cascade, Token: 5 serves, Token: 6 as, Token: 7 a, Token: 8 central, Token: 9 node, Token: 10 in, Token: 11 transducing, Token: 12 signals, Token: 13 from, Token: 14 membrane, Token: 15 receptors, Token: 16 to, Token: 17 the, Token: 18 nucleus.]
   '''
   ## https://www.geeksforgeeks.org/python-string-split/
   tokens = [str(token).split()[2] for token in sentence]
   print(tokens)
   '''
   ['The', 'RAS-MAPK', 'signalling', 'cascade', 'serves', 'as', 'a', 'central', 'node', 'in', 'transducing', 'signals', 'from', 'membrane', 'receptors', 'to', 'the', 'nucleus.']
   '''
   tensors = [token.embedding for token in sentence]
   print(tensors)
   '''
   [tensor([ 0.0077, -0.0227, -0.0004,  ...,  0.1377, -0.0003,  0.0028]),
   tensor([-0.0007, -0.1601, -0.0274,  ...,  0.1982,  0.0013,  0.0042]),
   tensor([ 4.2534e-03, -3.1018e-01, -3.9660e-01,  ...,  5.9336e-02, -9.4445e-05,  1.0025e-02]),
   tensor([ 0.0026, -0.0087, -0.1398,  ..., -0.0037,  0.0012,  0.0274]),
   tensor([-0.0005, -0.0164, -0.0233,  ..., -0.0013,  0.0039,  0.0004]),
   tensor([ 3.8261e-03, -7.6409e-02, -1.8632e-02,  ..., -2.8906e-03, -4.4556e-04,  5.6909e-05]),
   tensor([ 0.0035, -0.0207,  0.1700,  ..., -0.0193,  0.0017,  0.0006]),
   tensor([ 0.0159, -0.4097, -0.0489,  ...,  0.0743,  0.0005,  0.0012]),
   tensor([ 9.7725e-03, -3.3817e-01, -2.2848e-02,  ..., -6.6284e-02, 2.3646e-04,  1.0505e-02]),
   tensor([ 0.0219, -0.0677, -0.0154,  ...,  0.0102,  0.0066,  0.0016]),
   tensor([ 0.0092, -0.0431, -0.0450,  ...,  0.0060,  0.0002,  0.0005]),
   tensor([ 0.0047, -0.2732, -0.0408,  ...,  0.0136,  0.0005,  0.0072]),
   tensor([ 0.0072, -0.0173, -0.0149,  ..., -0.0013, -0.0004,  0.0056]),
   tensor([ 0.0086, -0.1151, -0.0629,  ...,  0.0043,  0.0050,  0.0016]),
   tensor([ 7.6452e-03, -2.3825e-01, -1.5683e-02,  ..., -5.4974e-04, -1.4646e-04,  6.6120e-03]),
   tensor([ 0.0038, -0.0354, -0.1337,  ...,  0.0060, -0.0004,  0.0102]),
   tensor([ 0.0186, -0.0151, -0.0641,  ...,  0.0188,  0.0391,  0.0069]),
   tensor([ 0.0003, -0.0461,  0.0043,  ..., -0.0126, -0.0004,  0.0142])]
   '''
   # ----------------------------------------
   ## Write those data to TSV files.
   ## https://stackoverflow.com/a/29896136/1904943
   import csv
   metadata_f = 'metadata.tsv'
   tensors_f = 'tensors.tsv'
   with open(metadata_f, 'w', encoding='utf8', newline='') as tsv_file:
   tsv_writer = csv.writer(tsv_file, delimiter='t', lineterminator='n')
   for token in tokens:
   ## Assign to a dummy variable ( _ ) to suppress character counts;
   ## if I use (token), rather than ([token]), I get spaces between all characters:
   _ = tsv_writer.writerow([token])
   ## metadata.tsv :
   '''
   The
   RAS-MAPK
   signalling
   cascade
   serves
   as
   a
   central
   node
   in
   transducing
   signals
   from
   membrane
   receptors
   to
   the
   nucleus.
   '''
   with open(metadata_f, 'w', encoding='utf8', newline='') as tsv_file:
   tsv_writer = csv.writer(tsv_file, delimiter='t', lineterminator='n')
   _ = tsv_writer.writerow(tokens)
