File size: 8,576 Bytes
63858e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION.  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.
""" GLUE processors and helpers """

import logging
import os

from transformers.file_utils import is_tf_available
from utils_hans import DataProcessor, InputExample, InputFeatures


if is_tf_available():
    import tensorflow as tf

logger = logging.getLogger(__name__)


def hans_convert_examples_to_features(
    examples,
    tokenizer,
    max_length=512,
    task=None,
    label_list=None,
    output_mode=None,
    pad_on_left=False,
    pad_token=0,
    pad_token_segment_id=0,
    mask_padding_with_zero=True,
):
    """
    Loads a data file into a list of ``InputFeatures``

    Args:
        examples: List of ``InputExamples`` or ``tf.data.Dataset`` containing the examples.
        tokenizer: Instance of a tokenizer that will tokenize the examples
        max_length: Maximum example length
        task: HANS
        label_list: List of labels. Can be obtained from the processor using the ``processor.get_labels()`` method
        output_mode: String indicating the output mode. Either ``regression`` or ``classification``
        pad_on_left: If set to ``True``, the examples will be padded on the left rather than on the right (default)
        pad_token: Padding token
        pad_token_segment_id: The segment ID for the padding token (It is usually 0, but can vary such as for XLNet where it is 4)
        mask_padding_with_zero: If set to ``True``, the attention mask will be filled by ``1`` for actual values
            and by ``0`` for padded values. If set to ``False``, inverts it (``1`` for padded values, ``0`` for
            actual values)

    Returns:
        If the ``examples`` input is a ``tf.data.Dataset``, will return a ``tf.data.Dataset``
        containing the task-specific features. If the input is a list of ``InputExamples``, will return
        a list of task-specific ``InputFeatures`` which can be fed to the model.

    """
    is_tf_dataset = False
    if is_tf_available() and isinstance(examples, tf.data.Dataset):
        is_tf_dataset = True

    if task is not None:
        processor = glue_processors[task]()
        if label_list is None:
            label_list = processor.get_labels()
            logger.info("Using label list %s for task %s" % (label_list, task))
        if output_mode is None:
            output_mode = glue_output_modes[task]
            logger.info("Using output mode %s for task %s" % (output_mode, task))

    label_map = {label: i for i, label in enumerate(label_list)}

    features = []
    for (ex_index, example) in enumerate(examples):
        if ex_index % 10000 == 0:
            logger.info("Writing example %d" % (ex_index))
        if is_tf_dataset:
            example = processor.get_example_from_tensor_dict(example)
            example = processor.tfds_map(example)

        inputs = tokenizer.encode_plus(example.text_a, example.text_b, add_special_tokens=True, max_length=max_length,)
        input_ids, token_type_ids = inputs["input_ids"], inputs["token_type_ids"]

        # The mask has 1 for real tokens and 0 for padding tokens. Only real
        # tokens are attended to.
        attention_mask = [1 if mask_padding_with_zero else 0] * len(input_ids)

        # Zero-pad up to the sequence length.
        padding_length = max_length - len(input_ids)
        if pad_on_left:
            input_ids = ([pad_token] * padding_length) + input_ids
            attention_mask = ([0 if mask_padding_with_zero else 1] * padding_length) + attention_mask
            token_type_ids = ([pad_token_segment_id] * padding_length) + token_type_ids
        else:
            input_ids = input_ids + ([pad_token] * padding_length)
            attention_mask = attention_mask + ([0 if mask_padding_with_zero else 1] * padding_length)
            token_type_ids = token_type_ids + ([pad_token_segment_id] * padding_length)

        assert len(input_ids) == max_length, "Error with input length {} vs {}".format(len(input_ids), max_length)
        assert len(attention_mask) == max_length, "Error with input length {} vs {}".format(
            len(attention_mask), max_length
        )
        assert len(token_type_ids) == max_length, "Error with input length {} vs {}".format(
            len(token_type_ids), max_length
        )

        if output_mode == "classification":
            label = label_map[example.label] if example.label in label_map else 0
        elif output_mode == "regression":
            label = float(example.label)
        else:
            raise KeyError(output_mode)
        pairID = str(example.pairID)

        if ex_index < 10:
            logger.info("*** Example ***")
            logger.info("text_a: %s" % (example.text_a))
            logger.info("text_b: %s" % (example.text_b))
            logger.info("guid: %s" % (example.guid))
            logger.info("input_ids: %s" % " ".join([str(x) for x in input_ids]))
            logger.info("attention_mask: %s" % " ".join([str(x) for x in attention_mask]))
            logger.info("token_type_ids: %s" % " ".join([str(x) for x in token_type_ids]))
            logger.info("label: %s (id = %d)" % (example.label, label))

        features.append(
            InputFeatures(
                input_ids=input_ids,
                attention_mask=attention_mask,
                token_type_ids=token_type_ids,
                label=label,
                pairID=pairID,
            )
        )

    if is_tf_available() and is_tf_dataset:

        def gen():
            for ex in features:
                yield (
                    {
                        "input_ids": ex.input_ids,
                        "attention_mask": ex.attention_mask,
                        "token_type_ids": ex.token_type_ids,
                    },
                    ex.label,
                )

        return tf.data.Dataset.from_generator(
            gen,
            ({"input_ids": tf.int32, "attention_mask": tf.int32, "token_type_ids": tf.int32}, tf.int64),
            (
                {
                    "input_ids": tf.TensorShape([None]),
                    "attention_mask": tf.TensorShape([None]),
                    "token_type_ids": tf.TensorShape([None]),
                },
                tf.TensorShape([]),
            ),
        )

    return features


class HansProcessor(DataProcessor):
    """Processor for the HANS data set."""

    def get_example_from_tensor_dict(self, tensor_dict):
        """See base class."""
        return InputExample(
            tensor_dict["idx"].numpy(),
            tensor_dict["premise"].numpy().decode("utf-8"),
            tensor_dict["hypothesis"].numpy().decode("utf-8"),
            str(tensor_dict["label"].numpy()),
        )

    def get_train_examples(self, data_dir):
        """See base class."""
        return self._create_examples(self._read_tsv(os.path.join(data_dir, "heuristics_train_set.txt")), "train")

    def get_dev_examples(self, data_dir):
        """See base class."""
        return self._create_examples(self._read_tsv(os.path.join(data_dir, "heuristics_evaluation_set.txt")), "dev")

    def get_labels(self):
        """See base class."""
        return ["contradiction", "entailment", "neutral"]

    def _create_examples(self, lines, set_type):
        """Creates examples for the training and dev sets."""
        examples = []
        for (i, line) in enumerate(lines):
            if i == 0:
                continue
            guid = "%s-%s" % (set_type, line[0])
            text_a = line[5]
            text_b = line[6]
            pairID = line[7][2:] if line[7].startswith("ex") else line[7]
            label = line[-1]
            examples.append(InputExample(guid=guid, text_a=text_a, text_b=text_b, label=label, pairID=pairID))
        return examples


glue_tasks_num_labels = {
    "hans": 3,
}

glue_processors = {
    "hans": HansProcessor,
}

glue_output_modes = {
    "hans": "classification",
}