Safe Haskell | None |
---|
- newtype Ob = Ob {}
- newtype Lb = Lb {}
- data Feat
- data CRF a b = CRF {}
- train :: (Ord o, Ord t) => Int -> FeatSel Ob [Lb] Feat -> SgdArgs -> TrainCRF o [t] (CRF o t)
- tag :: (Ord o, Ord t) => CRF o t -> TagCRF o [t]
- type FeatSel o t f = FeatGen o t f -> Xs o t -> Ys t -> [f]
- selectHidden :: FeatSel o t f
- selectPresent :: FeatSel o t f
Tiered model
CRF model data.
:: (Ord o, Ord t) | |
=> Int | Number of tagging layers |
-> FeatSel Ob [Lb] Feat | Feature selection |
-> SgdArgs | Args for SGD |
-> TrainCRF o [t] (CRF o t) |
Train the CRF using the stochastic gradient descent method. Use the provided feature selection function to determine model features.
Feature selection
selectHidden :: FeatSel o t f
The hiddenFeats
adapted to fit feature selection specs.
selectPresent :: FeatSel o t f
The presentFeats
adapted to fit feature selection specs.