Improve algorithm in a few ways:
* If the first letter is capital, only capitalized first tokens will be sampled. If the whole text is capitalized, then only fully capital tokens will be sampled for the whole word * If a word is an exact match, it gets boosted relative to others * Probability threshold for autocorrect is now 18.0 * Add "clueless" threshold, if it's less than 1.3 then just show the user's typed word in the middle instead.
parent
3aecbd5a
No related branches found
No related tags found
Showing
- java/src/org/futo/inputmethod/latin/uix/ActionBar.kt 12 additions, 0 deletionsjava/src/org/futo/inputmethod/latin/uix/ActionBar.kt
- java/src/org/futo/inputmethod/latin/xlm/LanguageModel.java 15 additions, 8 deletionsjava/src/org/futo/inputmethod/latin/xlm/LanguageModel.java
- native/jni/org_futo_inputmethod_latin_xlm_LanguageModel.cpp 136 additions, 10 deletionsnative/jni/org_futo_inputmethod_latin_xlm_LanguageModel.cpp
Loading
Please register or sign in to comment