aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJean Chalard <jchalard@google.com>2012-05-29 00:57:34 -0700
committerAndroid (Google) Code Review <android-gerrit@google.com>2012-05-29 00:57:34 -0700
commitb074dfead504fba4039e4eaaded07c10244ff292 (patch)
tree553277fce422bde6f5ab1686b54c16696dcdc0ef
parentbfba64bcfd70ce8e3932d52c4b9f3182d33e1f55 (diff)
parent46fe49fc05df02228222b8a8e49d4cc8e1f0ea3c (diff)
downloadlatinime-b074dfead504fba4039e4eaaded07c10244ff292.tar.gz
latinime-b074dfead504fba4039e4eaaded07c10244ff292.tar.xz
latinime-b074dfead504fba4039e4eaaded07c10244ff292.zip
Merge "Add a comment on a caveat for future reference." into jb-dev
-rw-r--r--native/jni/src/bigram_dictionary.cpp5
1 files changed, 5 insertions, 0 deletions
diff --git a/native/jni/src/bigram_dictionary.cpp b/native/jni/src/bigram_dictionary.cpp
index 8d0c8597f..eb4bf8d1a 100644
--- a/native/jni/src/bigram_dictionary.cpp
+++ b/native/jni/src/bigram_dictionary.cpp
@@ -126,6 +126,11 @@ int BigramDictionary::getBigrams(const int32_t *prevWord, int prevWordLength, in
// codesSize == 0 means we are trying to find bigram predictions.
if (codesSize < 1 || checkFirstCharacter(bigramBuffer)) {
const int bigramFreq = UnigramDictionary::MASK_ATTRIBUTE_FREQUENCY & bigramFlags;
+ // Due to space constraints, the frequency for bigrams is approximate - the lower the
+ // unigram frequency, the worse the precision. The theoritical maximum error in
+ // resulting frequency is 8 - although in the practice it's never bigger than 3 or 4
+ // in very bad cases. This means that sometimes, we'll see some bigrams interverted
+ // here, but it can't get too bad.
const int frequency =
BinaryFormat::computeFrequencyForBigram(unigramFreq, bigramFreq);
if (addWordBigram(bigramBuffer, length, frequency)) {