diff options
Diffstat (limited to 'training/dtrain/kbestget.h')
-rw-r--r-- | training/dtrain/kbestget.h | 66 |
1 files changed, 1 insertions, 65 deletions
diff --git a/training/dtrain/kbestget.h b/training/dtrain/kbestget.h index dd8882e1..85252db3 100644 --- a/training/dtrain/kbestget.h +++ b/training/dtrain/kbestget.h @@ -1,76 +1,12 @@ #ifndef _DTRAIN_KBESTGET_H_ #define _DTRAIN_KBESTGET_H_ -#include "kbest.h" // cdec -#include "sentence_metadata.h" - -#include "verbose.h" -#include "viterbi.h" -#include "ff_register.h" -#include "decoder.h" -#include "weights.h" -#include "logval.h" - -using namespace std; +#include "kbest.h" namespace dtrain { -typedef double score_t; - -struct ScoredHyp -{ - vector<WordID> w; - SparseVector<double> f; - score_t model; - score_t score; - unsigned rank; -}; - -struct LocalScorer -{ - unsigned N_; - vector<score_t> w_; - - virtual score_t - Score(vector<WordID>& hyp, vector<WordID>& ref, const unsigned rank, const unsigned src_len)=0; - - void Reset() {} // only for approx bleu - - inline void - Init(unsigned N, vector<score_t> weights) - { - assert(N > 0); - N_ = N; - if (weights.empty()) for (unsigned i = 0; i < N_; i++) w_.push_back(1./N_); - else w_ = weights; - } - - inline score_t - brevity_penalty(const unsigned hyp_len, const unsigned ref_len) - { - if (hyp_len > ref_len) return 1; - return exp(1 - (score_t)ref_len/hyp_len); - } -}; - -struct HypSampler : public DecoderObserver -{ - LocalScorer* scorer_; - vector<WordID>* ref_; - unsigned f_count_, sz_; - virtual vector<ScoredHyp>* GetSamples()=0; - inline void SetScorer(LocalScorer* scorer) { scorer_ = scorer; } - inline void SetRef(vector<WordID>& ref) { ref_ = &ref; } - inline unsigned get_f_count() { return f_count_; } - inline unsigned get_sz() { return sz_; } -}; -//////////////////////////////////////////////////////////////////////////////// - - - - struct KBestGetter : public HypSampler { const unsigned k_; |