BaseTagger Class Reference

#include <tagger_base.h>

Inheritance diagram for BaseTagger:

Collaboration diagram for BaseTagger:

Public Member Functions
	BaseTagger (TiCC::LogStream *, TiCC::LogStream *, const std::string &)
virtual	~BaseTagger ()
virtual bool	init (const TiCC::Configuration &)
virtual void	post_process (frog_data &)=0
virtual void	Classify (frog_data &)
virtual void	add_declaration (folia::Document &, folia::processor *) const =0
void	add_provenance (folia::Document &, folia::processor *) const
std::string	getTagset () const
std::string	set_eos_mark (const std::string &)
bool	fill_map (const std::string &, std::map< std::string, std::string > &)
std::vector< Tagger::TagResult >	tagLine (const std::string &)
std::vector< Tagger::TagResult >	tag_entries (const std::vector< tag_entry > &)
std::string	version () const

Protected Member Functions
void	extract_words_tags (const std::vector< folia::Word * > &, const std::string &, std::vector< std::string > &, std::vector< std::string > &)
std::vector< Tagger::TagResult >	call_server (const std::vector< tag_entry > &) const
	BaseTagger (const BaseTagger &)

Protected Attributes
int	debug
std::string	_label
std::string	tagset
std::string	_version
std::string	textclass
TiCC::LogStream *	err_log
TiCC::LogStream *	dbg_log
std::string	base
std::string	_host
std::string	_port
MbtAPI *	tagger
TiCC::UniFilter *	filter
std::vector< std::string >	_words
std::vector< Tagger::TagResult >	_tag_result
std::map< std::string, std::string >	token_tag_map

Constructor & Destructor Documentation

BaseTagger() [1/2]

BaseTagger::BaseTagger ( TiCC::LogStream *  errlog, TiCC::LogStream *  dbglog, const std::string &  label  )

explicit

~BaseTagger()

BaseTagger::~BaseTagger ( )

virtual

BaseTagger() [2/2]

BaseTagger::BaseTagger ( const BaseTagger &  )

inlineprotected

Member Function Documentation

add_declaration()

virtual void BaseTagger::add_declaration ( folia::Document &  , folia::processor *    ) const

pure virtual

Implemented in NERTagger, CGNTagger, and IOBTagger.

add_provenance()

void BaseTagger::add_provenance	(	folia::Document &	doc,
		folia::processor *	main
	)		const

add provenance information for this tagger. (FoLiA output only)

Parameters

doc	the FoLiA document to add to
main	the processor to use (presumably the Frog processor)

call_server()

vector< TagResult > BaseTagger::call_server ( const std::vector< tag_entry > &  tv ) const

protected

Connect to a MBT server, send and receive JSON and translate to a TagResult list

Parameters

tv	the tag_entry we would like to be seviced

Returns

a vector of TagResult elements

We set up a connection to the configured server, send a query in JSON and on succesful receiving back a JSON result we convert it back into a TagResult vector

Note

So this is a one-shot operation. No connection to the MBT server is kept open.

Classify()

void BaseTagger::Classify ( frog_data &  sent )

virtual

Tag one sentence, give in frog_data format

Parameters

sent	the frog_data structure to analyze

When tagging succeeds, 'sent' will be extended with the tag results

Reimplemented in NERTagger, and IOBTagger.

extract_words_tags()

void BaseTagger::extract_words_tags ( const std::vector< folia::Word * > &  swords, const std::string &  tagset, std::vector< std::string > &  words, std::vector< std::string > &  ptags  )

protected

extract word and POS-tag information from a list of folia::Word

fill_map()

bool BaseTagger::fill_map	(	const std::string &	file,
		std::map< std::string, std::string > &	mp
	)

fill a map op string-string vales from a fie

Parameters

file	the filenam
mp	the map to fill

Returns

true on succes, false otherwise

the file should contain lines with TAB separated attribute/value pairs

lines starting with '#' are seen as comment

getTagset()

std::string BaseTagger::getTagset ( ) const

inline

init()

bool BaseTagger::init ( const TiCC::Configuration &  config )

virtual

initalize a tagger from 'config'

Parameters

config

the TiCC::Configuration

Returns

true on succes, false otherwise

Reimplemented in NERTagger, CGNTagger, and IOBTagger.

post_process()

virtual void BaseTagger::post_process ( frog_data &  )

pure virtual

Implemented in NERTagger, CGNTagger, and IOBTagger.

set_eos_mark()

string BaseTagger::set_eos_mark

(

const std::string &

eos

)

set the EOS marker for the tagger

Parameters

eos	the eos marker as a string

Returns

the old value

tag_entries()

vector< TagResult > BaseTagger::tag_entries

(

const std::vector< tag_entry > &

to_do

)

tag a vector of teag_entry into a vector of TagResult elements

Parameters

to_do

a vector of tag_entry elements representing 1 sentence

tagLine()

vector< TagResult > BaseTagger::tagLine

(

const std::string &

line

)

tag a string into a vector of TagResult elements

Parameters

line	a (UTF8 encoded) string, may be multilined and include Enrichments

Returns

a vector of TagResult

Depending on the configurarion, the input is send to the local MBT tagger or the associated MBT server.

version()

std::string BaseTagger::version ( ) const

inline

Member Data Documentation

_host

std::string BaseTagger::_host

protected

_label

std::string BaseTagger::_label

protected

_port

std::string BaseTagger::_port

protected

_tag_result

std::vector<Tagger::TagResult> BaseTagger::_tag_result

protected

_version

std::string BaseTagger::_version

protected

_words

std::vector<std::string> BaseTagger::_words

protected

base

std::string BaseTagger::base

protected

dbg_log

TiCC::LogStream* BaseTagger::dbg_log

protected

debug

int BaseTagger::debug

protected

err_log

TiCC::LogStream* BaseTagger::err_log

protected

filter

TiCC::UniFilter* BaseTagger::filter

protected

tagger

MbtAPI* BaseTagger::tagger

protected

tagset

std::string BaseTagger::tagset

protected

textclass

std::string BaseTagger::textclass

protected

token_tag_map

std::map<std::string,std::string> BaseTagger::token_tag_map

protected

---

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

• include/frog/tagger_base.h
• src/tagger_base.cxx