Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
test_tokenization_xlm_prophetnet.py 4.02 KB
Newer Older
Weizhen's avatar
ProphetNet (#7157)  
Weizhen committed
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 
# coding=utf-8
# Copyright 2020 The HuggingFace Inc. team, The Microsoft Research team.
#
# 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 unittest

from transformers.file_utils import cached_property
from transformers.testing_utils import slow
from transformers.tokenization_xlm_prophetnet import SPIECE_UNDERLINE, XLMProphetNetTokenizer

from .test_tokenization_common import TokenizerTesterMixin


SAMPLE_VOCAB = os.path.join(os.path.dirname(os.path.abspath(__file__)), "fixtures/test_sentencepiece.model")


class XLMProphetNetTokenizationTest(TokenizerTesterMixin, unittest.TestCase):

    tokenizer_class = XLMProphetNetTokenizer
    test_rust_tokenizer = False

    def setUp(self):
        super().setUp()

        # We have a SentencePiece fixture for testing
        tokenizer = XLMProphetNetTokenizer(SAMPLE_VOCAB, keep_accents=True)
        tokenizer.save_pretrained(self.tmpdirname)

    def test_full_tokenizer(self):
        tokenizer = XLMProphetNetTokenizer(SAMPLE_VOCAB, keep_accents=True)

        tokens = tokenizer.tokenize("This is a test")
        self.assertListEqual(tokens, ["鈻乀his", "鈻乮s", "鈻乤", "鈻乼", "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 fals茅.")
        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",
                "茅",
                ".",
            ],
        )
        ids = tokenizer.convert_tokens_to_ids(tokens)
        self.assertListEqual(
            ids,
            [
                value + tokenizer.fairseq_offset
                for value in [8, 21, 84, 55, 24, 19, 7, -9, 602, 347, 347, 347, 3, 12, 66, 46, 72, 80, 6, -9, 4]
            ],
        )

        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]",
                ".",
            ],
        )

    @cached_property
    def big_tokenizer(self):
        return XLMProphetNetTokenizer.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")

    @slow
    def test_tokenization_base_easy_symbols(self):
        symbols = "Hello World!"
        original_tokenizer_encodings = [35389, 6672, 49, 2]
        self.assertListEqual(original_tokenizer_encodings, self.big_tokenizer.encode(symbols))