An AnnotatedSentence is a sentence whose tokens are each annotated with a feature vector.
The BrownClustersTagger tags the tokens of a sentence with their Brown clusters.
A directed graph.
A directed graph.
The index of a node is its position in the nodes
list (counting from 0).
the nodes of the directed graph
each node's outgoing edges
An edge of a directed graph.
An edge of a directed graph.
index of the node at the edge's tail
index of the node at the edge's head
a labeling of this edge
A node of a directed graph.
A node of a directed graph.
a labeling of this node
Frequency Distribution of dependency labels for tokens based on Google Ngram's Nodes (unigrams).
Frequency Distribution of POS tags for words based on Google Ngram's Nodes (unigrams).
A Position is a essentially a pointer to a node in a rooted, directed tree.
A Position is a essentially a pointer to a node in a rooted, directed tree. It is a sequence of non-negative integers.
It is probably easiest to describe the concept by example. The root of the tree is the empty sequence. The first child of the root is Seq(0) (we count from zero). The third child of the first child of the root is Seq(2, 0). The seventh child of the third child of the first child of the root is Seq(6, 2, 0). Etc.
the sequence of integers corresponding to a node's position in a tree
A PositionTree is a rooted, directed tree, implemented as a map from positions to nodes.
A PositionTree is a rooted, directed tree, implemented as a map from positions to nodes.
a sequence of (position, node) pairs
A node of a position tree.
A node of a position tree.
a map from label names to label values
A Sentence is a sequence of tokens.
A Sentence is a sequence of tokens.
the sequence of tokens in the sentence
A data source for Sentence objects.
A Token is the basic atom of a sentence.
A Token is the basic atom of a sentence.
the surface form of the token
The VerbnetTagger tags the tokens of an input sentence with their Verbnet classes.
The FactorieLemmatizer tags the tokens of an input sentence with their lemmas, according to the Factorie lemmatizer.
The FactorieSentenceTagger tags an input sentence with automatic part-of-speech tags from the Factorie tagger.
The LexicalPropertiesTagger tags the tokens of an input sentence with lexical properties like whether the first letter is capitalized, or whether it contains numeric digits.
The NexusToken is the "zeroth" token of a dependency parse.
The StanfordSentenceTagger tags an input sentence with automatic part-of-speech tags from the Stanford tagger.
An AnnotatedSentence is a sentence whose tokens are each annotated with a feature vector.
the unannotated sentence
an indexed sequence, of which the nth element is the feature vector for the nth token of the sentence