You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.

process_output.sh 1.6 kB

1234567891011121314151617181920212223242526272829303132333435
  1. #!/bin/bash
  2. # Copyright 2020 Huawei Technologies Co., Ltd
  3. #
  4. # Licensed under the Apache License, Version 2.0 (the "License");
  5. # you may not use this file except in compliance with the License.
  6. # You may obtain a copy of the License at
  7. #
  8. # http://www.apache.org/licenses/LICENSE-2.0
  9. #
  10. # Unless required by applicable law or agreed to in writing, software
  11. # distributed under the License is distributed on an "AS IS" BASIS,
  12. # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  13. # See the License for the specific language governing permissions and
  14. # limitations under the License.
  15. # ============================================================================
  16. echo "=============================================================================================================="
  17. echo "Please run the scipt as: "
  18. echo "sh process_output.sh REF_DATA EVAL_OUTPUT VOCAB_FILE"
  19. echo "for example: sh process_output.sh /path/newstest2014.tok.de /path/eval_output_file /path/vocab.bpe.32000"
  20. echo "It is better to use absolute path."
  21. echo "=============================================================================================================="
  22. BASEDIR=$(dirname "$0")
  23. ref_data=$1
  24. eval_output=$2
  25. vocab_file=$3
  26. cat $eval_output \
  27. | python src/process_output.py --vocab_file $vocab_file \
  28. | sed 's/@@ //g' > ${eval_output}.processed
  29. perl -ple 's/(\S)-(\S)/$1 #@#-#@# $2/g' < $ref_data | perl ${BASEDIR}/replace-quote.perl > ${ref_data}.forbleu
  30. perl -ple 's/(\S)-(\S)/$1 #@#-#@# $2/g' < ${eval_output}.processed > ${eval_output}.forbleu