mirror of
https://github.com/moses-smt/mosesdecoder.git
synced 2024-09-20 15:48:05 +03:00
83f234cf17
as --scconfig regtype:min,regwin:3 in extractor and mert. Only tested on toy example so far. git-svn-id: https://mosesdecoder.svn.sourceforge.net/svnroot/mosesdecoder/trunk@1860 1f5c12ca-751b-0410-a591-d2e778427230
54 lines
1.3 KiB
C++
54 lines
1.3 KiB
C++
#ifndef __PERSCORER_H__
|
|
#define __PERSCORER_H__
|
|
|
|
#include <algorithm>
|
|
#include <cmath>
|
|
#include <iostream>
|
|
#include <iterator>
|
|
#include <set>
|
|
#include <sstream>
|
|
#include <stdexcept>
|
|
#include <string>
|
|
#include <vector>
|
|
#include "Types.h"
|
|
#include "ScoreData.h"
|
|
#include "Scorer.h"
|
|
|
|
|
|
using namespace std;
|
|
|
|
/**
|
|
* Implementation of position-independent word error rate. This is defined
|
|
* as 1 - (correct - max(0,output_length - ref_length)) / ref_length
|
|
* In fact, we ignore the " 1 - " so that it can be maximised.
|
|
**/
|
|
class PerScorer: public StatisticsBasedScorer {
|
|
public:
|
|
PerScorer(const string& config = "") : StatisticsBasedScorer("PER",config) {}
|
|
virtual void setReferenceFiles(const vector<string>& referenceFiles);
|
|
virtual void prepareStats(size_t sid, const string& text, ScoreStats& entry);
|
|
|
|
virtual void whoami() {
|
|
cerr << "I AM PerScorer" << std::endl;
|
|
}
|
|
|
|
size_t NumberOfScores(){ cerr << "PerScorer: 3" << endl; return 3; };
|
|
|
|
protected:
|
|
|
|
virtual float calculateScore(const vector<int>& comps) ;
|
|
|
|
private:
|
|
|
|
//no copy
|
|
PerScorer(const PerScorer&);
|
|
~PerScorer(){};
|
|
PerScorer& operator=(const PerScorer&);
|
|
|
|
// data extracted from reference files
|
|
vector<size_t> _reflengths;
|
|
vector<multiset<int> > _reftokens;
|
|
};
|
|
|
|
#endif //__PERSCORER_H
|