public enum CrfSuiteAlgo extends Enum<CrfSuiteAlgo>
Enum Constant and Description 

ADAPTIVE_REGULARIZATION_OF_WEIGHT_VECTORS
Given an item sequence (x, y) in the training data, the algorithm computes the loss: s(x, y')
 s(x, y), where s(x, y') is the score of the Viterbi label sequence, and s(x, y) is the
score of the label sequence of the training data.

AVERAGED_PERCEPTRON
Given an item sequence (x, y) in the training data, the algorithm computes the loss: s(x, y')
 s(x, y) + sqrt(d(y', y)), where s(x, y') is the score of the Viterbi label sequence, s(x,
y) is the score of the label sequence of the training data, and d(y', y) measures the
distance between the Viterbi label sequence (y') and the reference label sequence (y).

L2SGD
Maximize the logarithm of the likelihood of the training data with L2 regularization term(s)
using Stochastic Gradient Descent (SGD) with batch size 1.

LBFGS
Maximize the logarithm of the likelihood of the training data with L1 and/or L2
regularization term(s) using the Limitedmemory BroydenFletcherGoldfarbShanno (LBFGS)
method.

Modifier and Type  Method and Description 

String 
toString() 
static CrfSuiteAlgo 
valueOf(String name)
Returns the enum constant of this type with the specified name.

static CrfSuiteAlgo[] 
values()
Returns an array containing the constants of this enum type, in
the order they are declared.

public static final CrfSuiteAlgo LBFGS
float feature.minfreq = 0.000000; The minimum frequency of features. int feature.possible_states = 0; Force to generate possible state features. int feature.possible_transitions = 0; Force to generate possible transition features. float c1 = 0.000000; Coefficient for L1 regularization. float c2 = 1.000000; Coefficient for L2 regularization. int max_iterations = 2147483647; The maximum number of iterations for LBFGS optimization. int num_memories = 6; The number of limited memories for approximating the inverse hessian matrix. float epsilon = 0.000010; Epsilon for testing the convergence of the objective. int period = 10; The duration of iterations to test the stopping criterion. float delta = 0.000010; The threshold for the stopping criterion; an LBFGS iteration stops when the improvement of the log likelihood over the last ${period} iterations is no greater than this threshold. string linesearch = MoreThuente; The line search algorithm used in LBFGS updates: { 'MoreThuente': More and Thuente's method, 'Backtracking': Backtracking method with regular Wolfe condition, 'StrongBacktracking': Backtracking method with strong Wolfe condition } int max_linesearch = 20; The maximum number of trials for the line search algorithm.
public static final CrfSuiteAlgo AVERAGED_PERCEPTRON
float feature.minfreq = 0.000000; The minimum frequency of features. int feature.possible_states = 0; Force to generate possible state features. int feature.possible_transitions = 0; Force to generate possible transition features. int max_iterations = 100; The maximum number of iterations. float epsilon = 0.000000; The stopping criterion (the ratio of incorrect label predictions).
public static final CrfSuiteAlgo ADAPTIVE_REGULARIZATION_OF_WEIGHT_VECTORS
float feature.minfreq = 0.000000; The minimum frequency of features. int feature.possible_states = 0; Force to generate possible state features. int feature.possible_transitions = 0; Force to generate possible transition features. float variance = 1.000000; The initial variance of every feature weight. float gamma = 1.000000; Tradeoff parameter. int max_iterations = 100; The maximum number of iterations. float epsilon = 0.000000; The stopping criterion (the mean loss).
public static final CrfSuiteAlgo L2SGD
float feature.minfreq = 0.000000; The minimum frequency of features. int feature.possible_states = 0; Force to generate possible state features. int feature.possible_transitions = 0; Force to generate possible transition features. float c2 = 1.000000; Coefficient for L2 regularization. int max_iterations = 1000; The maximum number of iterations (epochs) for SGD optimization. int period = 10; The duration of iterations to test the stopping criterion. float delta = 0.000001; The threshold for the stopping criterion; an optimization process stops when the improvement of the log likelihood over the last ${period} iterations is no greater than this threshold. float calibration.eta = 0.100000; The initial value of learning rate (eta) used for calibration. float calibration.rate = 2.000000; The rate of increase/decrease of learning rate for calibration. int calibration.samples = 1000; The number of instances used for calibration. int calibration.candidates = 10; The number of candidates of learning rate. int calibration.max_trials = 20; The maximum number of trials of learning rates for calibration.
public static CrfSuiteAlgo[] values()
for (CrfSuiteAlgo c : CrfSuiteAlgo.values()) System.out.println(c);
public static CrfSuiteAlgo valueOf(String name)
name
 the name of the enum constant to be returned.IllegalArgumentException
 if this enum type has no constant with the specified nameNullPointerException
 if the argument is nullpublic String toString()
toString
in class Enum<CrfSuiteAlgo>
Copyright © 2013–2019 Ubiquitous Knowledge Processing (UKP) Lab. All rights reserved.