diff options
Diffstat (limited to 'dtrain/score.cc')
| -rw-r--r-- | dtrain/score.cc | 16 |
1 files changed, 12 insertions, 4 deletions
diff --git a/dtrain/score.cc b/dtrain/score.cc index d0f9e8a0..b09d32ba 100644 --- a/dtrain/score.cc +++ b/dtrain/score.cc @@ -18,11 +18,15 @@ BleuScorer::Bleu(NgramCounts& counts, const unsigned hyp_len, const unsigned ref { if (hyp_len == 0 || ref_len == 0) return 0.; unsigned M = N_; - if (ref_len < N_) M = ref_len; + vector<score_t> v = w_; + if (ref_len < N_) { + M = ref_len; + for (unsigned i = 0; i < M; i++) v[i] = 1./((score_t)M); + } score_t sum = 0; for (unsigned i = 0; i < M; i++) { if (counts.sum_[i] == 0 || counts.clipped_[i] == 0) return 0.; - sum += w_[i] * log((score_t)counts.clipped_[i]/counts.sum_[i]); + sum += v[i] * log((score_t)counts.clipped_[i]/counts.sum_[i]); } return brevity_penalty(hyp_len, ref_len) * exp(sum); } @@ -55,12 +59,16 @@ StupidBleuScorer::Score(vector<WordID>& hyp, vector<WordID>& ref, if (hyp_len == 0 || ref_len == 0) return 0.; NgramCounts counts = make_ngram_counts(hyp, ref, N_); unsigned M = N_; - if (ref_len < N_) M = ref_len; + vector<score_t> v = w_; + if (ref_len < N_) { + M = ref_len; + for (unsigned i = 0; i < M; i++) v[i] = 1./((score_t)M); + } score_t sum = 0, add = 0; for (unsigned i = 0; i < M; i++) { if (i == 0 && (counts.sum_[i] == 0 || counts.clipped_[i] == 0)) return 0.; if (i == 1) add = 1; - sum += w_[i] * log(((score_t)counts.clipped_[i] + add)/((counts.sum_[i] + add))); + sum += v[i] * log(((score_t)counts.clipped_[i] + add)/((counts.sum_[i] + add))); } return brevity_penalty(hyp_len, ref_len) * exp(sum); } |