/
translate_input.py
640 lines (409 loc) · 17.8 KB
/
translate_input.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
# %%
import torch
import torch.nn as nn
import torch.optim as optim
import torchtext
from torchtext.data import Field, BucketIterator, TabularDataset
from torchtext.data.functional import sentencepiece_tokenizer, load_sp_model
from pathlib import Path
import dill
import numpy as np
import os
import random
import re
# %%
# path where the model and training data (for vocabulary) is saved
# name of the model: "model.pt"
path = Path("model/sentencepiece/20200728-152255/english_pretraining_with_sp/")
INPUT = "Das Wetter ist sehr schön."
# %%
sp_deu = load_sp_model(str(path / "spm_deu.model"))
sp_nds = load_sp_model(str(path / "spm_nds.model"))
#%%
SRC = Field(use_vocab = False, tokenize = sp_deu.encode,
init_token = sp_deu.bos_id(),
eos_token = sp_deu.eos_id(),
pad_token = sp_deu.pad_id(),
batch_first = True
)
TRG = Field(use_vocab = False, tokenize = sp_nds.encode,
init_token = sp_nds.bos_id(),
eos_token = sp_nds.eos_id(),
pad_token = sp_nds.pad_id(),
batch_first = True
)
print(SRC)
# %%
class Encoder(nn.Module):
def __init__(self,
input_dim,
hid_dim,
n_layers,
n_heads,
pf_dim,
dropout,
device,
max_length = 100):
super().__init__()
self.device = device
self.tok_embedding = nn.Embedding(input_dim, hid_dim)
self.pos_embedding = nn.Embedding(max_length, hid_dim)
self.layers = nn.ModuleList([EncoderLayer(hid_dim,
n_heads,
pf_dim,
dropout,
device)
for _ in range(n_layers)])
self.dropout = nn.Dropout(dropout)
self.scale = torch.sqrt(torch.FloatTensor([hid_dim])).to(device)
def forward(self, src, src_mask):
#src = [batch size, src len]
#src_mask = [batch size, src len]
batch_size = src.shape[0]
src_len = src.shape[1]
pos = torch.arange(0, src_len).unsqueeze(0).repeat(batch_size, 1).to(self.device)
#pos = [batch size, src len]
src = self.dropout((self.tok_embedding(src) * self.scale) + self.pos_embedding(pos))
#src = [batch size, src len, hid dim]
for layer in self.layers:
src = layer(src, src_mask)
#src = [batch size, src len, hid dim]
return src
#
# %%
class EncoderLayer(nn.Module):
def __init__(self,
hid_dim,
n_heads,
pf_dim,
dropout,
device):
super().__init__()
self.self_attn_layer_norm = nn.LayerNorm(hid_dim)
self.ff_layer_norm = nn.LayerNorm(hid_dim)
self.self_attention = MultiHeadAttentionLayer(hid_dim, n_heads, dropout, device)
self.positionwise_feedforward = PositionwiseFeedforwardLayer(hid_dim,
pf_dim,
dropout)
self.dropout = nn.Dropout(dropout)
def forward(self, src, src_mask):
#src = [batch size, src len, hid dim]
#src_mask = [batch size, src len]
#self attention
_src, _ = self.self_attention(src, src, src, src_mask)
#dropout, residual connection and layer norm
src = self.self_attn_layer_norm(src + self.dropout(_src))
#src = [batch size, src len, hid dim]
#positionwise feedforward
_src = self.positionwise_feedforward(src)
#dropout, residual and layer norm
src = self.ff_layer_norm(src + self.dropout(_src))
#src = [batch size, src len, hid dim]
return src
# %%
class MultiHeadAttentionLayer(nn.Module):
def __init__(self, hid_dim, n_heads, dropout, device):
super().__init__()
assert hid_dim % n_heads == 0
self.hid_dim = hid_dim
self.n_heads = n_heads
self.head_dim = hid_dim // n_heads
self.fc_q = nn.Linear(hid_dim, hid_dim)
self.fc_k = nn.Linear(hid_dim, hid_dim)
