Parsing Engine

Uses of Interface
danbikel.parser.Event

Packages that use Event
danbikel.parser Provides the core framework of this extensible statistical parsing engine. 
danbikel.parser.ms Default package for model structure classes (subclasses of ProbabilityStructure). 
 

Uses of Event in danbikel.parser
 

Subinterfaces of Event in danbikel.parser
 interface MutableEvent
          Provides additional methods to those of Event that permit modification of the event object.
 interface Subcat
          Specification for a collection of required arguments to be generated by a parser, also known as a subcategorization frame.
 

Classes in danbikel.parser that implement Event
 class AbstractEvent
          A convenience class that simply implements the equals method, as specified by the contract in equals(Object).
 class BrokenSubcatBag
          A “broken” version of SubcatBag that precisely reflects the details specified in Collins’ thesis (used for “clean-room” implementation).
 class SexpEvent
          Represents an event composed of one or more Sexp objects.
 class SexpSubcatEvent
          Represents an event composed of zero or more Sexp objects and zero or one Subcat object.
 class SubcatBag
          Provides a bag implementation of subcat requirements (a bag is a set that allows multiple occurrences of the same item).
 class SubcatList
          Implements subcats where requirements need to be met in the order in which they are added to this subcat (the strictest form of a subcat).
 

Methods in danbikel.parser that return Event
protected static Event Model.canonicalizeEvent(Event event, FlexibleMap canonical)
          This method first canonicalizes the information in the specified event (a Sexp or a Subcat and a Sexp), then it returns a canonical version of the event itself, copying it into the map if necessary.
 Event BrokenSubcatBag.copy()
          Returns a deep copy of this subcat bag.
 Event Event.copy()
          Returns a deep copy of this event of the same run-time type.
 Event SexpEvent.copy()
          Returns a deep copy of this event, which really just means creating a new instance with a deep copy of the backing Sexp, using the Sexp.deepCopy method.
 Event SexpSubcatEvent.copy()
          Returns a deep copy of this event, using SexpEvent.copy to copy the backing Sexp, and using Event.copy to copy the backing Subcat, if there is one.
 Event SubcatBag.copy()
          Returns a deep copy of this subcat bag.
 Event SubcatList.copy()
           
 Event Transition.future()
          Gets the future event of this transition object.
abstract  Event ProbabilityStructure.getFuture(TrainerEvent trainerEvent, int backOffLevel)
          Extracts the future for the specified level of back-off from the specified trainer event.
abstract  Event ProbabilityStructure.getHistory(TrainerEvent trainerEvent, int backOffLevel)
          Extracts the history context for the specified back-off level from the specified trainer event.
 Event Transition.history()
          Gets the history event of this transition object.
 

Methods in danbikel.parser with parameters of type Event
protected static Event Model.canonicalizeEvent(Event event, FlexibleMap canonical)
          This method first canonicalizes the information in the specified event (a Sexp or a Subcat and a Sexp), then it returns a canonical version of the event itself, copying it into the map if necessary.
static double[] AnalyzeDisns.getLogProbDisn(Model model, int level, Event hist, Set futures, double[] disn, Transition tmpTrans)
          Returns the smoothed log-probability distribution for the specified history at the specified back-off level in the specified model.
protected  void InterpolatedKnesserNeyModel.precomputeProbs(MapToPrimitive.Entry transEntry, double[] lambdas, double[] estimates, Transition[] transitions, Event[] histories, int lastLevel)
           
protected  void Model.precomputeProbs(MapToPrimitive.Entry transEntry, double[] lambdas, double[] estimates, Transition[] transitions, Event[] histories, int lastLevel)
          Precomputes the probabilities and smoothing values for the Transition object contained as a key within the specified map entry, where the value is the count of the transition.
protected  void InterpolatedKnesserNeyModel.precomputeProbs(TrainerEvent event, Transition[] transitions, Event[] histories)
          Deprecated. This method is called by Model.precomputeProbs(CountsTable,Filter), which is also deprecated.
protected  void Model.precomputeProbs(TrainerEvent event, Transition[] transitions, Event[] histories)
          Deprecated. This method is called by Model.precomputeProbs(CountsTable,Filter), which is also deprecated.
static void PrintDisn.printLogProbDisn(PrintWriter writer, ModelCollection mc, Model model, int level, Event hist, Set futures, Transition tmpTrans)
          Prints the log-probability distribution of the specified event at the specified back-off level of the specified model to the specified writer.
 boolean ProbabilityStructure.removeFuture(int backOffLevel, Event future)
          Indicates that Model.cleanup(), which is invoked at the end of Model.deriveCounts(CountsTable,danbikel.util.Filter,double,danbikel.util.FlexibleMap), can safely remove the specified event from the Model object's internal counts tables, as the event is not applicable to any of the probabilities for which the model will produce an estimate.
 boolean ProbabilityStructure.removeHistory(int backOffLevel, Event history)
          Indicates that Model.cleanup(), which is invoked at the end of Model.deriveCounts, can safely remove the specified event from the Model object's internal counts tables, as the event is not applicable to any of the probabilities for which the model will produce an estimate.
 void Transition.setFuture(Event future)
          Sets the future event of this transition.
 void Transition.setHistory(Event history)
          Sets the history event of this transition.
protected  void InterpolatedKnesserNeyModel.storePrecomputedProbs(double[] lambdas, double[] estimates, Transition[] transitions, Event[] histories, int lastLevel)
           
