edu.stanford.nlp.parser.shiftreduce

Class ShiftReduceParser

java.lang.Object

edu.stanford.nlp.parser.common.ParserGrammar

edu.stanford.nlp.parser.shiftreduce.ShiftReduceParser

All Implemented Interfaces:

Function<java.util.List<? extends HasWord>,Tree>, java.io.Serializable

public class ShiftReduceParser
extends ParserGrammar
implements java.io.Serializable

Overview and description available at http://nlp.stanford.edu/software/srparser.shtml

Author:

John Bauer

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
ShiftReduceParser(ShiftReduceOptions op)

Method Summary

Methods

Modifier and Type	Method and Description
Tree	apply(java.util.List<? extends HasWord> sentence) A convenience method which wraps the ParserQuery and returns a Tree
static ShiftReduceParser	averageModels(java.util.Collection<ShiftReduceParser> models)
static ShiftReduceParser	averageScoredModels(java.util.Collection<ScoredObject<ShiftReduceParser>> scoredModels)
static java.util.List<Tree>	binarizeTreebank(Treebank treebank, Options op)
static ShiftReduceOptions	buildTrainingOptions(java.lang.String tlppClass, java.lang.String[] args)
void	condenseFeatures() Iterate over the feature weight map.
void	copyWeights(ShiftReduceParser other) Fill in the current object's weights with the other parser's weights.
java.util.List<java.util.List<Transition>>	createTransitionSequences(java.util.List<Tree> binarizedTrees)
ShiftReduceParser	deepCopy()
java.lang.String[]	defaultCoreNLPFlags() Returns a set of options which should be set by default when used in corenlp.
void	filterFeatures(java.util.Set<java.lang.String> keep)
Transition	findEmergencyTransition(State state, java.util.List<ParserConstraint> constraints) Returns a transition which might not even be part of the model, but will hopefully allow progress in an otherwise stuck parse TODO: perhaps we want to create an EmergencyTransition class which indicates that something has gone wrong
ScoredObject<java.lang.Integer>	findHighestScoringTransition(State state, java.util.List<java.lang.String> features, boolean requireLegal) Convenience method: returns one highest scoring transition, without any ParserConstraints
java.util.Collection<ScoredObject<java.lang.Integer>>	findHighestScoringTransitions(State state, java.util.List<java.lang.String> features, boolean requireLegal, int numTransitions, java.util.List<ParserConstraint> constraints)
static void	findKnownStates(java.util.List<Tree> binarizedTrees, java.util.Set<java.lang.String> knownStates)
static void	findKnownStates(Tree tree, java.util.Set<java.lang.String> knownStates)
java.util.List<Eval>	getExtraEvals() TODO: add an eval which measures transition accuracy?
Options	getOp()
java.util.List<ParserQueryEval>	getParserQueryEvals() Return a list of Eval-style objects which care about the whole ParserQuery, not just the finished tree
TreebankLangParserParams	getTLPParams()
static State	initialStateFromGoldTagTree(Tree tree)
static State	initialStateFromTaggedSentence(java.util.List<? extends HasWord> words)
static ShiftReduceParser	loadModel(java.lang.String path, java.lang.String... extraFlags)
static void	main(java.lang.String[] args)
void	outputStats() Output some random facts about the parser
ParserQuery	parserQuery()
java.util.List<Tree>	readBinarizedTreebank(java.lang.String treebankPath, java.io.FileFilter treebankFilter)
Treebank	readTreebank(java.lang.String treebankPath, java.io.FileFilter treebankFilter)
static void	redoTags(java.util.List<Tree> trees, Tagger tagger, int nThreads)
static void	redoTags(Tree tree, Tagger tagger)
boolean	requiresTags() The model requires text to be pretagged
void	saveModel(java.lang.String path)
void	setOptionFlags(java.lang.String... flags)
TreebankLanguagePack	treebankLanguagePack()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

ShiftReduceParser

public ShiftReduceParser(ShiftReduceOptions op)

Method Detail

getOp

public Options getOp()

Specified by:

getOp in class ParserGrammar

getTLPParams

public TreebankLangParserParams getTLPParams()

Specified by:

getTLPParams in class ParserGrammar

treebankLanguagePack

public TreebankLanguagePack treebankLanguagePack()

Specified by:

treebankLanguagePack in class ParserGrammar

defaultCoreNLPFlags

public java.lang.String[] defaultCoreNLPFlags()

Description copied from class: ParserGrammar

Returns a set of options which should be set by default when used in corenlp. For example, the English PCFG/RNN models want -retainTmpSubcategories, and the ShiftReduceParser models may want -beamSize 4 depending on how they were trained.
TODO: right now completely hardcoded, should be settable as a training time option

