cdec now supports coarse-to-fine decoding (for SCFG only).

CTF has several options:

-coarse_to_fine_beam_prune=<double> (required to activate CTF)
  assign an alpha parameter for pruning the coarse foreast

-ctf_beam_widen=<double> (optional, defaults to 2.0):
  ratio to widen coarse pruning beam if fine parse fails.

-ctf_num_widenings=<int> (optional, defaults to 2):
  number of times to widen coarse beam before defaulting to exhaustive
  source parsing

-ctf_no_exhaustive (optional)
  do not attempt exhaustive parse if CTF fails to find a parse.

Additionally, script extools/coarsen_grammar.pl will create a
coarse-to-fine grammar (for X?? categories *only*).  cdec will
read CTF grammars in a format identical to the original, in which
refinements of a rule immediately follow the coarse projection,
preceded by an additional whitespace character.

Not fully tested, but should be backwards compatible.  Also not
yet integrated into pipelines, but should work on the command line.

git-svn-id: https://ws10smt.googlecode.com/svn/trunk@231 ec762483-ff6d-05da-a07a-a48fb63a330f

1 files changed, 8 insertions, 0 deletions

diff --git a/decoder/trule.h b/decoder/trule.h
index defdbeb9..3bc96165 100644
--- a/decoder/trule.h
+++ b/decoder/trule.h
@@ -34,6 +34,9 @@ class TRule {
   TRule(const std::vector<WordID>& e, const std::vector<WordID>& f, const WordID& lhs) :
     e_(e), f_(f), lhs_(lhs), prev_i(-1), prev_j(-1) {}
 
+  TRule(const TRule& other) :
+    e_(other.e_), f_(other.f_), lhs_(other.lhs_), scores_(other.scores_), arity_(other.arity_), prev_i(-1), prev_j(-1) {}
+
   // deprecated - this will be private soon
   explicit TRule(const std::string& text, bool strict = false, bool mono = false) : prev_i(-1), prev_j(-1) {
     ReadFromString(text, strict, mono);
@@ -130,6 +133,8 @@ class TRule {
   SparseVector<double> scores_;
 
   char arity_;
+  
+  // these attributes are application-specific and should probably be refactored 
   TRulePtr parent_rule_;  // usually NULL, except when doing constrained decoding
 
   // this is only used when doing synchronous parsing
@@ -139,6 +144,9 @@ class TRule {
   // may be null
   boost::shared_ptr<NTSizeSummaryStatistics> nt_size_summary_;
 
+  // only for coarse-to-fine decoding
+  boost::shared_ptr<std::vector<TRulePtr> > fine_rules_;
+
  private:
   TRule(const WordID& src, const WordID& trg) : e_(1, trg), f_(1, src), lhs_(), arity_(), prev_i(), prev_j() {}
   bool SanityCheck() const;