-
Notifications
You must be signed in to change notification settings - Fork 28.4k
/
Copy pathtest_tokenization_mbart.py
251 lines (216 loc) · 9.99 KB
/
test_tokenization_mbart.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
# Copyright 2020 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import tempfile
import unittest
from transformers import SPIECE_UNDERLINE, BatchEncoding, MBartTokenizer, MBartTokenizerFast, is_torch_available
from transformers.testing_utils import nested_simplify, require_sentencepiece, require_tokenizers, require_torch
from .test_tokenization_common import TokenizerTesterMixin
SAMPLE_VOCAB = os.path.join(os.path.dirname(os.path.abspath(__file__)), "fixtures/test_sentencepiece.model")
if is_torch_available():
from transformers.models.mbart.modeling_mbart import shift_tokens_right
EN_CODE = 250004
RO_CODE = 250020
@require_sentencepiece
@require_tokenizers
class MBartTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
tokenizer_class = MBartTokenizer
rust_tokenizer_class = MBartTokenizerFast
test_rust_tokenizer = True
def setUp(self):
super().setUp()
# We have a SentencePiece fixture for testing
tokenizer = MBartTokenizer(SAMPLE_VOCAB, keep_accents=True)
tokenizer.save_pretrained(self.tmpdirname)
def test_full_tokenizer(self):
tokenizer = MBartTokenizer(SAMPLE_VOCAB, keep_accents=True)
tokens = tokenizer.tokenize("This is a test")
self.assertListEqual(tokens, ["▁This", "▁is", "▁a", "▁t", "est"])
self.assertListEqual(
tokenizer.convert_tokens_to_ids(tokens),
[value + tokenizer.fairseq_offset for value in [285, 46, 10, 170, 382]],
)
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
self.assertListEqual(
tokens,
[
SPIECE_UNDERLINE + "I",
SPIECE_UNDERLINE + "was",
SPIECE_UNDERLINE + "b",
"or",
"n",
SPIECE_UNDERLINE + "in",
SPIECE_UNDERLINE + "",
"9",
"2",
"0",
"0",
"0",
",",
SPIECE_UNDERLINE + "and",
SPIECE_UNDERLINE + "this",
SPIECE_UNDERLINE + "is",
SPIECE_UNDERLINE + "f",
"al",
"s",
"é",
".",
],
)
ids = tokenizer.convert_tokens_to_ids(tokens)
self.assertListEqual(
ids,
[
value + tokenizer.fairseq_offset
for value in [8, 21, 84, 55, 24, 19, 7, 2, 602, 347, 347, 347, 3, 12, 66, 46, 72, 80, 6, 2, 4]
# ^ unk: 2 + 1 = 3 unk: 2 + 1 = 3 ^
],
)
back_tokens = tokenizer.convert_ids_to_tokens(ids)
self.assertListEqual(
back_tokens,
[
SPIECE_UNDERLINE + "I",
SPIECE_UNDERLINE + "was",
SPIECE_UNDERLINE + "b",
"or",
"n",
SPIECE_UNDERLINE + "in",
SPIECE_UNDERLINE + "",
"<unk>",
"2",
"0",
"0",
"0",
",",
SPIECE_UNDERLINE + "and",
SPIECE_UNDERLINE + "this",
SPIECE_UNDERLINE + "is",
SPIECE_UNDERLINE + "f",
"al",
"s",
"<unk>",
".",
],
)
@require_torch
@require_sentencepiece
@require_tokenizers
class MBartEnroIntegrationTest(unittest.TestCase):
checkpoint_name = "facebook/mbart-large-en-ro"
src_text = [
" UN Chief Says There Is No Military Solution in Syria",
""" Secretary-General Ban Ki-moon says his response to Russia's stepped up military support for Syria is that "there is no military solution" to the nearly five-year conflict and more weapons will only worsen the violence and misery for millions of people.""",
]
tgt_text = [
"Şeful ONU declară că nu există o soluţie militară în Siria",
'Secretarul General Ban Ki-moon declară că răspunsul său la intensificarea sprijinului militar al Rusiei pentru Siria este că "nu există o soluţie militară" la conflictul de aproape cinci ani şi că noi arme nu vor face decât să înrăutăţească violenţele şi mizeria pentru milioane de oameni.',
]
expected_src_tokens = [8274, 127873, 25916, 7, 8622, 2071, 438, 67485, 53, 187895, 23, 51712, 2, EN_CODE]
@classmethod
def setUpClass(cls):
cls.tokenizer: MBartTokenizer = MBartTokenizer.from_pretrained(
cls.checkpoint_name, src_lang="en_XX", tgt_lang="ro_RO"
)
cls.pad_token_id = 1
return cls
def check_language_codes(self):
self.assertEqual(self.tokenizer.fairseq_tokens_to_ids["ar_AR"], 250001)
self.assertEqual(self.tokenizer.fairseq_tokens_to_ids["en_EN"], 250004)
