def bleu_wrapper(ref_filename, hyp_filename, case_sensitive=False):
"""Compute BLEU for two files (reference and hypothesis translation)."""
ref_lines = tokenizer.native_to_unicode(
tf.io.gfile.GFile(ref_filename).read()).strip().splitlines()
hyp_lines = tokenizer.native_to_unicode(
tf.io.gfile.GFile(hyp_filename).read()).strip().splitlines()
return bleu_on_list(ref_lines, hyp_lines, case_sensitive)
def bleu_wrapper(ref_filename, hyp_filename, case_sensitive=False):
"""Compute BLEU for two files (reference and hypothesis translation)."""
ref_lines = tokenizer.native_to_unicode(
tf.io.gfile.GFile(ref_filename).read()).strip().splitlines()
hyp_lines = tokenizer.native_to_unicode(
tf.io.gfile.GFile(hyp_filename).read()).strip().splitlines()
if len(ref_lines) != len(hyp_lines):
raise ValueError(
"Reference and translation files have different number of "
"lines. If training only a few steps (100-200), the "
"translation may be empty.")
if not case_sensitive:
ref_lines = [x.lower() for x in ref_lines]
hyp_lines = [x.lower() for x in hyp_lines]
ref_tokens = [bleu_tokenize(x) for x in ref_lines]
hyp_tokens = [bleu_tokenize(x) for x in hyp_lines]
return metrics.compute_bleu(ref_tokens, hyp_tokens) * 100