Specified by:

defaultCoreNLPFlags in class ParserGrammar

requiresTags

public boolean requiresTags()

Description copied from class: ParserGrammar

The model requires text to be pretagged

Specified by:

requiresTags in class ParserGrammar

deepCopy

public ShiftReduceParser deepCopy()

copyWeights

public void copyWeights(ShiftReduceParser other)

Fill in the current object's weights with the other parser's weights.

averageScoredModels

public static ShiftReduceParser averageScoredModels(java.util.Collection<ScoredObject<ShiftReduceParser>> scoredModels)

averageModels

public static ShiftReduceParser averageModels(java.util.Collection<ShiftReduceParser> models)

parserQuery

public ParserQuery parserQuery()

Specified by:

parserQuery in class ParserGrammar

apply

public Tree apply(java.util.List<? extends HasWord> sentence)

Description copied from class: ParserGrammar

A convenience method which wraps the ParserQuery and returns a Tree

Specified by:

apply in interface Function<java.util.List<? extends HasWord>,Tree>

Specified by:

apply in class ParserGrammar

Parameters:

sentence - The function's argument

Returns:

The function's evaluated value

condenseFeatures

public void condenseFeatures()

Iterate over the feature weight map. For each feature, remove all transitions with score of 0. Any feature with no transitions left is then removed

filterFeatures

public void filterFeatures(java.util.Set<java.lang.String> keep)

outputStats

public void outputStats()

Output some random facts about the parser

getExtraEvals

public java.util.List<Eval> getExtraEvals()

TODO: add an eval which measures transition accuracy?

Specified by:

getExtraEvals in class ParserGrammar

getParserQueryEvals

public java.util.List<ParserQueryEval> getParserQueryEvals()

Description copied from class: ParserGrammar

Return a list of Eval-style objects which care about the whole ParserQuery, not just the finished tree

Specified by:

getParserQueryEvals in class ParserGrammar

findEmergencyTransition

public Transition findEmergencyTransition(State state,
                                 java.util.List<ParserConstraint> constraints)

Returns a transition which might not even be part of the model, but will hopefully allow progress in an otherwise stuck parse TODO: perhaps we want to create an EmergencyTransition class which indicates that something has gone wrong

findHighestScoringTransition

public ScoredObject<java.lang.Integer> findHighestScoringTransition(State state,
                                                           java.util.List<java.lang.String> features,
                                                           boolean requireLegal)

Convenience method: returns one highest scoring transition, without any ParserConstraints

findHighestScoringTransitions

public java.util.Collection<ScoredObject<java.lang.Integer>> findHighestScoringTransitions(State state,
                                                                                  java.util.List<java.lang.String> features,
                                                                                  boolean requireLegal,
                                                                                  int numTransitions,
                                                                                  java.util.List<ParserConstraint> constraints)

initialStateFromGoldTagTree

public static State initialStateFromGoldTagTree(Tree tree)

initialStateFromTaggedSentence

public static State initialStateFromTaggedSentence(java.util.List<? extends HasWord> words)

buildTrainingOptions

public static ShiftReduceOptions buildTrainingOptions(java.lang.String tlppClass,
                                      java.lang.String[] args)

readTreebank

public Treebank readTreebank(java.lang.String treebankPath,
                    java.io.FileFilter treebankFilter)

readBinarizedTreebank

public java.util.List<Tree> readBinarizedTreebank(java.lang.String treebankPath,
                                         java.io.FileFilter treebankFilter)

binarizeTreebank

public static java.util.List<Tree> binarizeTreebank(Treebank treebank,
                                    Options op)

createTransitionSequences

public java.util.List<java.util.List<Transition>> createTransitionSequences(java.util.List<Tree> binarizedTrees)

findKnownStates

public static void findKnownStates(java.util.List<Tree> binarizedTrees,
                   java.util.Set<java.lang.String> knownStates)

findKnownStates

public static void findKnownStates(Tree tree,
                   java.util.Set<java.lang.String> knownStates)

redoTags

public static void redoTags(Tree tree,
            Tagger tagger)

redoTags

public static void redoTags(java.util.List<Tree> trees,
            Tagger tagger,
            int nThreads)

setOptionFlags

public void setOptionFlags(java.lang.String... flags)

Specified by:

setOptionFlags in class ParserGrammar

loadModel

public static ShiftReduceParser loadModel(java.lang.String path,
                          java.lang.String... extraFlags)

saveModel

public void saveModel(java.lang.String path)

main

public static void main(java.lang.String[] args)