   ## metadata.tsv :
   '''
   The   RAS-MAPK    signalling  cascade serves  as  a   central node    in  transducing signals from    membrane    receptors   to  the nucleus.
   '''
   tensors = [token.embedding for token in sentence]
   print(tensors)
   '''
   [tensor([ 0.0077, -0.0227, -0.0004,  ...,  0.1377, -0.0003,  0.0028]),
   tensor([-0.0007, -0.1601, -0.0274,  ...,  0.1982,  0.0013,  0.0042]),
   tensor([ 4.2534e-03, -3.1018e-01, -3.9660e-01,  ...,  5.9336e-02, -9.4445e-05,  1.0025e-02]),
   tensor([ 0.0026, -0.0087, -0.1398,  ..., -0.0037,  0.0012,  0.0274]),
   tensor([-0.0005, -0.0164, -0.0233,  ..., -0.0013,  0.0039,  0.0004]),
   tensor([ 3.8261e-03, -7.6409e-02, -1.8632e-02,  ..., -2.8906e-03, -4.4556e-04,  5.6909e-05]),
   tensor([ 0.0035, -0.0207,  0.1700,  ..., -0.0193,  0.0017,  0.0006]),
   tensor([ 0.0159, -0.4097, -0.0489,  ...,  0.0743,  0.0005,  0.0012]),
   tensor([ 9.7725e-03, -3.3817e-01, -2.2848e-02,  ..., -6.6284e-02, 2.3646e-04,  1.0505e-02]),
   tensor([ 0.0219, -0.0677, -0.0154,  ...,  0.0102,  0.0066,  0.0016]),
   tensor([ 0.0092, -0.0431, -0.0450,  ...,  0.0060,  0.0002,  0.0005]),
   tensor([ 0.0047, -0.2732, -0.0408,  ...,  0.0136,  0.0005,  0.0072]),
   tensor([ 0.0072, -0.0173, -0.0149,  ..., -0.0013, -0.0004,  0.0056]),
   tensor([ 0.0086, -0.1151, -0.0629,  ...,  0.0043,  0.0050,  0.0016]),
   tensor([ 7.6452e-03, -2.3825e-01, -1.5683e-02,  ..., -5.4974e-04, -1.4646e-04,  6.6120e-03]),
   tensor([ 0.0038, -0.0354, -0.1337,  ...,  0.0060, -0.0004,  0.0102]),
   tensor([ 0.0186, -0.0151, -0.0641,  ...,  0.0188,  0.0391,  0.0069]),
   tensor([ 0.0003, -0.0461,  0.0043,  ..., -0.0126, -0.0004,  0.0142])]
   '''
   with open(tensors_f, 'w', encoding='utf8', newline='') as tsv_file:
   tsv_writer = csv.writer(tsv_file, delimiter='t', lineterminator='n')
   for token in sentence:
   embedding = token.embedding
   _ = tsv_writer.writerow(embedding.tolist())
   ## tensors.tsv (18 lines: one embedding per token in metadata.tsv):
   ## note: enormous output, even for this simple sentence.
   '''
   0.007691788021475077  -0.02268664352595806    -0.0004340760060586035  ...
   '''
   

---

3. 最后，我的目的是将上下文语言嵌入(Flair等(加载到TensorFlow的嵌入投影器中。 事实证明，我所需要做的就是将(此处为Flair数据(转换为NumPy数组，并将它们加载到TensorFlow TensorBoard实例中(不需要TSV文件！

   我在我的博客文章中详细描述了这一点：在TensorFlow的TensorBoard中可视化语言模型张量(嵌入([TensorBoard Projector：PCA; t-SNE; ...]。

Answer 2

要获取令牌，您可以使用 token.text 和 token.embedding.tolist(( 来获取嵌入：

def flair_embeddings(sentences, output_file=None):
if output_file:
f = open(output_file, 'w')
# init embedding
flair_embedding_forward = FlairEmbeddings('news-forward')

for i, sent in enumerate(sentences):
print("Encoding the {}th input sentence!".format(i))
# create a sentence
sentence = Sentence(sent)
# embed words in sentence
flair_embedding_forward.embed(sentence)
for token in sentence:
if output_file:
f.write(token.text + "t" + "t".join([str(num) for num in token.embedding.tolist()]) + 'n')
else:
print(token.text + "t" + "t".join([str(num) for num in token.embedding.tolist()]) + 'n')