Skip to content
Snippets Groups Projects
  1. Apr 18, 2024
  2. Dec 17, 2014
  3. Dec 15, 2014
  4. Dec 09, 2014
  5. Nov 25, 2014
    • Keisuke Kuroyanagi's avatar
      Enable Quadgram for personalized dicts. · 60021bbd
      Keisuke Kuroyanagi authored
      Before:
      Total words: 1134659, Success Num: 944709, Success Percentage: 83.259%
      Bad Failures, with auto-correction (typed word == expected word, output word != expected word): 1258, Bad Failure Percentage: 0.111%
      Failures, with auto-correction (F-C): 28013, F-C Percentage: 2.469%
      Max Keystrokes: 6072844, Min Keystrokes: 3347332, Keystroke Saving Percentage:44.880%
      
      After:
      Total words: 1134665, Success Num: 945026, Success Percentage: 83.287%
      Bad Failures, with auto-correction (typed word == expected word, output word != expected word): 1271, Bad Failure Percentage: 0.112%
      Failures, with auto-correction (F-C): 27756, F-C Percentage: 2.446%
      Max Keystrokes: 6072850, Min Keystrokes: 3290996, Keystroke Saving Percentage:45.808%
      
      Change-Id: I16af52a3e9c371b95fd6f0741f45ee6b2443bea6
      60021bbd
    • Keisuke Kuroyanagi's avatar
      Use enum to specify ngram type. · 78212a6d
      Keisuke Kuroyanagi authored
      Change-Id: Ie28768ceadcd7a2d940c57eb30be7d4c364e509f
      78212a6d
  6. Nov 10, 2014
  7. Nov 01, 2014
  8. Oct 31, 2014
    • Keisuke Kuroyanagi's avatar
      Update v4 format version from 402 to 403. · ea468cc9
      Keisuke Kuroyanagi authored
      Without personalization:
      Total words: 1134774, Success Num: 899230, Success Percentage: 79.243%
      Bad Failures, with auto-correction (typed word == expected word, output word != expected word): 1871, Bad Failure Percentage: 0.165%
      Failures, with auto-correction (F-C): 29084, F-C Percentage: 2.563%
      Max Keystrokes: 6072959, Min Keystrokes: 4436090, Keystroke Saving Percentage:26.953%
      
      Before:
      Total words: 1134646, Success Num: 925194, Success Percentage: 81.540%
      Bad Failures, with auto-correction (typed word == expected word, output word != expected word): 1316, Bad Failure Percentage: 0.116%
      Failures, with auto-correction (F-C): 28288, F-C Percentage: 2.493%
      Max Keystrokes: 6072831, Min Keystrokes: 3946188, Keystroke Saving Percentage:35.019%
      
      After
      Total words: 1134659, Success Num: 944746, Success Percentage: 83.263%
      Bad Failures, with auto-correction (typed word == expected word, output word != expected word): 1258, Bad Failure Percentage: 0.111%
      Failures, with auto-correction (F-C): 28016, F-C Percentage: 2.469%
      Max Keystrokes: 6072844, Min Keystrokes: 3387333, Keystroke Saving Percentage:44.222%
      
      Change-Id: I3af42ec37a11847c0429c28616e726f6a339247f
      ea468cc9
    • Keisuke Kuroyanagi's avatar
      Add hacks for better handling count value during migration. · c6119899
      Keisuke Kuroyanagi authored
      Bug: 14425059
      Change-Id: Ib050574aa7c4babd4285322a11c3af9be9fbab1e
      c6119899
    • Keisuke Kuroyanagi's avatar
      Change v403 historical info format. · 2383575d
      Keisuke Kuroyanagi authored
      count -> 2B, level -> 0B.
      
      Change-Id: I3b241126f56eb33cdf09cb1ebfed04f534e4ec48
      2383575d
    • Adrian Velicu's avatar
      Further fixes to treat 0-frequency words · 009e02ce
      Adrian Velicu authored
      Previously, when both legitimate 0-frequency words (such as
      distracters) and offensive words were encoded in the same
      way, distracters would never show up when the user blocked
      offensive words (the default setting, as well as the setting
      for regression tests).
      