self.fc_v = nn.Linear(hid_dim, hid_dim)
self.fc_o = nn.Linear(hid_dim, hid_dim)
self.dropout = nn.Dropout(dropout)
self.scale = torch.sqrt(torch.FloatTensor([self.head_dim])).to(device)
def forward(self, query, key, value, mask = None):
batch_size = query.shape[0]
#query = [batch size, query len, hid dim]
#key = [batch size, key len, hid dim]
#value = [batch size, value len, hid dim]
Q = self.fc_q(query)
K = self.fc_k(key)
V = self.fc_v(value)
#Q = [batch size, query len, hid dim]
#K = [batch size, key len, hid dim]
#V = [batch size, value len, hid dim]
Q = Q.view(batch_size, -1, self.n_heads, self.head_dim).permute(0, 2, 1, 3)
K = K.view(batch_size, -1, self.n_heads, self.head_dim).permute(0, 2, 1, 3)
V = V.view(batch_size, -1, self.n_heads, self.head_dim).permute(0, 2, 1, 3)
#Q = [batch size, n heads, query len, head dim]
#K = [batch size, n heads, key len, head dim]
#V = [batch size, n heads, value len, head dim]
energy = torch.matmul(Q, K.permute(0, 1, 3, 2)) / self.scale
#energy = [batch size, n heads, query len, key len]
if mask is not None:
energy = energy.masked_fill(mask == 0, -1e10)
attention = torch.softmax(energy, dim = -1)
#attention = [batch size, n heads, query len, key len]
x = torch.matmul(self.dropout(attention), V)
#x = [batch size, n heads, query len, head dim]
x = x.permute(0, 2, 1, 3).contiguous()
#x = [batch size, query len, n heads, head dim]
x = x.view(batch_size, -1, self.hid_dim)
#x = [batch size, query len, hid dim]
x = self.fc_o(x)
#x = [batch size, query len, hid dim]
return x, attention
# %%
class PositionwiseFeedforwardLayer(nn.Module):
def __init__(self, hid_dim, pf_dim, dropout):
super().__init__()
self.fc_1 = nn.Linear(hid_dim, pf_dim)
self.fc_2 = nn.Linear(pf_dim, hid_dim)
self.dropout = nn.Dropout(dropout)
def forward(self, x):
#x = [batch size, seq len, hid dim]
x = self.dropout(torch.relu(self.fc_1(x)))
#x = [batch size, seq len, pf dim]
x = self.fc_2(x)
#x = [batch size, seq len, hid dim]
return x
# %%
class Decoder(nn.Module):
def __init__(self,
output_dim,
hid_dim,
n_layers,
n_heads,
pf_dim,
dropout,
device,
max_length = 100):
super().__init__()
self.device = device
self.tok_embedding = nn.Embedding(output_dim, hid_dim)
self.pos_embedding = nn.Embedding(max_length, hid_dim)
self.layers = nn.ModuleList([DecoderLayer(hid_dim,
n_heads,
pf_dim,
dropout,
device)
for _ in range(n_layers)])
self.fc_out = nn.Linear(hid_dim, output_dim)
self.dropout = nn.Dropout(dropout)
self.scale = torch.sqrt(torch.FloatTensor([hid_dim])).to(device)
def forward(self, trg, enc_src, trg_mask, src_mask):
#trg = [batch size, trg len]
#enc_src = [batch size, src len, hid dim]
#trg_mask = [batch size, trg len]
#src_mask = [batch size, src len]
batch_size = trg.shape[0]
trg_len = trg.shape[1]
pos = torch.arange(0, trg_len).unsqueeze(0).repeat(batch_size, 1).to(self.device)
#pos = [batch size, trg len]
trg = self.dropout((self.tok_embedding(trg) * self.scale) + self.pos_embedding(pos))
#trg = [batch size, trg len, hid dim]
for layer in self.layers:
trg, attention = layer(trg, enc_src, trg_mask, src_mask)
#trg = [batch size, trg len, hid dim]
#attention = [batch size, n heads, trg len, src len]
output = self.fc_out(trg)
#output = [batch size, trg len, output dim]
return output, attention
# %%
class DecoderLayer(nn.Module):
def __init__(self,
hid_dim,
n_heads,
pf_dim,
dropout,
device):
super().__init__()
