public class ShiftReduceTrainOptions extends TrainOptions
Modifier and Type | Class and Description |
---|---|
static class |
ShiftReduceTrainOptions.TrainingMethod |
TrainOptions.TransformMatrixType
Modifier and Type | Field and Description |
---|---|
int |
averagedModels
If set to 0, training outputs the last model produced, regardless
of its score.
|
int |
beamSize |
boolean |
cvAveragedModels
Cross-validate over the number of models to average, using the
dev set, to figure out which number between 1 and averagedModels
we actually want to use
|
double |
decayLearningRate
If positive, every 10 iterations, multiply the learning rate by this amount.
|
static int |
DEFAULT_BEAM_SIZE |
int |
featureFrequencyCutoff
How many times a feature must be seen when training.
|
boolean |
oracleBinaryToShift
Does help, but makes the models much bigger for a miniscule gain
|
boolean |
oracleShiftToBinary
Does not seem to help...
|
boolean |
retrainAfterCutoff
If we cut off features with featureFrequencyCutoff, this retrains with only the existing features
|
boolean |
saveIntermediateModels
Saves intermediate models, but that takes up a lot of space
|
ShiftReduceTrainOptions.TrainingMethod |
trainingMethod |
basicCategoryTagsInDependencyGrammar, batchSize, cheatPCFG, collinsPunc, compactGrammar, debugOutputFrequency, DEFAULT_BATCH_SIZE, DEFAULT_DELTA_MARGIN, DEFAULT_K_BEST, DEFAULT_LEARNING_RATE, DEFAULT_QN_ITERATIONS_PER_BATCH, DEFAULT_REGCOST, DEFAULT_SCALING_FOR_INIT, DEFAULT_STALLED_ITERATION_LIMIT, DEFAULT_TRAINING_ITERATIONS, DEFAULT_UNK_WORD, deleteSplitters, deltaMargin, dvKBest, dvSimplifiedModel, fractionBeforeUnseenCounting, gPA, HSEL_CUT, hSelSplit, learningRate, leftRec, leftToRight, lowercaseWordVectors, markFinalStates, markovFactor, markovOrder, markStrahler, markUnary, markUnaryTags, maxTrainTimeSeconds, noRebinarization, noTagSplit, openClassTypesThreshold, PA, postGPA, postPA, postSplitters, postSplitWithBaseCategory, predictSplits, preTransformer, printAnnotatedPW, printAnnotatedRuleCounts, printAnnotatedStateCounts, printBinarizedPW, printStates, printTreeTransformations, qnEstimates, qnIterationsPerBatch, qnTolerance, randomSeed, regCost, rightRec, ruleDiscount, ruleSmoothing, ruleSmoothingAlpha, scalingForInit, selectivePostSplit, selectivePostSplitCutOff, selectiveSplit, selectiveSplitCutOff, simpleBinarizedLabels, sisterAnnotate, sisterSplitters, smoothing, splitCount, splitPrePreT, splitRecombineRate, splitters, stalledIterationLimit, taggedFiles, tagPA, tagSelectivePostSplit, tagSelectivePostSplitCutOff, tagSelectiveSplit, tagSelectiveSplitCutOff, trainingIterations, trainingThreads, trainLengthLimit, trainTreeFile, trainWordVectors, transformMatrixType, unknownCapsVector, unknownChineseNumberVector, unknownChinesePercentVector, unknownChineseYearVector, unknownDashedWordVectors, unknownNumberVector, unkWord, useContextWords
Constructor and Description |
---|
ShiftReduceTrainOptions() |
compactGrammar, display, outsideFactor, printTrainTree, toString
public int averagedModels
public boolean cvAveragedModels
public ShiftReduceTrainOptions.TrainingMethod trainingMethod
public static final int DEFAULT_BEAM_SIZE
public int beamSize
public int featureFrequencyCutoff
public boolean saveIntermediateModels
public boolean retrainAfterCutoff
public boolean oracleShiftToBinary
public boolean oracleBinaryToShift
public double decayLearningRate