summaryrefslogtreecommitdiff
path: root/gi/pf/base_measures.cc
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2011-11-03 00:38:49 +0100
committerPatrick Simianer <p@simianer.de>2011-11-03 00:38:49 +0100
commit5ccbfda8675d01d91e56be477ab4e2f50db85aa9 (patch)
treea03e4a950c07982dfdbd73bc91ae15433fe48691 /gi/pf/base_measures.cc
parent4b6b25c944270df34852c9b8de3a0ba714d76dcf (diff)
parenta769e4964db2443ce165043095e18dfc0d788910 (diff)
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'gi/pf/base_measures.cc')
-rw-r--r--gi/pf/base_measures.cc56
1 files changed, 56 insertions, 0 deletions
diff --git a/gi/pf/base_measures.cc b/gi/pf/base_measures.cc
index f8ddfd32..8adb37d7 100644
--- a/gi/pf/base_measures.cc
+++ b/gi/pf/base_measures.cc
@@ -89,6 +89,62 @@ prob_t PhraseJointBase::p0(const vector<WordID>& vsrc,
return p;
}
+prob_t PhraseJointBase_BiDir::p0(const vector<WordID>& vsrc,
+ const vector<WordID>& vtrg,
+ int start_src, int start_trg) const {
+ const int flen = vsrc.size() - start_src;
+ const int elen = vtrg.size() - start_trg;
+ prob_t uniform_src_alignment; uniform_src_alignment.logeq(-log(flen + 1));
+ prob_t uniform_trg_alignment; uniform_trg_alignment.logeq(-log(elen + 1));
+
+ prob_t p1;
+ p1.logeq(log_poisson(flen, 1.0)); // flen ~Pois(1)
+ // elen | flen ~Pois(flen + 0.01)
+ prob_t ptrglen; ptrglen.logeq(log_poisson(elen, flen + 0.01));
+ p1 *= ptrglen;
+ p1 *= kUNIFORM_SOURCE.pow(flen); // each f in F ~Uniform
+ for (int i = 0; i < elen; ++i) { // for each position i in E
+ const WordID trg = vtrg[i + start_trg];
+ prob_t tp = prob_t::Zero();
+ for (int j = -1; j < flen; ++j) {
+ const WordID src = j < 0 ? 0 : vsrc[j + start_src];
+ tp += kM1MIXTURE * model1(src, trg);
+ tp += kUNIFORM_MIXTURE * kUNIFORM_TARGET;
+ }
+ tp *= uniform_src_alignment; // draw a_i ~uniform
+ p1 *= tp; // draw e_i ~Model1(f_a_i) / uniform
+ }
+ if (p1.is_0()) {
+ cerr << "Zero! " << vsrc << "\nTRG=" << vtrg << endl;
+ abort();
+ }
+
+ prob_t p2;
+ p2.logeq(log_poisson(elen, 1.0)); // elen ~Pois(1)
+ // flen | elen ~Pois(flen + 0.01)
+ prob_t psrclen; psrclen.logeq(log_poisson(flen, elen + 0.01));
+ p2 *= psrclen;
+ p2 *= kUNIFORM_TARGET.pow(elen); // each f in F ~Uniform
+ for (int i = 0; i < flen; ++i) { // for each position i in E
+ const WordID src = vsrc[i + start_src];
+ prob_t tp = prob_t::Zero();
+ for (int j = -1; j < elen; ++j) {
+ const WordID trg = j < 0 ? 0 : vtrg[j + start_trg];
+ tp += kM1MIXTURE * invmodel1(trg, src);
+ tp += kUNIFORM_MIXTURE * kUNIFORM_SOURCE;
+ }
+ tp *= uniform_trg_alignment; // draw a_i ~uniform
+ p2 *= tp; // draw e_i ~Model1(f_a_i) / uniform
+ }
+ if (p2.is_0()) {
+ cerr << "Zero! " << vsrc << "\nTRG=" << vtrg << endl;
+ abort();
+ }
+
+ static const prob_t kHALF(0.5);
+ return (p1 + p2) * kHALF;
+}
+
JumpBase::JumpBase() : p(200) {
for (unsigned src_len = 1; src_len < 200; ++src_len) {
map<int, prob_t>& cpd = p[src_len];