32 typedef fst::LexicographicArc< fst::StdArc::Weight, fst::StdArc::Weight> Arc;
33 typedef fst::LexicographicWeight<fst::StdArc::Weight, fst::StdArc::Weight>
52 unordered_map<std::size_t, std::string>
oovwmap;
64 unordered_map<std::string, std::vector< pair <uint, uint> > >
hpinstances;
70 unordered_set<std::string>
tvcb;
76 boost::shared_ptr<ucam::fsttools::StatsData>
stats;
85 unordered_map<std::string, ucam::util::WordMapper *>
wm;
unordered_map< std::size_t, std::string > oovwmap
Contains oovs.
Data structure containing all cyk-related information.
Data class containing relevant variables. To be used as template for task classes using it...
unordered_map< std::string, ucam::util::WordMapper * > wm
Wordmap/Integer map objects.
boost::shared_ptr< ucam::fsttools::StatsData > stats
To collect statistics across the whole pipeline.
Struct containing grammar rules.
unordered_set< std::string > * recasingvcblm
mixed-case vocabulary of the recasing unigram language model
std::string * translation
Translated sentence will be stored here.
std::string originalsentence
source sentence
const GrammarData * grammar
Contains translation grammar.
std::string tokenizedsentence
unordered_map< std::string, std::vector< pair< uint, uint > > > hpinstances
std::vector< std::string > pinstances
Pattern instances.
Structure for sentence-specific grammar Rules will be queried by cyk per position and number of eleme...
unordered_set< std::string > tvcb
Target vocabulary.
SentenceSpecificGrammarData * ssgd
Sentence-specific grammar information – hashes to rule indices.
CYKdata * cykdata
cyk data structures