A class that asks about all anchored spans.
A ChartDecoder converts marginals into a binarized tree.
TODO
TODO docs
A GrammarAnchoring is a grammar that has been tuned to a particular sentence (if applicable).
Attempts to find a parse that maximizes the expected number of correct labels.
Tries to extract a tree that maximizes rule product in the coarse grammar.
Projects a tree to an anchored PCFG and then does viterbi on that tree.
Hack approximation to true parse eval.
Represents marginals over trees.
A Parser produces a syntactic representation of a sentence, called a epic.trees.Tree, which has internal nodes that demarcate syntactic functions
A ParserAnnotator is a slab-ified epic.parser.Parser.
ParserPipeline is a base-trait for the parser training pipeline.
TODO
Creates a product of two derivation scorers, seamlessly combining their refinements as appropriate.
Creates a product of two epic.parser.UnrefinedGrammarAnchorings (product is in log space, so actually a sum.
A simple Featurizer that just counts lexical and rule productions that are used.
TODO
Holds the information for the marginals for a sentence.
A simple Featurizer that just counts lexical and rule productions that are used.
A RuleTopology is basically a grammar with no weights.
TODO
A epic.parser.SimpleGrammar is a grammar where the topology of the grammar (including the refinements) and the scores for the rules does not vary with the input sentence.
This class is mostly an implementation detail.
This isn't really a marginal, except in a degenerate sense.
epic.parser.UnrefinedGrammarAnchoring score rules and labels in a particular context without needed extra "refined" categories.
Tries to extract a tree that maximizes log score.
Contains codes to read off parsers and grammars from a treebank.
Simple class that reads in a bunch of files and parses them.
Mostly a utility class for parsertrainers.
ParserTester just tests a grammar reading in the treebank and params and such