diff options
author | 2013-10-03 18:15:29 -0700 | |
---|---|---|
committer | 2013-10-03 19:30:26 -0700 | |
commit | 2ed09c214afb49ffd0ce348c9a9f22ec23ae9792 (patch) | |
tree | 23ab2e0eeef0d4159d8a5dfd6047ef8560c4e677 /native/jni/src | |
parent | 9d763910580379d3e68b4559f91e655cf05f02a3 (diff) | |
download | latinime-2ed09c214afb49ffd0ce348c9a9f22ec23ae9792.tar.gz latinime-2ed09c214afb49ffd0ce348c9a9f22ec23ae9792.tar.xz latinime-2ed09c214afb49ffd0ce348c9a9f22ec23ae9792.zip |
Optimize the parameters for the typing algorithm
The new set of parameters are optimized for both
keystroke savings and regression test scores.
This change is corresponding to the patch 6 of
Change-Id: Ib8439a85de26cbbba58837344717f0acbfcf0ab0
in the regression test repository.
Here is the link to the doc analyzing the
“nnow → know” case:
https://docs.google.com/a/google.com/document/d/1XIHfAHLlP1f3F8R-u7yxPGWcP58tokygzN_lQKXFFgM/edit
Here is the link to the spreadsheet showing
the diff of the words with frequencies >= 10
in en_user_log_phones_2011_08.csv.
https://docs.google.com/a/google.com/spreadsheet/ccc?key=0Am_RQlV4zC6SdFFVTlhJT0RLUENCWWZOZ3JQTUpMQ2c&usp=drive_web#gid=0
Updated TRT Results for this change:
[Category diff]
+1 783
-1 717
+2 20
-2 34
+3 34
-3 20
+4 575
-4 777
+5 765
-5 755
+6 785
-6 666
+7 479
-7 472
[Weighted category diff]
+1 999
-1 965
+2 21
-2 35
+3 35
-3 21
+4 804
-4 980
+5 970
-5 971
+6 954
-6 831
+7 645
-7 625
Bug: 10613502
Change-Id: I5cd447673a196ad5af641a2118602bec879bdefb
Diffstat (limited to 'native/jni/src')
-rw-r--r-- | native/jni/src/suggest/policyimpl/typing/scoring_params.cpp | 48 |
1 files changed, 24 insertions, 24 deletions
diff --git a/native/jni/src/suggest/policyimpl/typing/scoring_params.cpp b/native/jni/src/suggest/policyimpl/typing/scoring_params.cpp index ecceb60d3..66637ac4b 100644 --- a/native/jni/src/suggest/policyimpl/typing/scoring_params.cpp +++ b/native/jni/src/suggest/policyimpl/typing/scoring_params.cpp @@ -27,30 +27,30 @@ const int ScoringParams::MAX_CACHE_DIC_NODE_SIZE = 170; const int ScoringParams::MAX_CACHE_DIC_NODE_SIZE_FOR_SINGLE_POINT = 310; const int ScoringParams::THRESHOLD_SHORT_WORD_LENGTH = 4; -const float ScoringParams::DISTANCE_WEIGHT_LENGTH = 0.132f; -const float ScoringParams::PROXIMITY_COST = 0.095f; -const float ScoringParams::FIRST_CHAR_PROXIMITY_COST = 0.102f; -const float ScoringParams::FIRST_PROXIMITY_COST = 0.019f; -const float ScoringParams::OMISSION_COST = 0.458f; -const float ScoringParams::OMISSION_COST_SAME_CHAR = 0.491f; -const float ScoringParams::OMISSION_COST_FIRST_CHAR = 0.582f; -const float ScoringParams::INSERTION_COST = 0.730f; -const float ScoringParams::TERMINAL_INSERTION_COST = 0.93f; -const float ScoringParams::INSERTION_COST_SAME_CHAR = 0.586f; -const float ScoringParams::INSERTION_COST_PROXIMITY_CHAR = 0.70f; -const float ScoringParams::INSERTION_COST_FIRST_CHAR = 0.623f; -const float ScoringParams::TRANSPOSITION_COST = 0.526f; -const float ScoringParams::SPACE_SUBSTITUTION_COST = 0.319f; -const float ScoringParams::ADDITIONAL_PROXIMITY_COST = 0.380f; -const float ScoringParams::SUBSTITUTION_COST = 0.383f; -const float ScoringParams::COST_NEW_WORD = 0.042f; -const float ScoringParams::COST_SECOND_OR_LATER_WORD_FIRST_CHAR_UPPERCASE = 0.25f; -const float ScoringParams::DISTANCE_WEIGHT_LANGUAGE = 1.123f; -const float ScoringParams::COST_FIRST_LOOKAHEAD = 0.545f; -const float ScoringParams::COST_LOOKAHEAD = 0.073f; -const float ScoringParams::HAS_PROXIMITY_TERMINAL_COST = 0.093f; -const float ScoringParams::HAS_EDIT_CORRECTION_TERMINAL_COST = 0.041f; -const float ScoringParams::HAS_MULTI_WORD_TERMINAL_COST = 0.447f; +const float ScoringParams::DISTANCE_WEIGHT_LENGTH = 0.1524f; +const float ScoringParams::PROXIMITY_COST = 0.0694f; +const float ScoringParams::FIRST_CHAR_PROXIMITY_COST = 0.072f; +const float ScoringParams::FIRST_PROXIMITY_COST = 0.07788f; +const float ScoringParams::OMISSION_COST = 0.4676f; +const float ScoringParams::OMISSION_COST_SAME_CHAR = 0.399f; +const float ScoringParams::OMISSION_COST_FIRST_CHAR = 0.5256f; +const float ScoringParams::INSERTION_COST = 0.7248f; +const float ScoringParams::TERMINAL_INSERTION_COST = 0.9828f; +const float ScoringParams::INSERTION_COST_SAME_CHAR = 0.5508f; +const float ScoringParams::INSERTION_COST_PROXIMITY_CHAR = 0.674f; +const float ScoringParams::INSERTION_COST_FIRST_CHAR = 0.639f; +const float ScoringParams::TRANSPOSITION_COST = 0.5608f; +const float ScoringParams::SPACE_SUBSTITUTION_COST = 0.339f; +const float ScoringParams::ADDITIONAL_PROXIMITY_COST = 0.4576f; +const float ScoringParams::SUBSTITUTION_COST = 0.3806f; +const float ScoringParams::COST_NEW_WORD = 0.0292f; +const float ScoringParams::COST_SECOND_OR_LATER_WORD_FIRST_CHAR_UPPERCASE = 0.3224f; +const float ScoringParams::DISTANCE_WEIGHT_LANGUAGE = 1.1214f; +const float ScoringParams::COST_FIRST_LOOKAHEAD = 0.4786f; +const float ScoringParams::COST_LOOKAHEAD = 0.00624f; +const float ScoringParams::HAS_PROXIMITY_TERMINAL_COST = 0.06836f; +const float ScoringParams::HAS_EDIT_CORRECTION_TERMINAL_COST = 0.0362f; +const float ScoringParams::HAS_MULTI_WORD_TERMINAL_COST = 0.4182f; const float ScoringParams::TYPING_BASE_OUTPUT_SCORE = 1.0f; const float ScoringParams::TYPING_MAX_OUTPUT_SCORE_PER_INPUT = 0.1f; const float ScoringParams::NORMALIZED_SPATIAL_DISTANCE_THRESHOLD_FOR_EDIT = 0.045f; |