      When b/11031090 was fixed and a separate encoding was used
      for offensive words, 0-frequency words would no longer be
      blocked when they were an "exact match" (where case
      mismatches and accent mismatches would be considered an
      "exact match"). The exact match boosting functionality meant
      that, for example, when the user typed "mt" they would be
      suggested the word "Mt", although they most probably meant
      to type "my".
      
      For this reason, we introduced this change, which does the
      following:
      * Defines the "perfect match" as a really exact match, with
      no room for case or accent mismatches
      * When the target word has probability zero (as "Mt" does,
      because it is a distracter), ONLY boost its score if it is a
      perfect match.
      
      By doing this, when the user types "mt", the word "Mt" will
      NOT be boosted, and they will get "my". However, if the user
      makes an explicit effort to type "Mt", we do boost the word
      "Mt" so that the user's input is not autocorrected to "My".
      
      Bug: 11031090
      Change-Id: I92ee1b4e742645d52e2f7f8c4390920481e8fff0
      009e02ce
    • Adrian Velicu's avatar
      Using "blacklist" flag as "possibly offensive" · 7c87859d
      Adrian Velicu authored
      Bug: 11031090
      Change-Id: I5cc0d006ab003656498eb82b0875eb9c051d331e
      7c87859d
  9. Oct 30, 2014
  10. Oct 29, 2014
  11. Oct 28, 2014
    • Keisuke Kuroyanagi's avatar
      Improve space substitution error correction. · 8a809f34
      Keisuke Kuroyanagi authored
      Bug: 17432052
      
      [Category diff]
      +1     262
      -1      93
      +2       2
      -2      18
      +3      18
      -3       2
      +4     111
      -4     148
      +5     295
      -5     217
      +6      51
      -6     276
      +7     139
      -7     124
      
      [Weighted category diff]
      +1     276
      -1     100
      +2       4
      -2      20
      +3      20
      -3       4
      +4     118
      -4     160
      +5     309
      -5     225
      +6      52
      -6     298
      +7     163
      -7     135
      
      show diff for ./en_user_log_phones_2011_08.csv
      +1     173
      -1      28
      +2       2
      -2      17
      +3      17
      -3       2
      +4      63
      -4      82
      +5     120
      -5      51
      +6      24
      -6     220
      +7      88
      -7      87
      
      Change-Id: I9d673acb0ff632828ae2e0ead56e76e3a20411c6
      8a809f34
  12. Oct 27, 2014
  13. Oct 22, 2014
  14. Oct 21, 2014
  15. Oct 20, 2014
  16. Oct 15, 2014
  17. Oct 14, 2014
  18. Oct 13, 2014
  19. Oct 10, 2014
  20. Oct 09, 2014
  21. Oct 06, 2014
    • Keisuke Kuroyanagi's avatar
      Improve bigram probability computation for decaying dicts. · aae1a062
      Keisuke Kuroyanagi authored
      Without personalization:
      Total words: 1079345, Success Num: 819749, Success Percentage: 75.949%
      Bad Failures, with auto-correction (typed word == expected word, output word != expected word): 1754, Bad Failure Percentage: 0.163%
      Failures, with auto-correction (F-C): 28463, F-C Percentage: 2.637%
      Max Keystrokes: 6074285, Min Keystrokes: 4649326, Keystroke Saving Percentage:23.459%
      
      With current probability computing logic:
      Total words: 1079382, Success Num: 838329, Success Percentage: 77.667%
      Bad Failures, with auto-correction (typed word == expected word, output word != expected word): 1332, Bad Failure Percentage: 0.123%
      Failures, with auto-correction (F-C): 28558, F-C Percentage: 2.646%
      Max Keystrokes: 6074503, Min Keystrokes: 4474102, Keystroke Saving Percentage:26.346%
      Remove isof files.
      
      With new probability computing logic:
      Total words: 1079356, Success Num: 844954, Success Percentage: 78.283%
      Bad Failures, with auto-correction (typed word == expected word, output word != expected word): 1306, Bad Failure Percentage: 0.121%
      Failures, with auto-correction (F-C): 27214, F-C Percentage: 2.521%
      Max Keystrokes: 6074477, Min Keystrokes: 4243021, Keystroke Saving Percentage:30.150%
      Remove isof files.
      
      Bug: 16547409
      Change-Id: I3d2a49c7aaa2c0f6835c52ef72d22466ee225789
      aae1a062
Loading