summaryrefslogtreecommitdiff
path: root/training/dtrain/score.cc
diff options
context:
space:
mode:
authorPaul Baltescu <pauldb89@gmail.com>2013-04-24 17:18:10 +0100
committerPaul Baltescu <pauldb89@gmail.com>2013-04-24 17:18:10 +0100
commitba206aaac1d95e76126443c9e7ccc5941e879849 (patch)
tree13a918da3f3983fd8e4cb74e7cdc3f5e1fc01cd1 /training/dtrain/score.cc
parentc2aede0f19b7a5e43581768b8c4fbfae8b92c68c (diff)
parentdb960a8bba81df3217660ec5a96d73e0d6baa01b (diff)
Merge branch 'master' of https://github.com/redpony/cdec
Diffstat (limited to 'training/dtrain/score.cc')
-rw-r--r--training/dtrain/score.cc31
1 files changed, 30 insertions, 1 deletions
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