protected  void Model.storePrecomputedProbs(double[] lambdas, double[] estimates, Transition[] transitions, Event[] histories, int lastLevel)
          Stores the specified smoothing values (lambdas) and smoothed probability estimates in the Model.precomputedProbs and Model.smoothingParams map arrays.
 

Constructors in danbikel.parser with parameters of type Event
Transition(Event future, Event history)
          Constructs this transition with the specified future and history events.
 

Uses of Event in danbikel.parser.ms
 

Methods in danbikel.parser.ms that return Event
 Event BrokenLeftSubcatModelStructure.getFuture(TrainerEvent trainerEvent, int backOffLevel)
          Gets the future being predicted conditioning on this subcat event.
 Event BrokenLexPriorModelStructure.getFuture(TrainerEvent trainerEvent, int backOffLevel)
          Returns an event whose two components are the word and part-of-speech for which a marginal probability is being computed.
 Event BrokenModWordModelStructure.getFuture(TrainerEvent trainerEvent, int backOffLevel)
          Returns an event whose sole component is the word being generated as the head of some modifier nonterminal.
 Event BrokenRightSubcatModelStructure.getFuture(TrainerEvent trainerEvent, int backOffLevel)
          Gets the future being predicted conditioning on this subcat event.
 Event BrokenTopLexModelStructure.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event GapModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event HeadModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event LeftSubcatModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event LeftSubcatModelStructure2.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event LexPriorModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure2.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure3.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure4.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure5.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure6.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure7.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure8.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure9.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure2.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure3.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure4.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure5.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure6.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure7.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure8.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure9.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event NonterminalPriorModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event RightSubcatModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event RightSubcatModelStructure2.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event TagModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event TagModelStructure2.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event TopLexModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event TopNonterminalModelStructure1.getFuture(TrainerEvent trainerEvent, int backOffLevel)
           
 Event BrokenLexPriorModelStructure.getHistory(TrainerEvent trainerEvent, int backOffLevel)
          As this model simulates unconditional probabilities using relative-frequency estimation, this method returns a history whose sole component is a dummy object that is the same regardless of the “future” being estimated.
 Event BrokenModWordModelStructure.getHistory(TrainerEvent trainerEvent, int backOffLevel)
          Returns the history event corresponding to the specified back-off level.
 Event BrokenTopLexModelStructure.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event GapModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event HeadModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event LexPriorModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure2.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure3.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure4.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure6.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure7.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure8.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModNonterminalModelStructure9.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure2.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure3.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure4.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure5.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure6.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure7.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure8.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event ModWordModelStructure9.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event NonterminalPriorModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event SubcatModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
          Returns a history for the specified back-off level, according to the following zero-indexed list of history events.
 Event SubcatModelStructure2.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event TagModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event TagModelStructure2.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event TopLexModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 Event TopNonterminalModelStructure1.getHistory(TrainerEvent trainerEvent, int backOffLevel)
           
 

Methods in danbikel.parser.ms with parameters of type Event
 boolean ModWordModelStructure2.removeFuture(int backOffLevel, Event future)
           
 boolean ModWordModelStructure4.removeFuture(int backOffLevel, Event future)
           
 boolean ModWordModelStructure6.removeFuture(int backOffLevel, Event future)
           
 boolean ModWordModelStructure7.removeFuture(int backOffLevel, Event future)
           
 boolean ModWordModelStructure8.removeFuture(int backOffLevel, Event future)
           
 boolean BrokenModWordModelStructure.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p^(w | t), the trainer “fakes” a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModNonterminalModelStructure2.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModNonterminalModelStructure4.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModNonterminalModelStructure6.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModNonterminalModelStructure7.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModNonterminalModelStructure8.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModNonterminalModelStructure9.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModWordModelStructure2.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModWordModelStructure4.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModWordModelStructure5.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModWordModelStructure6.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModWordModelStructure7.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean ModWordModelStructure8.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean TagModelStructure1.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean TagModelStructure2.removeHistory(int backOffLevel, Event history)
          In order to gather statistics for words that appear as the head of the entire sentence when estimating p(w | t), the trainer "fakes" a modifier event, as though the root node of the observed tree was seen to modify the magical +TOP+ node.
 boolean TopLexModelStructure1.removeHistory(int backOffLevel, Event history)
           
 


Parsing Engine

Author: Dan Bikel.