Class analysis stores a possible reading (lemma, PoS, probability, distance) for a word. More...

#include <language.h>

Public Member Functions
	analysis ()
	constructor
	analysis (const std::wstring &, const std::wstring &)
	constructor
analysis &	operator= (const analysis &)
	assignment
void	set_lemma (const std::wstring &)
	Set lemma for analysis.
void	set_tag (const std::wstring &)
	Set PoS tag for analysis.
void	set_prob (double)
	Set probability for analysis.
void	set_distance (double)
	Set distance for analysis.
void	set_retokenizable (const std::list< word > &)
	Set retokenization info for analysis.
bool	has_prob () const
	Check whether probability has been set.
bool	has_distance () const
	Check whether distance has been set.
std::wstring	get_lemma () const
	Get lemma value for analysis.
std::wstring	get_tag () const
	Get PoS tag value for analysis.
std::wstring	get_short_tag () const
	Get short version of the PoS tag for the analysis, assuming usual EAGLES tagset.
std::wstring	get_short_tag (const std::wstring &) const
double	get_prob () const
	Get probability value for analysis (-1 if not set).
double	get_distance () const
	Get distance value for analysis (-1 if not set).
bool	is_retokenizable () const
	Find out if the analysis may imply retokenization.
std::list< word >	get_retokenizable () const
	Get retokenization info for analysis.
std::list< std::pair < std::wstring, double > >	get_senses () const
	get analysis sense list
void	set_senses (const std::list< std::pair< std::wstring, double > > &)
	set analiysis sense list
std::wstring	get_senses_string () const
int	max_kbest () const
bool	is_selected (int k=0) const
	find out whether the analysis is selected in the tagger k-th best sequence
void	mark_selected (int k=0)
	mark this analysis as selected in k-th best sequence
void	unmark_selected (int k=0)
	unmark this analysis as selected in k-th best sequence
bool	operator< (const analysis &) const
	Comparison to sort analysis by decreasing probability.
bool	operator== (const analysis &) const
	Comparison (to please MSVC)
Public Attributes
std::vector< std::wstring >	user
	user-managed data, we just store it.
Private Member Functions
std::wstring	shorten_tag (const std::wstring &s=L"V") const
	Get short version of the PoS tag for the analysis, assigning 3 digits to categories listed in "s".
Private Attributes
std::wstring	lemma
	lemma
std::wstring	tag
	PoS tag.
double	prob
	probability of that lemma-tag given the word
double	distance
	distance from a added analysis from corrector to the original word
std::list< std::pair < std::wstring, double > >	senses
	list of possible senses for that analysis, along with their rank as attributed by the ukb PPR algorithm
std::list< word >	retok
	information to retokenize the word after tagging if this analysis is selected
std::set< int >	selected_kbest
Static Private Attributes
static std::map< std::wstring, std::wstring >	stag_cache
	Class analysis stores a possible reading (lemma, PoS, probability, distance) for a word.

Detailed Description

Class analysis stores a possible reading (lemma, PoS, probability, distance) for a word.

Constructor & Destructor Documentation

analysis::analysis ( )

constructor

Create empty analysis.

analysis::analysis	(	const std::wstring &	,
		const std::wstring &
	)

constructor

Member Function Documentation

double analysis::get_distance ( ) const

Get distance value for analysis (-1 if not set).

wstring analysis::get_lemma ( ) const

Get lemma value for analysis.

double analysis::get_prob ( ) const

Get probability value for analysis (-1 if not set).

list< word > analysis::get_retokenizable ( ) const

Get retokenization info for analysis.

list< pair< wstring, double > > analysis::get_senses ( ) const

get analysis sense list

wstring analysis::get_senses_string ( ) const

References util::pairlist2wstring().

wstring analysis::get_short_tag ( ) const

Get short version of the PoS tag for the analysis, assuming usual EAGLES tagset.

Referenced by probabilities::guesser(), and hmm_tagger::hmm_tagger().

std::wstring analysis::get_short_tag ( const std::wstring & ) const

wstring analysis::get_tag ( ) const

Get PoS tag value for analysis.

bool analysis::has_distance ( ) const

Check whether distance has been set.

bool analysis::has_prob ( ) const

Check whether probability has been set.

bool analysis::is_retokenizable ( ) const

Find out if the analysis may imply retokenization.

bool analysis::is_selected ( int k = 0 ) const

find out whether the analysis is selected in the tagger k-th best sequence

void analysis::mark_selected ( int k = 0 )

mark this analysis as selected in k-th best sequence

int analysis::max_kbest ( ) const

bool analysis::operator< ( const analysis & a ) const

Comparison to sort analysis by *decreasing* probability.

Comparison to sort analysis by *decreasing* probability and ascending alphabetical tag.

References prob, and tag.

analysis & analysis::operator= ( const analysis & a )

assignment

Assignment.

References distance, lemma, prob, retok, selected_kbest, senses, tag, and user.

bool analysis::operator== ( const analysis & a ) const

Comparison (to please MSVC)

comparison (just to please MSVC)

References lemma, and tag.

void analysis::set_distance ( double d )

Set distance for analysis.

void analysis::set_lemma ( const std::wstring & )

Set lemma for analysis.

void analysis::set_prob ( double p )

Set probability for analysis.

Referenced by senses::analyze(), and probabilities::guesser().

void analysis::set_retokenizable ( const std::list< word > & )

Set retokenization info for analysis.

Referenced by affixes::ApplyRule().

void analysis::set_senses ( const std::list< std::pair< std::wstring, double > > & )

set analiysis sense list

Referenced by senses::analyze().

void analysis::set_tag ( const std::wstring & )

Set PoS tag for analysis.

wstring analysis::shorten_tag ( const std::wstring & s = L"V" ) const [private]

Get short version of the PoS tag for the analysis, assigning 3 digits to categories listed in "s".

void analysis::unmark_selected ( int k = 0 )

unmark this analysis as selected in k-th best sequence

Member Data Documentation

double analysis::distance [private]

distance from a added analysis from corrector to the original word

Referenced by operator=().

std::wstring analysis::lemma [private]

lemma

Referenced by operator=(), and operator==().

double analysis::prob [private]

probability of that lemma-tag given the word

Referenced by operator<(), and operator=().

std::list<word> analysis::retok [private]

information to retokenize the word after tagging if this analysis is selected

Referenced by operator=().

std::set<int> analysis::selected_kbest [private]

Referenced by operator=().

std::list<std::pair<std::wstring,double> > analysis::senses [private]

list of possible senses for that analysis, along with their rank as attributed by the ukb PPR algorithm

Referenced by operator=().

map< wstring, wstring > analysis::stag_cache [static, private]

Class analysis stores a possible reading (lemma, PoS, probability, distance) for a word.

static cache for shortening tags.

std::wstring analysis::tag [private]

PoS tag.

Referenced by operator<(), operator=(), and operator==().

std::vector<std::wstring> analysis::user

user-managed data, we just store it.

Referenced by operator=().

The documentation for this class was generated from the following files:

Public Member Functions

Public Attributes

Private Member Functions

Private Attributes

Static Private Attributes

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation