Package opennlp.tools.depparse
package opennlp.tools.depparse
-
ClassesClassDescriptionCross validator for
DependencyParserME.Measures the quality of aDependencyParseragainst goldsampleswith the two standard scores: the unlabeled attachment score (UAS, the fraction of tokens with the correct head) and the labeled attachment score (LAS, the fraction of tokens with the correct head and relation label).The persisted form of a trainedDependencyParserME: the transition classification model plus the standard model manifest, serialized and loaded through the sameBaseModelmachinery as every other tool model.A greedy transition-basedDependencyParser: a classifier picks the next arc-standardTransitionfor each configuration until the parse is complete, always taking the highest scoring transition that is applicable.The persisted form of a trainedFeedforwardDependencyParser: the network weights plus the standard model manifest, serialized and loaded through the sameBaseModelmachinery as every other tool model.The neuralDependencyParser: an arc-standard decoder over theFeedforwardDependencyModel.Trains theFeedforwardDependencyModel: oracle-derived transition examples, minibatch AdaGrad over a softmax cross-entropy loss, cube activation, and inverted dropout on the hidden layer, the training recipe of Chen and Manning (2014).