optionally sample from forest to get training instances, rather than k-best it

1 files changed, 27 insertions, 0 deletions

diff --git a/decoder/hg_sampler.h b/decoder/hg_sampler.h
new file mode 100644
index 00000000..bf4e1eb0
--- /dev/null
+++ b/decoder/hg_sampler.h
@@ -0,0 +1,27 @@
+#ifndef _HG_SAMPLER_H_
+#define _HG_SAMPLER_H_
+
+
+#include <vector>
+#include "sparse_vector.h"
+#include "sampler.h"
+#include "wordid.h"
+
+class Hypergraph;
+
+struct HypergraphSampler {
+
+  struct Hypothesis {
+    std::vector<WordID> words;
+    SparseVector<double> fmap;
+    prob_t model_score;   // log unnormalized probability
+  };
+
+  static void
+  sample_hypotheses(const Hypergraph& hg,
+                    unsigned n,   // how many samples to draw
+                    MT19937* rng,
+                    std::vector<Hypothesis>* hypos);
+};
+
+#endif