added fixed BLEU+1

3 files changed, 37 insertions, 1 deletions

diff --git a/training/dtrain/dtrain.cc b/training/dtrain/dtrain.cc
index b317c365..53487d34 100644
--- a/training/dtrain/dtrain.cc
+++ b/training/dtrain/dtrain.cc
@@ -163,6 +163,8 @@ main(int argc, char** argv)
     scorer = dynamic_cast<BleuScorer*>(new BleuScorer);
   } else if (scorer_str == "stupid_bleu") {
     scorer = dynamic_cast<StupidBleuScorer*>(new StupidBleuScorer);
+  } else if (scorer_str == "fixed_stupid_bleu") {
+    scorer = dynamic_cast<FixedStupidBleuScorer*>(new FixedStupidBleuScorer);
   } else if (scorer_str == "smooth_bleu") {
     scorer = dynamic_cast<SmoothBleuScorer*>(new SmoothBleuScorer);
   } else if (scorer_str == "sum_bleu") {
diff --git a/training/dtrain/score.cc b/training/dtrain/score.cc
index 34fc86a9..96d6e10a 100644
--- a/training/dtrain/score.cc
+++ b/training/dtrain/score.cc
@@ -49,7 +49,7 @@ BleuScorer::Score(vector<WordID>& hyp, vector<WordID>& ref,
  *        for Machine Translation"
  * (Lin & Och '04)
  *
- * NOTE: 0 iff no 1gram match
+ * NOTE: 0 iff no 1gram match ('grounded')
  */
 score_t
 StupidBleuScorer::Score(vector<WordID>& hyp, vector<WordID>& ref,
@@ -74,6 +74,35 @@ StupidBleuScorer::Score(vector<WordID>& hyp, vector<WordID>& ref,
 }
 
 /*
+ * fixed 'stupid' bleu
+ *
+ * as in "Optimizing for Sentence-Level BLEU+1
+ *        Yields Short Translations"
+ * (Nakov et al. '12)
+ */
+score_t
+FixedStupidBleuScorer::Score(vector<WordID>& hyp, vector<WordID>& ref,
+                        const unsigned /*rank*/, const unsigned /*src_len*/)
+{
+  unsigned hyp_len = hyp.size(), ref_len = ref.size();
+  if (hyp_len == 0 || ref_len == 0) return 0.;
+  NgramCounts counts = make_ngram_counts(hyp, ref, N_);
+  unsigned M = N_;
+  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 += v[i] * log(((score_t)counts.clipped_[i] + add)/((counts.sum_[i] + add)));
+  }
+  return  brevity_penalty(hyp_len, ref_len+1) * exp(sum); // <- fix
+}
+
+/*
  * smooth bleu
  *
  * as in "An End-to-End Discriminative Approach
diff --git a/training/dtrain/score.h b/training/dtrain/score.h
index f317c903..bddaa071 100644
--- a/training/dtrain/score.h
+++ b/training/dtrain/score.h
@@ -148,6 +148,11 @@ struct StupidBleuScorer : public LocalScorer
   score_t Score(vector<WordID>& hyp, vector<WordID>& ref, const unsigned /*rank*/, const unsigned /*src_len*/);
 };
 
+struct FixedStupidBleuScorer : public LocalScorer
+{
+  score_t Score(vector<WordID>& hyp, vector<WordID>& ref, const unsigned /*rank*/, const unsigned /*src_len*/);
+};
+
 struct SmoothBleuScorer : public LocalScorer
 {
   score_t Score(vector<WordID>& hyp, vector<WordID>& ref, const unsigned /*rank*/, const unsigned /*src_len*/);