1 files changed, 11 insertions, 3 deletions
diff --git a/native/jni/src/bigram_dictionary.cpp b/native/jni/src/bigram_dictionary.cpp
index ac2a26172..eb4bf8d1a 100644
--- a/native/jni/src/bigram_dictionary.cpp
+++ b/native/jni/src/bigram_dictionary.cpp
@@ -117,14 +117,22 @@ int BigramDictionary::getBigrams(const int32_t *prevWord, int prevWordLength, in
     do {
         bigramFlags = BinaryFormat::getFlagsAndForwardPointer(root, &pos);
         uint16_t bigramBuffer[MAX_WORD_LENGTH];
+        int unigramFreq;
         const int bigramPos = BinaryFormat::getAttributeAddressAndForwardPointer(root, bigramFlags,
                 &pos);
         const int length = BinaryFormat::getWordAtAddress(root, bigramPos, MAX_WORD_LENGTH,
-                bigramBuffer);
+                bigramBuffer, &unigramFreq);
 
         // codesSize == 0 means we are trying to find bigram predictions.
         if (codesSize < 1 || checkFirstCharacter(bigramBuffer)) {
-            const int frequency = UnigramDictionary::MASK_ATTRIBUTE_FREQUENCY & bigramFlags;
+            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)) {
                 ++bigramCount;
             }
@@ -149,8 +157,8 @@ int BigramDictionary::getBigramListPositionForWord(const int32_t *prevWord,
     } else {
         pos = BinaryFormat::skipOtherCharacters(root, pos);
     }
-    pos = BinaryFormat::skipChildrenPosition(flags, pos);
     pos = BinaryFormat::skipFrequency(flags, pos);
+    pos = BinaryFormat::skipChildrenPosition(flags, pos);
     pos = BinaryFormat::skipShortcuts(root, flags, pos);
     return pos;
 }