From 104aad02a868c1fc6320276d9b3b9b0e1f41f457 Mon Sep 17 00:00:00 2001 From: Chris Dyer Date: Sun, 27 May 2012 23:25:16 -0400 Subject: fix mapper to use common candidate set code --- pro-train/Makefile.am | 6 +- pro-train/mr_pro_map.cc | 174 +++--------------------------------------------- 2 files changed, 11 insertions(+), 169 deletions(-) (limited to 'pro-train') diff --git a/pro-train/Makefile.am b/pro-train/Makefile.am index a98dd245..1e9d46b0 100644 --- a/pro-train/Makefile.am +++ b/pro-train/Makefile.am @@ -2,12 +2,10 @@ bin_PROGRAMS = \ mr_pro_map \ mr_pro_reduce -TESTS = lo_test - mr_pro_map_SOURCES = mr_pro_map.cc -mr_pro_map_LDADD = $(top_srcdir)/decoder/libcdec.a $(top_srcdir)/mteval/libmteval.a $(top_srcdir)/utils/libutils.a -lz +mr_pro_map_LDADD = $(top_srcdir)/training/libtraining.a $(top_srcdir)/decoder/libcdec.a $(top_srcdir)/mteval/libmteval.a $(top_srcdir)/utils/libutils.a -lz mr_pro_reduce_SOURCES = mr_pro_reduce.cc mr_pro_reduce_LDADD = $(top_srcdir)/training/liblbfgs/liblbfgs.a $(top_srcdir)/utils/libutils.a -lz -AM_CPPFLAGS = -W -Wall -Wno-sign-compare $(GTEST_CPPFLAGS) -I$(top_srcdir)/utils -I$(top_srcdir)/decoder -I$(top_srcdir)/mteval -I$(top_srcdir)/training +AM_CPPFLAGS = -W -Wall -Wno-sign-compare -I$(top_srcdir)/utils -I$(top_srcdir)/decoder -I$(top_srcdir)/mteval -I$(top_srcdir)/training diff --git a/pro-train/mr_pro_map.cc b/pro-train/mr_pro_map.cc index 52b67f32..2aa0dc6f 100644 --- a/pro-train/mr_pro_map.cc +++ b/pro-train/mr_pro_map.cc @@ -9,14 +9,13 @@ #include #include +#include "candidate_set.h" #include "sampler.h" #include "filelib.h" #include "stringlib.h" #include "weights.h" #include "inside_outside.h" #include "hg_io.h" -#include "kbest.h" -#include "viterbi.h" #include "ns.h" #include "ns_docscorer.h" @@ -25,52 +24,6 @@ using namespace std; namespace po = boost::program_options; -struct ApproxVectorHasher { - static const size_t MASK = 0xFFFFFFFFull; - union UType { - double f; // leave as double - size_t i; - }; - static inline double round(const double x) { - UType t; - t.f = x; - size_t r = t.i & MASK; - if ((r << 1) > MASK) - t.i += MASK - r + 1; - else - t.i &= (1ull - MASK); - return t.f; - } - size_t operator()(const SparseVector& x) const { - size_t h = 0x573915839; - for (SparseVector::const_iterator it = x.begin(); it != x.end(); ++it) { - UType t; - t.f = it->second; - if (t.f) { - size_t z = (t.i >> 32); - boost::hash_combine(h, it->first); - boost::hash_combine(h, z); - } - } - return h; - } -}; - -struct ApproxVectorEquals { - bool operator()(const SparseVector& a, const SparseVector& b) const { - SparseVector::const_iterator bit = b.begin(); - for (SparseVector::const_iterator ait = a.begin(); ait != a.end(); ++ait) { - if (bit == b.end() || - ait->first != bit->first || - ApproxVectorHasher::round(ait->second) != ApproxVectorHasher::round(bit->second)) - return false; - ++bit; - } - if (bit != b.end()) return false; - return true; - } -}; - boost::shared_ptr rng; void InitCommandLine(int argc, char** argv, po::variables_map* conf) { @@ -105,107 +58,6 @@ void InitCommandLine(int argc, char** argv, po::variables_map* conf) { } } -struct HypInfo { - HypInfo() : g_(-100.0f) {} - HypInfo(const vector& h, const SparseVector& feats) : hyp(h), g_(-100.0f), x(feats) {} - - // lazy evaluation - double g(const SegmentEvaluator& scorer, const EvaluationMetric* metric) const { - if (g_ == -100.0f) { - SufficientStats ss; - scorer.Evaluate(hyp, &ss); - g_ = metric->ComputeScore(ss); - } - return g_; - } - vector hyp; - mutable float g_; - SparseVector x; -}; - -struct HypInfoCompare { - bool operator()(const HypInfo& a, const HypInfo& b) const { - ApproxVectorEquals comp; - return (a.hyp == b.hyp && comp(a.x,b.x)); - } -}; - -struct HypInfoHasher { - size_t operator()(const HypInfo& x) const { - boost::hash > hhasher; - ApproxVectorHasher