1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
|
#ifndef _DTRAIN_PAIRSAMPLING_H_
#define _DTRAIN_PAIRSAMPLING_H_
namespace dtrain
{
inline void
sample_all_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training)
{
for (unsigned i = 0; i < s->size()-1; i++) {
for (unsigned j = i+1; j < s->size(); j++) {
pair<ScoredHyp,ScoredHyp> p;
p.first = (*s)[i];
p.second = (*s)[j];
training.push_back(p);
}
}
}
inline void
sample_rand_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training,
MT19937* prng)
{
for (unsigned i = 0; i < s->size()-1; i++) {
for (unsigned j = i+1; j < s->size(); j++) {
if (prng->next() < .5) {
pair<ScoredHyp,ScoredHyp> p;
p.first = (*s)[i];
p.second = (*s)[j];
training.push_back(p);
}
}
}
}
bool
sort_samples_by_score(ScoredHyp a, ScoredHyp b)
{
return a.score < b.score;
}
inline void
sample108010(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training)
{
sort(s->begin(), s->end(), sort_samples_by_score);
pair<ScoredHyp,ScoredHyp> p;
unsigned sz = s->size();
unsigned slice = 10;
unsigned sep = sz%slice;
if (sep == 0) sep = sz/slice;
for (unsigned i = 0; i < sep; i++) {
for(unsigned j = sep; j < sz; j++) {
p.first = (*s)[i];
p.second = (*s)[j];
if(p.first.rank < p.second.rank) training.push_back(p);
}
}
for (unsigned i = sep; i < sz-sep; i++) {
for (unsigned j = sz-sep; j < sz; j++) {
p.first = (*s)[i];
p.second = (*s)[j];
if(p.first.rank < p.second.rank) training.push_back(p);
}
}
}
} // namespace
#endif
|
