summaryrefslogtreecommitdiff
path: root/training/candidate_set.h
blob: 9d326ed0c6ca0e8ed915e1b429d036d6046aa7fb (plain)
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
#ifndef _CANDIDATE_SET_H_
#define _CANDIDATE_SET_H_

#include <vector>
#include <algorithm>

#include "ns.h"
#include "wordid.h"
#include "sparse_vector.h"

class Hypergraph;

namespace training {

struct Candidate {
  Candidate() {}
  Candidate(const std::vector<WordID>& e, const SparseVector<double>& fm) :
      ewords(e),
      fmap(fm) {}
  Candidate(const std::vector<WordID>& e,
            const SparseVector<double>& fm,
            const SegmentEvaluator& se) :
      ewords(e),
      fmap(fm) {
    se.Evaluate(ewords, &eval_feats);
  }

  void swap(Candidate& other) {
    eval_feats.swap(other.eval_feats);
    ewords.swap(other.ewords);
    fmap.swap(other.fmap);
  }

  std::vector<WordID> ewords;
  SparseVector<double> fmap;
  SufficientStats eval_feats;
};

// represents some kind of collection of translation candidates, e.g.
// aggregated k-best lists, sample lists, etc.
class CandidateSet {
 public:
  CandidateSet() {}
  inline size_t size() const { return cs.size(); }
  const Candidate& operator[](size_t i) const { return cs[i]; }

  void ReadFromFile(const std::string& file);
  void WriteToFile(const std::string& file) const;
  void AddKBestCandidates(const Hypergraph& hg, size_t kbest_size, const SegmentEvaluator* scorer = NULL);
  // TODO add code to do unique k-best
  // TODO add code to draw k samples

 private:
  void Dedup();
  std::vector<Candidate> cs;
};

}

#endif