vhasher; - size_t ha = hhasher(x.hyp); - boost::hash_combine(ha, vhasher(x.x)); - return ha; - } -}; - -void WriteKBest(const string& file, const vector& kbest) { - WriteFile wf(file); - ostream& out = *wf.stream(); - out.precision(10); - for (int i = 0; i < kbest.size(); ++i) { - out << TD::GetString(kbest[i].hyp) << endl; - out << kbest[i].x << endl; - } -} - -void ParseSparseVector(string& line, size_t cur, SparseVector* out) { - SparseVector& x = *out; - size_t last_start = cur; - size_t last_comma = string::npos; - while(cur <= line.size()) { - if (line[cur] == ' ' || cur == line.size()) { - if (!(cur > last_start && last_comma != string::npos && cur > last_comma)) { - cerr << "[ERROR] " << line << endl << " position = " << cur << endl; - exit(1); - } - const int fid = FD::Convert(line.substr(last_start, last_comma - last_start)); - if (cur < line.size()) line[cur] = 0; - const double val = strtod(&line[last_comma + 1], NULL); - x.set_value(fid, val); - - last_comma = string::npos; - last_start = cur+1; - } else { - if (line[cur] == '=') - last_comma = cur; - } - ++cur; - } -} - -void ReadKBest(const string& file, vector* kbest) { - cerr << "Reading from " << file << endl; - ReadFile rf(file); - istream& in = *rf.stream(); - string cand; - string feats; - while(getline(in, cand)) { - getline(in, feats); - assert(in); - kbest->push_back(HypInfo()); - TD::ConvertSentence(cand, &kbest->back().hyp); - ParseSparseVector(feats, 0, &kbest->back().x); - } - cerr << " read " << kbest->size() << " hypotheses\n"; -} - -void Dedup(vector* h) { - cerr << "Dedup in=" << h->size(); - tr1::unordered_set u; - while(h->size() > 0) { - u.insert(h->back()); - h->pop_back(); - } - tr1::unordered_set::iterator it = u.begin(); - while (it != u.end()) { - h->push_back(*it); - it = u.erase(it); - } - cerr << " out=" << h->size() << endl; -} - struct ThresholdAlpha { explicit ThresholdAlpha(double t = 0.05) : threshold(t) {} double operator()(double mag) const { @@ -239,7 +91,7 @@ struct DiffOrder { void Sample(const unsigned gamma, const unsigned xi, - const vector& J_i, + const training::CandidateSet& J_i, const SegmentEvaluator& scorer, const EvaluationMetric* metric, vector* pv) { @@ -257,10 +109,10 @@ void Sample(const unsigned gamma, const float gdiff = fabs(ga - gb); if (!gdiff) continue; avg_diff += gdiff; - SparseVector xdiff = (J_i[a].x - J_i[b].x).erase_zeros(); + SparseVector xdiff = (J_i[a].fmap - J_i[b].fmap).erase_zeros(); if (xdiff.empty()) { - cerr << "Empty diff:\n " << TD::GetString(J_i[a].hyp) << endl << "x=" << J_i[a].x << endl; - cerr << " " << TD::GetString(J_i[b].hyp) << endl << "x=" << J_i[b].x << endl; + cerr << "Empty diff:\n " << TD::GetString(J_i[a].ewords) << endl << "x=" << J_i[a].fmap << endl; + cerr << " " << TD::GetString(J_i[b].ewords) << endl << "x=" << J_i[b].fmap << endl; continue; } v1.push_back(TrainingInstance(xdiff, positive, gdiff)); @@ -328,23 +180,15 @@ int main(int argc, char** argv) { is >> file >> sent_id; ReadFile rf(file); ostringstream os; - vector J_i; + training::CandidateSet J_i; os << kbest_repo << "/kbest." << sent_id << ".txt.gz"; const string kbest_file = os.str(); if (FileExists(kbest_file)) - ReadKBest(kbest_file, &J_i); + J_i.ReadFromFile(kbest_file); HypergraphIO::ReadFromJSON(rf.stream(), &hg); hg.Reweight(weights); - KBest::KBestDerivations, ESentenceTraversal> kbest(hg, kbest_size); - - for (int i = 0; i < kbest_size; ++i) { - const KBest::KBestDerivations, ESentenceTraversal>::Derivation* d = - kbest.LazyKthBest(hg.nodes_.size() - 1, i); - if (!d) break; - J_i.push_back(HypInfo(d->yield, d->feature_values)); - } - Dedup(&J_i); - WriteKBest(kbest_file, J_i); + J_i.AddKBestCandidates(hg, kbest_size); + J_i.WriteToFile(kbest_file); Sample(gamma, xi, J_i, *ds[sent_id], metric, &v); for (unsigned i = 0; i < v.size(); ++i) { -- cgit v1.2.3