From 6ba464f6d78e38970d5467b10ce1114f4d7feaa4 Mon Sep 17 00:00:00 2001
From: Chris Dyer <cdyer@cs.cmu.edu>
Date: Tue, 7 Aug 2012 23:22:44 -0400
Subject: sample trees from hypergraphs

---
 decoder/hg_sampler.cc | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++
 decoder/hg_sampler.h  |  7 +++++++
 2 files changed, 62 insertions(+)

(limited to 'decoder')

diff --git a/decoder/hg_sampler.cc b/decoder/hg_sampler.cc
index cdf0ec3c..c4d3dede 100644
--- a/decoder/hg_sampler.cc
+++ b/decoder/hg_sampler.cc
@@ -71,3 +71,58 @@ void HypergraphSampler::sample_hypotheses(const Hypergraph& hg,
     Viterbi(hg, &hyp.words, ESentenceTraversal(), SampledDerivationWeightFunction(sampled_edges));
   }
 }
+
+void HypergraphSampler::sample_trees(const Hypergraph& hg,
+                                     unsigned n,
+                                     MT19937* rng,
+                                     vector<string>* trees) {
+  trees->clear();
+  trees->resize(n);
+
+  // compute inside probabilities
+  vector<prob_t> node_probs;
+  Inside<prob_t, EdgeProb>(hg, &node_probs, EdgeProb());
+
+  vector<bool> sampled_edges(hg.edges_.size());
+  queue<unsigned> q;
+  SampleSet<prob_t> ss;
+  for (unsigned i = 0; i < n; ++i) {
+    fill(sampled_edges.begin(), sampled_edges.end(), false);
+    // sample derivation top down
+    assert(q.empty());
+    q.push(hg.nodes_.size() - 1);
+    prob_t model_score = prob_t::One();
+    while(!q.empty()) {
+      unsigned cur_node_id = q.front();
+      q.pop();
+      const Hypergraph::Node& node = hg.nodes_[cur_node_id];
+      const unsigned num_in_edges = node.in_edges_.size();
+      unsigned sampled_edge_idx = 0;
+      if (num_in_edges == 1) {
+        sampled_edge_idx = node.in_edges_[0];
+      } else {
+        assert(num_in_edges > 1);
+        ss.clear();
+        for (unsigned j = 0; j < num_in_edges; ++j) {
+          const Hypergraph::Edge& edge = hg.edges_[node.in_edges_[j]];
+          prob_t p = edge.edge_prob_;   // edge weight
+          for (unsigned k = 0; k < edge.tail_nodes_.size(); ++k)
+            p *= node_probs[edge.tail_nodes_[k]];  // tail node inside weight
+          ss.add(p);
+        }
+        sampled_edge_idx = node.in_edges_[rng->SelectSample(ss)];
+      }
+      sampled_edges[sampled_edge_idx] = true;
+      const Hypergraph::Edge& sampled_edge = hg.edges_[sampled_edge_idx];
+      model_score *= sampled_edge.edge_prob_;
+      //sampled_deriv->push_back(sampled_edge_idx);
+      for (unsigned j = 0; j < sampled_edge.tail_nodes_.size(); ++j) {
+        q.push(sampled_edge.tail_nodes_[j]);
+      }
+    }
+    vector<WordID> tmp;
+    Viterbi(hg, &tmp, ETreeTraversal(), SampledDerivationWeightFunction(sampled_edges));
+    (*trees)[n] = TD::GetString(tmp);
+  }
+}
+
diff --git a/decoder/hg_sampler.h b/decoder/hg_sampler.h
index bf4e1eb0..6ac39a20 100644
--- a/decoder/hg_sampler.h
+++ b/decoder/hg_sampler.h
@@ -3,6 +3,7 @@
 
 
 #include <vector>
+#include <string>
 #include "sparse_vector.h"
 #include "sampler.h"
 #include "wordid.h"
@@ -22,6 +23,12 @@ struct HypergraphSampler {
                     unsigned n,   // how many samples to draw
                     MT19937* rng,
                     std::vector<Hypothesis>* hypos);
+
+  static void
+  sample_trees(const Hypergraph& hg,
+               unsigned n,
+               MT19937* rng,
+               std::vector<std::string>* trees);
 };
 
 #endif
-- 
cgit v1.2.3