From 105a52a8d37497fe69a01a7de771ef9b9300cd71 Mon Sep 17 00:00:00 2001
From: Chris Dyer <cdyer@cs.cmu.edu>
Date: Fri, 11 Nov 2011 17:12:39 -0500
Subject: optionally sample from forest to get training instances, rather than
 k-best it

---
 decoder/hg_sampler.h | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 decoder/hg_sampler.h

(limited to 'decoder/hg_sampler.h')

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
-- 
cgit v1.2.3