self.assertEqual(self.tokenizer.fairseq_tokens_to_ids["ro_RO"], 250020)
def test_enro_tokenizer_batch_encode_plus(self):
ids = self.tokenizer.batch_encode_plus(self.src_text).input_ids[0]
self.assertListEqual(self.expected_src_tokens, ids)
def test_enro_tokenizer_decode_ignores_language_codes(self):
self.assertIn(RO_CODE, self.tokenizer.all_special_ids)
generated_ids = [RO_CODE, 884, 9019, 96, 9, 916, 86792, 36, 18743, 15596, 5, 2]
result = self.tokenizer.decode(generated_ids, skip_special_tokens=True)
expected_romanian = self.tokenizer.decode(generated_ids[1:], skip_special_tokens=True)
self.assertEqual(result, expected_romanian)
self.assertNotIn(self.tokenizer.eos_token, result)
def test_enro_tokenizer_truncation(self):
src_text = ["this is gunna be a long sentence " * 20]
assert isinstance(src_text[0], str)
desired_max_length = 10
ids = self.tokenizer(src_text, max_length=desired_max_length, truncation=True).input_ids[0]
self.assertEqual(ids[-2], 2)
self.assertEqual(ids[-1], EN_CODE)
self.assertEqual(len(ids), desired_max_length)
def test_mask_token(self):
self.assertListEqual(self.tokenizer.convert_tokens_to_ids(["<mask>", "ar_AR"]), [250026, 250001])
def test_special_tokens_unaffacted_by_save_load(self):
tmpdirname = tempfile.mkdtemp()
original_special_tokens = self.tokenizer.fairseq_tokens_to_ids
self.tokenizer.save_pretrained(tmpdirname)
new_tok = MBartTokenizer.from_pretrained(tmpdirname)
self.assertDictEqual(new_tok.fairseq_tokens_to_ids, original_special_tokens)
@require_torch
def test_batch_fairseq_parity(self):
batch = self.tokenizer(self.src_text, padding=True)
with self.tokenizer.as_target_tokenizer():
targets = self.tokenizer(self.tgt_text, padding=True, return_tensors="pt")
labels = targets["input_ids"]
batch["decoder_input_ids"] = shift_tokens_right(labels, self.tokenizer.pad_token_id).tolist()
# fairseq batch: https://gist.github.com/sshleifer/cba08bc2109361a74ac3760a7e30e4f4
assert batch.input_ids[1][-2:] == [2, EN_CODE]
assert batch.decoder_input_ids[1][0] == RO_CODE
assert batch.decoder_input_ids[1][-1] == 2
assert labels[1][-2:].tolist() == [2, RO_CODE]
@require_torch
def test_enro_tokenizer_prepare_batch(self):
batch = self.tokenizer(
self.src_text, padding=True, truncation=True, max_length=len(self.expected_src_tokens), return_tensors="pt"
)
with self.tokenizer.as_target_tokenizer():
targets = self.tokenizer(
self.tgt_text,
padding=True,
truncation=True,
max_length=len(self.expected_src_tokens),
return_tensors="pt",
)
labels = targets["input_ids"]
batch["decoder_input_ids"] = shift_tokens_right(labels, self.tokenizer.pad_token_id)
self.assertIsInstance(batch, BatchEncoding)
self.assertEqual((2, 14), batch.input_ids.shape)
self.assertEqual((2, 14), batch.attention_mask.shape)
result = batch.input_ids.tolist()[0]
self.assertListEqual(self.expected_src_tokens, result)
self.assertEqual(2, batch.decoder_input_ids[0, -1]) # EOS
# Test that special tokens are reset
self.assertEqual(self.tokenizer.prefix_tokens, [])
self.assertEqual(self.tokenizer.suffix_tokens, [self.tokenizer.eos_token_id, EN_CODE])
def test_seq2seq_max_length(self):
batch = self.tokenizer(self.src_text, padding=True, truncation=True, max_length=3, return_tensors="pt")
with self.tokenizer.as_target_tokenizer():
targets = self.tokenizer(self.tgt_text, padding=True, truncation=True, max_length=10, return_tensors="pt")
labels = targets["input_ids"]
batch["decoder_input_ids"] = shift_tokens_right(labels, self.tokenizer.pad_token_id)
self.assertEqual(batch.input_ids.shape[1], 3)
self.assertEqual(batch.decoder_input_ids.shape[1], 10)
@require_torch
def test_tokenizer_translation(self):
inputs = self.tokenizer._build_translation_inputs(
"A test", return_tensors="pt", src_lang="en_XX", tgt_lang="ar_AR"
)
self.assertEqual(
nested_simplify(inputs),
{
# A, test, EOS, en_XX
"input_ids": [[62, 3034, 2, 250004]],
"attention_mask": [[1, 1, 1, 1]],
# ar_AR
"forced_bos_token_id": 250001,
},
)