self.self_attn_layer_norm = nn.LayerNorm(hid_dim)
self.enc_attn_layer_norm = nn.LayerNorm(hid_dim)
self.ff_layer_norm = nn.LayerNorm(hid_dim)
self.self_attention = MultiHeadAttentionLayer(hid_dim, n_heads, dropout, device)
self.encoder_attention = MultiHeadAttentionLayer(hid_dim, n_heads, dropout, device)
self.positionwise_feedforward = PositionwiseFeedforwardLayer(hid_dim,
pf_dim,
dropout)
self.dropout = nn.Dropout(dropout)
def forward(self, trg, enc_src, trg_mask, src_mask):
#trg = [batch size, trg len, hid dim]
#enc_src = [batch size, src len, hid dim]
#trg_mask = [batch size, trg len]
#src_mask = [batch size, src len]
#self attention
_trg, _ = self.self_attention(trg, trg, trg, trg_mask)
#dropout, residual connection and layer norm
trg = self.self_attn_layer_norm(trg + self.dropout(_trg))
#trg = [batch size, trg len, hid dim]
#encoder attention
_trg, attention = self.encoder_attention(trg, enc_src, enc_src, src_mask)
#dropout, residual connection and layer norm
trg = self.enc_attn_layer_norm(trg + self.dropout(_trg))
#trg = [batch size, trg len, hid dim]
#positionwise feedforward
_trg = self.positionwise_feedforward(trg)
#dropout, residual and layer norm
trg = self.ff_layer_norm(trg + self.dropout(_trg))
#trg = [batch size, trg len, hid dim]
#attention = [batch size, n heads, trg len, src len]
return trg, attention
# %% [markdown]
# ### Seq2Seq
#
# %%
class Seq2Seq(nn.Module):
def __init__(self,
encoder,
decoder,
src_pad_idx,
trg_pad_idx,
device):
super().__init__()
self.encoder = encoder
self.decoder = decoder
self.src_pad_idx = src_pad_idx
self.trg_pad_idx = trg_pad_idx
self.device = device
def make_src_mask(self, src):
#src = [batch size, src len]
src_mask = (src != self.src_pad_idx).unsqueeze(1).unsqueeze(2)
#src_mask = [batch size, 1, 1, src len]
return src_mask
def make_trg_mask(self, trg):
#trg = [batch size, trg len]
trg_pad_mask = (trg != self.trg_pad_idx).unsqueeze(1).unsqueeze(2)
#trg_pad_mask = [batch size, 1, 1, trg len]
trg_len = trg.shape[1]
trg_sub_mask = torch.tril(torch.ones((trg_len, trg_len), device = self.device)).bool()
#trg_sub_mask = [trg len, trg len]
trg_mask = trg_pad_mask & trg_sub_mask
#trg_mask = [batch size, 1, trg len, trg len]
return trg_mask
def forward(self, src, trg):
#src = [batch size, src len]
#trg = [batch size, trg len]
src_mask = self.make_src_mask(src)
trg_mask = self.make_trg_mask(trg)
#src_mask = [batch size, 1, 1, src len]
#trg_mask = [batch size, 1, trg len, trg len]
enc_src = self.encoder(src, src_mask)
#enc_src = [batch size, src len, hid dim]
output, attention = self.decoder(trg, enc_src, trg_mask, src_mask)
#output = [batch size, trg len, output dim]
#attention = [batch size, n heads, trg len, src len]
return output, attention
def evaluate(model, iterator, criterion):
model.eval()
epoch_loss = 0
with torch.no_grad():
for i, batch in enumerate(iterator):
src = batch.src
trg = batch.trg
output, _ = model(src, trg[:,:-1])
#output = [batch size, trg len - 1, output dim]
#trg = [batch size, trg len]
output_dim = output.shape[-1]
output = output.contiguous().view(-1, output_dim)
trg = trg[:,1:].contiguous().view(-1)
#output = [batch size * trg len - 1, output dim]
#trg = [batch size * trg len - 1]
loss = criterion(output, trg)
epoch_loss += loss.item()
return epoch_loss / len(iterator)
# %%
def instantiate_objects(SRC,TRG, vocab_size=vocab_size):
