Sequence representations and labeling models/algorithms. More...

Classes
class	crf
	Linear-chain conditional random field for POS tagging and chunking applications. More...

class	forward_trellis
	Special trellis for the normalized forward algorithm. More...

class	observation
	Represents an observation in a tagged sequence. More...

class	perceptron
	A greedy averaged perceptron tagger. More...

class	sequence
	Represents a tagged sequence of observations. More...

class	sequence_analyzer
	Analyzer that operates over sequences, generating features based on a set of "observation functions". More...

class	trellis
	Basic trellis for holding score data for the forward/backward algorithm. More...

class	viterbi_trellis
	Special trellis for the Viterbi algorithm. More...

Functions
void	register_analyzers ()
	Registers analyzers provided by the meta-sequence-analyzers library.

std::vector< sequence >	extract_sequences (const std::string &filename)
	Reads a Penn Treebank formatted part of speech tagged file and returns a set of sequences parsed from it. More...

sequence_analyzer	default_pos_analyzer ()
	Constructs a sequence_analyzer that is specialized for part-of-speech tagging. More...

Detailed Description

Sequence representations and labeling models/algorithms.

Function Documentation

std::vector< sequence > meta::sequence::extract_sequences ( const std::string & filename )

Reads a Penn Treebank formatted part of speech tagged file and returns a set of sequences parsed from it.

Parameters

filename The name of the file to be parsed

sequence_analyzer meta::sequence::default_pos_analyzer ( )

Constructs a sequence_analyzer that is specialized for part-of-speech tagging.

Uses a predefined set of observation functions.