Package edu.ucla.sspace.wordsi

Interface Summary

Interface	Description
AssignmentReporter	An interface for reporting the results of a Wordsi run.
ContextExtractor	An interface for extracting context vectors from a document and passing on the vector to a Wordsi implementation.
ContextGenerator	An interface for generating context vectors from raw unparsed text.
DependencyContextGenerator	An interface for generating context vectors from raw unparsed text.
Wordsi	An interface for all Wordsi implementations.

Class Summary

Class	Description
AbstractOccurrenceDependencyContextGenerator	An abstract DependencyContextGenerator that creates a context vector for a node in an array of DependencyTreeNodes by using any form of co-occurrence information in the tree.
BaseWordsi	This base class accepts or rejects key words based on a set of acceptedWords and dispatches calls to a ContextExtractor so that Wordsi sub-classes will be called with each generated vector.
DependencyContextExtractor	This ContextExtractor reads in documents that have been dependency parsed.
EvaluationWordsi	An Wordsi implementation to be used for evaluations.
GeneralContextExtractor	A general purpose ContextExtractor.
OccurrenceDependencyContextGenerator	A DependencyContextGenerator that marks each co-occurrence with ordering information.
OrderingDependencyContextGenerator	A DependencyContextGenerator that marks each co-occurrence with ordering information.
PartOfSpeechDependencyContextGenerator	A DependencyContextGenerator that marks each co-occurrence with part of speech information.
PreComputedContextExtractor	A ContextExtractor that assumes that the corpus has already been pre-processed and each document is a single line with the following format:
RandomIndexingContextGenerator	A random indexing based ContextGenerator.
RandomIndexingDependencyContextGenerator	A DependencyContextGenerator that forms context vectors using a summation of index vectors.
SelPrefDependencyContextGenerator	A DependencyContextGenerator that marks each co-occurrence with ordering information.
StreamingWordsi	A Wordsi implementation that utilizes streaming, or online, clustering algorithms.
TopicModelContextExtractor	A ContextExtractor for processing documents with topic signatures for contexts as computed by the Mallet framework.
WaitingWordsi	A Wordsi implementation that performs batch clustering.
WordOccrrenceContextGenerator	A raw word co-occurrence ContextGenerator.
WordOccrrenceDependencyContextGenerator	A DependencyContextGenerator that forms co-occurrence context vectors from words that are reachable via a valid DependencyPath from a focus term.