Cambridge SMT System
|
data structure for disambig tool. It needs at least a mixed case language model, mixed-case vocabulary and a transduction unigram model. More...
#include <data-main.disambig.hpp>
Public Member Functions | |
DisambigData () | |
Public Attributes | |
uint | sidx |
Sentence index. More... | |
unordered_map< std::string, std::vector< const KenLMData * > > | klm |
lists of language models indexed by a key (i.e. parameter ) More... | |
unordered_set< std::string > * | recasingvcblm |
Mixed case vocabulary used by the unigram model and the language model. More... | |
unordered_map< std::string, void * > | fsts |
Unigram model to be stored here. More... | |
StatsData * | stats |
unordered_map< std::string, ucam::util::WordMapper * > | wm |
Wordmap/Integer map objects. More... | |
data structure for disambig tool. It needs at least a mixed case language model, mixed-case vocabulary and a transduction unigram model.
Definition at line 32 of file data-main.disambig.hpp.
|
inline |
Definition at line 33 of file data-main.disambig.hpp.
unordered_map<std::string, void * > ucam::fsttools::DisambigData::fsts |
Unigram model to be stored here.
Definition at line 47 of file data-main.disambig.hpp.
unordered_map<std::string, std::vector <const KenLMData*> > ucam::fsttools::DisambigData::klm |
lists of language models indexed by a key (i.e. parameter )
Definition at line 43 of file data-main.disambig.hpp.
unordered_set<std::string>* ucam::fsttools::DisambigData::recasingvcblm |
Mixed case vocabulary used by the unigram model and the language model.
Definition at line 45 of file data-main.disambig.hpp.
uint ucam::fsttools::DisambigData::sidx |
Sentence index.
Definition at line 37 of file data-main.disambig.hpp.
StatsData* ucam::fsttools::DisambigData::stats |
Definition at line 49 of file data-main.disambig.hpp.
unordered_map<std::string, ucam::util::WordMapper *> ucam::fsttools::DisambigData::wm |
Wordmap/Integer map objects.
Definition at line 52 of file data-main.disambig.hpp.