n-best tree output

moses-chart-cmd/IOWrapper.cpp

@@ -712,6 +712,8 @@ void IOWrapper::OutputNBestList(const ChartKBestExtractor::KBestVec &nBestList,
   bool includeWordAlignment =
       StaticData::Instance().PrintAlignmentInfoInNbest();
 
+  bool PrintNBestTrees = StaticData::Instance().PrintNBestTrees();
+
   for (ChartKBestExtractor::KBestVec::const_iterator p = nBestList.begin();
        p != nBestList.end(); ++p) {
     const ChartKBestExtractor::Derivation &derivation = **p;
@@ -743,6 +745,12 @@ void IOWrapper::OutputNBestList(const ChartKBestExtractor::KBestVec &nBestList,
       }
     }
 
+    // optionally, print tree
+    if (PrintNBestTrees) {
+      TreePointer tree = ChartKBestExtractor::GetOutputTree(derivation);
+      out << " ||| " << tree->GetString();
+    }
+
     out << std::endl;
   }
 

moses-chart-cmd/IOWrapper.h

@@ -128,6 +128,7 @@ public:
   void OutputBestNone(long translationId);
   void OutputNBestList(const std::vector<boost::shared_ptr<Moses::ChartKBestExtractor::Derivation> > &nBestList, long translationId);
   void OutputNBestList(const std::vector<search::Applied> &nbest, long translationId);
+  void OutputNBestTrees(const std::vector<boost::shared_ptr<Moses::ChartKBestExtractor::Derivation> > &nBestList, long translationId);
   void OutputDetailedTranslationReport(const Moses::ChartHypothesis *hypo, const Moses::Sentence &sentence, long translationId);
   void OutputDetailedTranslationReport(const search::Applied *applied, const Moses::Sentence &sentence, long translationId);
   void OutputDetailedTreeFragmentsTranslationReport(const Moses::ChartHypothesis *hypo, const Moses::Sentence &sentence, long translationId);

moses/ChartKBestExtractor.cpp

@@ -124,6 +124,35 @@ Phrase ChartKBestExtractor::GetOutputPhrase(const Derivation &d)
   return ret;
 }
 
+// Generate the target tree of the derivation d.
+TreePointer ChartKBestExtractor::GetOutputTree(const Derivation &d)
+{
+  const ChartHypothesis &hypo = d.edge.head->hypothesis;
+  const TargetPhrase &phrase = hypo.GetCurrTargetPhrase();
+  if (const PhraseProperty *property = phrase.GetProperty("Tree")) {
+    const std::string *tree = property->GetValueString();
+    TreePointer mytree (boost::make_shared<InternalTree>(*tree));
+
+    //get subtrees (in target order)
+    std::vector<TreePointer> previous_trees;
+    for (size_t pos = 0; pos < phrase.GetSize(); ++pos) {
+      const Word &word = phrase.GetWord(pos);
+      if (word.IsNonTerminal()) {
+        size_t nonTermInd = phrase.GetAlignNonTerm().GetNonTermIndexMap()[pos];
+        const Derivation &subderivation = *d.subderivations[nonTermInd];
+        const TreePointer prev_tree = GetOutputTree(subderivation);
+        previous_trees.push_back(prev_tree);
+      }
+    }
+
+    mytree->Combine(previous_trees);
+    return mytree;
+  }
+  else {
+    UTIL_THROW2("Error: TreeStructureFeature active, but no internal tree structure found");
+  }
+}
+
 // Create an unweighted hyperarc corresponding to the given ChartHypothesis.
 ChartKBestExtractor::UnweightedHyperarc ChartKBestExtractor::CreateEdge(
     const ChartHypothesis &h)

moses/ChartKBestExtractor.h

@@ -22,6 +22,7 @@
 #include <cassert>
 #include "ChartHypothesis.h"
 #include "ScoreComponentCollection.h"
+#include "FF/InternalTree.h"
 
 #include <boost/unordered_set.hpp>
 #include <boost/weak_ptr.hpp>
@@ -89,6 +90,7 @@ public:
                std::size_t k, KBestVec &);
 
   static Phrase GetOutputPhrase(const Derivation &);
+  static TreePointer GetOutputTree(const Derivation &);
 
 private:
   typedef boost::unordered_map<const ChartHypothesis *,

moses/Parameter.cpp

@@ -57,6 +57,7 @@ Parameter::Parameter()
   AddParam("max-trans-opt-per-coverage", "maximum number of translation options per input span (after applying mapping steps)");
   AddParam("max-phrase-length", "maximum phrase length (default 20)");
   AddParam("n-best-list", "file and size of n-best-list to be generated; specify - as the file in order to write to STDOUT");
+  AddParam("n-best-trees", "Write n-best target-side trees (additional to normal n-best-list) to file {n-best-list-file}.trees");
   AddParam("lattice-samples", "generate samples from lattice, in same format as nbest list. Uses the file and size arguments, as in n-best-list");
   AddParam("n-best-factor", "factor to compute the maximum number of contenders (=factor*nbest-size). value 0 means infinity, i.e. no threshold. default is 0");
   AddParam("print-all-derivations", "to print all derivations in search graph");

moses/StaticData.cpp

@@ -431,6 +431,7 @@ bool StaticData::LoadData(Parameter *parameter)
   if (m_useConsensusDecoding) m_mbr=true;
 
   SetBooleanParameter( &m_defaultNonTermOnlyForEmptyRange, "default-non-term-for-empty-range-only", false );
+  SetBooleanParameter( &m_printNBestTrees, "n-best-trees", false );
 
 
   // Compact phrase table and reordering model

moses/StaticData.h

@@ -199,6 +199,7 @@ protected:
   FactorType m_placeHolderFactor;
   bool m_useLegacyPT;
   bool m_defaultNonTermOnlyForEmptyRange;
+  bool m_printNBestTrees;
 
   FeatureRegistry m_registry;
   PhrasePropertyFactory m_phrasePropertyFactory;
@@ -766,6 +767,10 @@ public:
   bool GetDefaultNonTermOnlyForEmptyRange() const
   { return m_defaultNonTermOnlyForEmptyRange; }
 
+  bool PrintNBestTrees() const {
+    return m_printNBestTrees;
+  }
+
 };
 
 }