File size: 14,157 Bytes
650c5f6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#!/usr/bin/env python3 -u
# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

"""
Generate n-best translations using a trained model.
"""

import os
import subprocess
from contextlib import redirect_stdout

from fairseq import options
from fairseq_cli import generate, preprocess

from examples.noisychannel import rerank_options, rerank_utils


def gen_and_reprocess_nbest(args):
    if args.score_dict_dir is None:
        args.score_dict_dir = args.data
    if args.prefix_len is not None:
        assert (
            args.right_to_left1 is False
        ), "prefix length not compatible with right to left models"
        assert (
            args.right_to_left2 is False
        ), "prefix length not compatible with right to left models"

    if args.nbest_list is not None:
        assert args.score_model2 is None

    if args.backwards1:
        scorer1_src = args.target_lang
        scorer1_tgt = args.source_lang
    else:
        scorer1_src = args.source_lang
        scorer1_tgt = args.target_lang

    store_data = (
        os.path.join(os.path.dirname(__file__)) + "/rerank_data/" + args.data_dir_name
    )
    if not os.path.exists(store_data):
        os.makedirs(store_data)

    (
        pre_gen,
        left_to_right_preprocessed_dir,
        right_to_left_preprocessed_dir,
        backwards_preprocessed_dir,
        lm_preprocessed_dir,
    ) = rerank_utils.get_directories(
        args.data_dir_name,
        args.num_rescore,
        args.gen_subset,
        args.gen_model_name,
        args.shard_id,
        args.num_shards,
        args.sampling,
        args.prefix_len,
        args.target_prefix_frac,
        args.source_prefix_frac,
    )
    assert not (
        args.right_to_left1 and args.backwards1
    ), "backwards right to left not supported"
    assert not (
        args.right_to_left2 and args.backwards2
    ), "backwards right to left not supported"
    assert not (
        args.prefix_len is not None and args.target_prefix_frac is not None
    ), "target prefix frac and target prefix len incompatible"

    # make directory to store generation results
    if not os.path.exists(pre_gen):
        os.makedirs(pre_gen)

    rerank1_is_gen = (
        args.gen_model == args.score_model1 and args.source_prefix_frac is None
    )
    rerank2_is_gen = (
        args.gen_model == args.score_model2 and args.source_prefix_frac is None
    )

    if args.nbest_list is not None:
        rerank2_is_gen = True

    # make directories to store preprossed nbest list for reranking
    if not os.path.exists(left_to_right_preprocessed_dir):
        os.makedirs(left_to_right_preprocessed_dir)
    if not os.path.exists(right_to_left_preprocessed_dir):
        os.makedirs(right_to_left_preprocessed_dir)
    if not os.path.exists(lm_preprocessed_dir):
        os.makedirs(lm_preprocessed_dir)
    if not os.path.exists(backwards_preprocessed_dir):
        os.makedirs(backwards_preprocessed_dir)

    score1_file = rerank_utils.rescore_file_name(
        pre_gen,
        args.prefix_len,
        args.model1_name,
        target_prefix_frac=args.target_prefix_frac,
        source_prefix_frac=args.source_prefix_frac,
        backwards=args.backwards1,
    )
    if args.score_model2 is not None:
        score2_file = rerank_utils.rescore_file_name(
            pre_gen,
            args.prefix_len,
            args.model2_name,
            target_prefix_frac=args.target_prefix_frac,
            source_prefix_frac=args.source_prefix_frac,
            backwards=args.backwards2,
        )

    predictions_bpe_file = pre_gen + "/generate_output_bpe.txt"

    using_nbest = args.nbest_list is not None

    if using_nbest:
        print("Using predefined n-best list from interactive.py")
        predictions_bpe_file = args.nbest_list

    else:
        if not os.path.isfile(predictions_bpe_file):
            print("STEP 1: generate predictions using the p(T|S) model with bpe")
            print(args.data)
            param1 = [
                args.data,
                "--path",
                args.gen_model,
                "--shard-id",
                str(args.shard_id),
                "--num-shards",
                str(args.num_shards),
                "--nbest",
                str(args.num_rescore),
                "--batch-size",
                str(args.batch_size),
                "--beam",
                str(args.num_rescore),
                "--batch-size",
                str(args.num_rescore),
                "--gen-subset",
                args.gen_subset,
                "--source-lang",
                args.source_lang,
                "--target-lang",
                args.target_lang,
            ]
            if args.sampling:
                param1 += ["--sampling"]

