diff options
author | Chris Dyer <cdyer@cs.cmu.edu> | 2012-03-09 23:13:09 -0500 |
---|---|---|
committer | Chris Dyer <cdyer@cs.cmu.edu> | 2012-03-09 23:13:09 -0500 |
commit | 5f9f400f4359bc14f7231d6eabd76b7ceee737aa (patch) | |
tree | 7e94ab9d1240183d713b0fbc58a99495ada5d5a7 | |
parent | e8f1e4e75dd8e27b81fd4e68116a38830547c2c4 (diff) |
logging after alignment
-rw-r--r-- | gi/pf/align-lexonly-pyp.cc | 1 | ||||
-rw-r--r-- | gi/pf/pyp_tm.cc | 7 | ||||
-rw-r--r-- | gi/pf/pyp_word_model.h | 2 | ||||
-rw-r--r-- | utils/ccrp.h | 1 |
4 files changed, 8 insertions, 3 deletions
diff --git a/gi/pf/align-lexonly-pyp.cc b/gi/pf/align-lexonly-pyp.cc index d68a4b8f..4a1d1db6 100644 --- a/gi/pf/align-lexonly-pyp.cc +++ b/gi/pf/align-lexonly-pyp.cc @@ -208,6 +208,7 @@ int main(int argc, char** argv) { } for (unsigned i = 0; i < corpus.size(); ++i) WriteAlignments(corpus[i]); + aligner.model.Summary(); return 0; } diff --git a/gi/pf/pyp_tm.cc b/gi/pf/pyp_tm.cc index 94cbe7c3..b5262f47 100644 --- a/gi/pf/pyp_tm.cc +++ b/gi/pf/pyp_tm.cc @@ -54,8 +54,6 @@ struct ConditionalPYPWordModel { assert(it != r.end()); if (it->second.decrement(trglets, rng)) { base.Decrement(trglets, rng); - if (it->second.num_customers() == 0) - r.erase(it); } } @@ -84,6 +82,11 @@ PYPLexicalTranslation::PYPLexicalTranslation(const vector<vector<WordID> >& lets tmodel(new ConditionalPYPWordModel<PYPWordModel>(up0)), kX(-TD::Convert("X")) {} +void PYPLexicalTranslation::Summary() const { + tmodel->Summary(); + up0->Summary(); +} + prob_t PYPLexicalTranslation::Likelihood() const { prob_t p = up0->Likelihood(); p *= tmodel->Likelihood(); diff --git a/gi/pf/pyp_word_model.h b/gi/pf/pyp_word_model.h index 800a4fd7..ff366865 100644 --- a/gi/pf/pyp_word_model.h +++ b/gi/pf/pyp_word_model.h @@ -12,7 +12,7 @@ // PYP(d,s,poisson-uniform) represented as a CRP struct PYPWordModel { - explicit PYPWordModel(const unsigned vocab_e_size, const double mean_len = 7.5) : + explicit PYPWordModel(const unsigned vocab_e_size, const double mean_len = 5) : base(prob_t::One()), r(1,1,1,1,0.66,50.0), u0(-std::log(vocab_e_size)), mean_length(mean_len) {} void ResampleHyperparameters(MT19937* rng); diff --git a/utils/ccrp.h b/utils/ccrp.h index 439d7e1e..4a8b80e7 100644 --- a/utils/ccrp.h +++ b/utils/ccrp.h @@ -221,6 +221,7 @@ class CCRP { void resample_hyperparameters(MT19937* rng, const unsigned nloop = 5, const unsigned niterations = 10) { assert(has_discount_prior() || has_strength_prior()); + if (num_customers() == 0) return; DiscountResampler dr(*this); StrengthResampler sr(*this); for (int iter = 0; iter < nloop; ++iter) { |