Fix a bug where the bigram freq would be underevaluated
The difference in score is not large, but it's still a bug Change-Id: Ie22c2b6e1206e829c1c8af096469df05af14d47bmain
parent
19ebd93646
commit
cb99376307
|
@ -537,7 +537,7 @@ inline int BinaryFormat::computeFrequencyForBigram(const int unigramFreq, const
|
|||
// while a value of 15 represents the middle of the top step.
|
||||
// See makedict.BinaryDictInputOutput for details.
|
||||
const float stepSize = ((float)MAX_FREQ - unigramFreq) / (1.5f + MAX_BIGRAM_FREQ);
|
||||
return (int)(unigramFreq + bigramFreq * stepSize);
|
||||
return (int)(unigramFreq + (bigramFreq + 1) * stepSize);
|
||||
}
|
||||
|
||||
// This returns a probability in log space.
|
||||
|
|
Loading…
Reference in New Issue