            gen_parser = options.get_generation_parser()
            input_args = options.parse_args_and_arch(gen_parser, param1)

            print(input_args)
            with open(predictions_bpe_file, "w") as f:
                with redirect_stdout(f):
                    generate.main(input_args)

    gen_output = rerank_utils.BitextOutputFromGen(
        predictions_bpe_file,
        bpe_symbol=args.post_process,
        nbest=using_nbest,
        prefix_len=args.prefix_len,
        target_prefix_frac=args.target_prefix_frac,
    )

    if args.diff_bpe:
        rerank_utils.write_reprocessed(
            gen_output.no_bpe_source,
            gen_output.no_bpe_hypo,
            gen_output.no_bpe_target,
            pre_gen + "/source_gen_bpe." + args.source_lang,
            pre_gen + "/target_gen_bpe." + args.target_lang,
            pre_gen + "/reference_gen_bpe." + args.target_lang,
        )
        bitext_bpe = args.rescore_bpe_code
        bpe_src_param = [
            "-c",
            bitext_bpe,
            "--input",
            pre_gen + "/source_gen_bpe." + args.source_lang,
            "--output",
            pre_gen + "/rescore_data." + args.source_lang,
        ]
        bpe_tgt_param = [
            "-c",
            bitext_bpe,
            "--input",
            pre_gen + "/target_gen_bpe." + args.target_lang,
            "--output",
            pre_gen + "/rescore_data." + args.target_lang,
        ]

        subprocess.call(
            [
                "python",
                os.path.join(
                    os.path.dirname(__file__), "subword-nmt/subword_nmt/apply_bpe.py"
                ),
            ]
            + bpe_src_param,
            shell=False,
        )

        subprocess.call(
            [
                "python",
                os.path.join(
                    os.path.dirname(__file__), "subword-nmt/subword_nmt/apply_bpe.py"
                ),
            ]
            + bpe_tgt_param,
            shell=False,
        )

    if (not os.path.isfile(score1_file) and not rerank1_is_gen) or (
        args.score_model2 is not None
        and not os.path.isfile(score2_file)
        and not rerank2_is_gen
    ):
        print(
            "STEP 2: process the output of generate.py so we have clean text files with the translations"
        )

        rescore_file = "/rescore_data"
        if args.prefix_len is not None:
            prefix_len_rescore_file = rescore_file + "prefix" + str(args.prefix_len)
        if args.target_prefix_frac is not None:
            target_prefix_frac_rescore_file = (
                rescore_file + "target_prefix_frac" + str(args.target_prefix_frac)
            )
        if args.source_prefix_frac is not None:
            source_prefix_frac_rescore_file = (
                rescore_file + "source_prefix_frac" + str(args.source_prefix_frac)
            )

        if not args.right_to_left1 or not args.right_to_left2:
            if not args.diff_bpe:
                rerank_utils.write_reprocessed(
                    gen_output.source,
                    gen_output.hypo,
                    gen_output.target,
                    pre_gen + rescore_file + "." + args.source_lang,
                    pre_gen + rescore_file + "." + args.target_lang,
                    pre_gen + "/reference_file",
                    bpe_symbol=args.post_process,
                )
                if args.prefix_len is not None:
                    bw_rescore_file = prefix_len_rescore_file
                    rerank_utils.write_reprocessed(
                        gen_output.source,
                        gen_output.hypo,
                        gen_output.target,
                        pre_gen + prefix_len_rescore_file + "." + args.source_lang,
                        pre_gen + prefix_len_rescore_file + "." + args.target_lang,
                        pre_gen + "/reference_file",
                        prefix_len=args.prefix_len,
                        bpe_symbol=args.post_process,
                    )
                elif args.target_prefix_frac is not None:
                    bw_rescore_file = target_prefix_frac_rescore_file
                    rerank_utils.write_reprocessed(
                        gen_output.source,
                        gen_output.hypo,
                        gen_output.target,
                        pre_gen
                        + target_prefix_frac_rescore_file
                        + "."
                        + args.source_lang,
                        pre_gen
                        + target_prefix_frac_rescore_file
                        + "."
                        + args.target_lang,
                        pre_gen + "/reference_file",
                        bpe_symbol=args.post_process,
                        target_prefix_frac=args.target_prefix_frac,
                    )
                else:
                    bw_rescore_file = rescore_file

