am e382bcc3: am 8f9f55dd: Merge "Fix a bug where the bigram freq would be underevaluated" into jb-dev
* commit 'e382bcc39aa6aa64504a0fcd2ca59ad09dda0d25': Fix a bug where the bigram freq would be underevaluatedmain
commit
14c72f071e
|
@ -537,7 +537,7 @@ inline int BinaryFormat::computeFrequencyForBigram(const int unigramFreq, const
|
||||||
// while a value of 15 represents the middle of the top step.
|
// while a value of 15 represents the middle of the top step.
|
||||||
// See makedict.BinaryDictInputOutput for details.
|
// See makedict.BinaryDictInputOutput for details.
|
||||||
const float stepSize = ((float)MAX_FREQ - unigramFreq) / (1.5f + MAX_BIGRAM_FREQ);
|
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.
|
// This returns a probability in log space.
|
||||||
|
|
Loading…
Reference in New Issue