INPUT_DIM = vocab_size
OUTPUT_DIM = vocab_size
# hidden_dim was 256 before
HID_DIM = 256
ENC_LAYERS = 3
DEC_LAYERS = 3
ENC_HEADS = 8
DEC_HEADS = 8
ENC_PF_DIM = 512
DEC_PF_DIM = 512
ENC_DROPOUT = 0.1
DEC_DROPOUT = 0.1
enc = Encoder(INPUT_DIM,
HID_DIM,
ENC_LAYERS,
ENC_HEADS,
ENC_PF_DIM,
ENC_DROPOUT,
device)
dec = Decoder(OUTPUT_DIM,
HID_DIM,
DEC_LAYERS,
DEC_HEADS,
DEC_PF_DIM,
DEC_DROPOUT,
device)
return enc, dec
# %%
device = torch.device("cpu")
# %%
def translate_sentence(sentence, src_field, trg_field, model, device, max_len = 50):
model.eval()
if isinstance(sentence, str):
tokens = sp_deu.encode(sentence)
else:
tokens = [token for token in sentence]
if tokens[0] != src_field.init_token and tokens[-1] != src_field.eos_token:
tokens = [src_field.init_token] + tokens + [src_field.eos_token]
src_indexes = tokens
src_tensor = torch.LongTensor(src_indexes).unsqueeze(0).to(device)
src_mask = model.make_src_mask(src_tensor)
with torch.no_grad():
enc_src = model.encoder(src_tensor, src_mask)
trg_indexes = [trg_field.init_token]
for i in range(max_len):
trg_tensor = torch.LongTensor(trg_indexes).unsqueeze(0).to(device)
trg_mask = model.make_trg_mask(trg_tensor)
with torch.no_grad():
output, attention = model.decoder(trg_tensor, enc_src, trg_mask, src_mask)
pred_token = output.argmax(2)[:,-1].item()
trg_indexes.append(pred_token)
if pred_token == trg_field.eos_token:
break
trg_tokens = sp_nds.decode(trg_indexes)
return trg_tokens
# %%
enc , dec = instantiate_objects(SRC,TRG)
SRC_PAD_IDX = SRC.pad_token
TRG_PAD_IDX = TRG.pad_token
model = Seq2Seq(enc, dec, SRC_PAD_IDX, TRG_PAD_IDX, device).to(device)
criterion = nn.CrossEntropyLoss(ignore_index = TRG_PAD_IDX)
model.load_state_dict(torch.load(path / 'model.pt', map_location=torch.device(device)))
def translate_to_platt(input_string):
translation = translate_sentence(input_string, SRC, TRG, model, device)
#translation = ''.join(translation[:-1]).replace('▁', ' ')
return translation
# %%
import pandas as pd
untranslated = pd.read_csv("preprocessed_data/tatoeba/untranslated_sentences.csv", index_col = 0)
untranslated = untranslated[["deu"]]
def get_length(df):
df_output = df.copy()
# split by a simple tokenizer which uses regex and return the length of tokens
df_output.deu = df_output.deu.str.split(r"[\s.,;:?!-\"\']+")
return df_output.applymap(len)
def get_range(df, start, end):
df_length = get_length(df)
df_length = df_length[df_length.deu.ge(start) & df_length.deu.le(end)]
return df.loc[df_length.index,:]
untranslated = get_range(untranslated,1,30)
#%%
sentence = untranslated["deu"].sample().item()
print(sentence)
print(translate_to_platt(sentence))
# %%
ai_comparison = False
if ai_comparison:
ai_translation = untranslated[["deu"]].sample(50, random_state=42)
ai_translation["ai_nds"] = untranslated["deu"].sample(50, random_state=42).apply(translate_to_platt)
ai_translation.to_csv("preprocessed_data/tatoeba/ai_translations_model_pre_training_en_sentencepiece.csv")
# %%
# %%
#sentence = "Ich habe während der Mittagspause ein wenig geschlafen, weil ich so müde war."
sentence = "Nachdem wir die Erdbeeren gepflückt haben, backen wir einen leckeren Kuchen."
#sentence = "Das Wetter wird übermorgen sehr schön."
sentence = "Mein Handy muss aufgeladen werden."
translate_to_platt(sp_deu.encode(sentence))
# %%
if __name__ == "__main__":
print(translate_to_platt(INPUT))