                if args.source_prefix_frac is not None:
                    fw_rescore_file = source_prefix_frac_rescore_file
                    rerank_utils.write_reprocessed(
                        gen_output.source,
                        gen_output.hypo,
                        gen_output.target,
                        pre_gen
                        + source_prefix_frac_rescore_file
                        + "."
                        + args.source_lang,
                        pre_gen
                        + source_prefix_frac_rescore_file
                        + "."
                        + args.target_lang,
                        pre_gen + "/reference_file",
                        bpe_symbol=args.post_process,
                        source_prefix_frac=args.source_prefix_frac,
                    )
                else:
                    fw_rescore_file = rescore_file

        if args.right_to_left1 or args.right_to_left2:
            rerank_utils.write_reprocessed(
                gen_output.source,
                gen_output.hypo,
                gen_output.target,
                pre_gen + "/right_to_left_rescore_data." + args.source_lang,
                pre_gen + "/right_to_left_rescore_data." + args.target_lang,
                pre_gen + "/right_to_left_reference_file",
                right_to_left=True,
                bpe_symbol=args.post_process,
            )

        print("STEP 3: binarize the translations")
        if (
            not args.right_to_left1
            or args.score_model2 is not None
            and not args.right_to_left2
            or not rerank1_is_gen
        ):

            if args.backwards1 or args.backwards2:
                if args.backwards_score_dict_dir is not None:
                    bw_dict = args.backwards_score_dict_dir
                else:
                    bw_dict = args.score_dict_dir
                bw_preprocess_param = [
                    "--source-lang",
                    scorer1_src,
                    "--target-lang",
                    scorer1_tgt,
                    "--trainpref",
                    pre_gen + bw_rescore_file,
                    "--srcdict",
                    bw_dict + "/dict." + scorer1_src + ".txt",
                    "--tgtdict",
                    bw_dict + "/dict." + scorer1_tgt + ".txt",
                    "--destdir",
                    backwards_preprocessed_dir,
                ]
                preprocess_parser = options.get_preprocessing_parser()
                input_args = preprocess_parser.parse_args(bw_preprocess_param)
                preprocess.main(input_args)

            preprocess_param = [
                "--source-lang",
                scorer1_src,
                "--target-lang",
                scorer1_tgt,
                "--trainpref",
                pre_gen + fw_rescore_file,
                "--srcdict",
                args.score_dict_dir + "/dict." + scorer1_src + ".txt",
                "--tgtdict",
                args.score_dict_dir + "/dict." + scorer1_tgt + ".txt",
                "--destdir",
                left_to_right_preprocessed_dir,
            ]
            preprocess_parser = options.get_preprocessing_parser()
            input_args = preprocess_parser.parse_args(preprocess_param)
            preprocess.main(input_args)

        if args.right_to_left1 or args.right_to_left2:
            preprocess_param = [
                "--source-lang",
                scorer1_src,
                "--target-lang",
                scorer1_tgt,
                "--trainpref",
                pre_gen + "/right_to_left_rescore_data",
                "--srcdict",
                args.score_dict_dir + "/dict." + scorer1_src + ".txt",
                "--tgtdict",
                args.score_dict_dir + "/dict." + scorer1_tgt + ".txt",
                "--destdir",
                right_to_left_preprocessed_dir,
            ]
            preprocess_parser = options.get_preprocessing_parser()
            input_args = preprocess_parser.parse_args(preprocess_param)
            preprocess.main(input_args)

    return gen_output


def cli_main():
    parser = rerank_options.get_reranking_parser()
    args = options.parse_args_and_arch(parser)
    gen_and_reprocess_nbest(args)


if __name__ == "__main__":
    cli_main()