EST_Ngrammar.h File Reference

#include <cstdarg>
#include <cstdlib>
#include "EST_String.h"
#include "EST_Val.h"
#include "EST_rw_status.h"
#include "EST_types.h"
#include "EST_FMatrix.h"
#include "EST_TList.h"
#include "EST_StringTrie.h"
#include "EST_simplestats.h"
#include "EST_PST.h"
#include "EST_string_aux.h"
#include "EST_math.h"

Include dependency graph for EST_Ngrammar.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	EST_NgrammarState
class	EST_BackoffNgrammarState
class	EST_Ngrammar

Macros
#define	SENTENCE_START_MARKER   "!ENTER"
#define	SENTENCE_END_MARKER   "!EXIT"
#define	OOV_MARKER   "!OOV"
#define	EST_NGRAMBIN_MAGIC   1315402337
#define	GZIP_FILENAME_EXTENSION   "gz"
#define	COMPRESS_FILENAME_EXTENSION   "Z"
#define	TINY_FREQ   1.0e-10

Functions
EST_write_status	save_ngram_htk_ascii (const EST_String filename, EST_Ngrammar &n, double floor=0.0)
EST_write_status	save_ngram_cstr_ascii (const EST_String filename, EST_Ngrammar &n, const bool trace=false, double floor=0.0)
EST_write_status	save_ngram_cstr_bin (const EST_String filename, EST_Ngrammar &n, const bool trace=false, double floor=0.0)
void	frequency_of_frequencies (EST_DVector &ff, EST_Ngrammar &n, int this_order=0)
void	map_frequencies (EST_Ngrammar &n, const EST_DVector &map, const int this_order=0)
bool	Good_Turing_smooth (EST_Ngrammar &n, int maxcount, int mincount=0)
void	Good_Turing_discount (EST_Ngrammar &ngrammar, const int maxcount, const double default_discount=0.5)
void	Ngram_freqsmooth (EST_Ngrammar &ngram, int smooth_thresh1, int smooth_thresh2)
void	slide (EST_IVector &i, const int l)
void	slide (EST_StrVector &i, const int l)
bool	test_stats (EST_Ngrammar &ngram, const EST_String &filename, double &raw_entropy, double &count, double &entropy, double &perplexity, const EST_String &input_format, const EST_String &prev=SENTENCE_START_MARKER, const EST_String &prev_prev=SENTENCE_END_MARKER, const EST_String &last=SENTENCE_END_MARKER)

Macro Definition Documentation

#define SENTENCE_START_MARKER   "!ENTER"

Definition at line 59 of file EST_Ngrammar.h.

#define SENTENCE_END_MARKER   "!EXIT"

Definition at line 60 of file EST_Ngrammar.h.

#define OOV_MARKER   "!OOV"

Definition at line 61 of file EST_Ngrammar.h.

#define EST_NGRAMBIN_MAGIC   1315402337

Definition at line 63 of file EST_Ngrammar.h.

#define GZIP_FILENAME_EXTENSION   "gz"

Definition at line 66 of file EST_Ngrammar.h.

#define COMPRESS_FILENAME_EXTENSION   "Z"

Definition at line 67 of file EST_Ngrammar.h.

#define TINY_FREQ   1.0e-10

Definition at line 70 of file EST_Ngrammar.h.

Function Documentation

EST_write_status save_ngram_htk_ascii	(	const EST_String	filename,
		EST_Ngrammar &	n,
		double	floor = 0.0
	)

Definition at line 565 of file ngrammar_io.cc.

EST_write_status save_ngram_cstr_ascii	(	const EST_String	filename,
		EST_Ngrammar &	n,
		const bool	trace = false,
		double	floor = 0.0
	)

Definition at line 747 of file ngrammar_io.cc.

EST_write_status save_ngram_cstr_bin	(	const EST_String	filename,
		EST_Ngrammar &	n,
		const bool	trace = false,
		double	floor = 0.0
	)

Definition at line 844 of file ngrammar_io.cc.

void frequency_of_frequencies	(	EST_DVector &	ff,
		EST_Ngrammar &	n,
		int	this_order = 0
	)

Definition at line 207 of file ngrammar_aux.cc.

void map_frequencies	(	EST_Ngrammar &	n,
		const EST_DVector &	map,
		const int	this_order = 0
	)

Definition at line 306 of file ngrammar_aux.cc.

bool Good_Turing_smooth	(	EST_Ngrammar &	n,
		int	maxcount,
		int	mincount = 0
	)

Definition at line 410 of file ngrammar_aux.cc.

void Good_Turing_discount	(	EST_Ngrammar &	ngrammar,
		const int	maxcount,
		const double	default_discount = 0.5
	)

Definition at line 540 of file ngrammar_aux.cc.

void Ngram_freqsmooth	(	EST_Ngrammar &	ngram,
		int	smooth_thresh1,
		int	smooth_thresh2
	)

Definition at line 58 of file freqsmooth.cc.

void slide	(	EST_IVector &	i,
		const int	l
	)

Definition at line 2614 of file EST_Ngrammar.cc.

void slide	(	EST_StrVector &	i,
		const int	l
	)

Definition at line 2735 of file EST_Ngrammar.cc.

bool test_stats	(	EST_Ngrammar &	ngram,
		const EST_String &	filename,
		double &	raw_entropy,
		double &	count,
		double &	entropy,
		double &	perplexity,
		const EST_String &	input_format,
		const EST_String &	prev = SENTENCE_START_MARKER,
		const EST_String &	prev_prev = SENTENCE_END_MARKER,
		const EST_String &	last = SENTENCE_END_MARKER
	)

Definition at line 89 of file ngrammar_utils.cc.