moses-smt/mosesdecoder
1
1
Fork 0
mirror of https://github.com/moses-smt/mosesdecoder.git synced 2024-09-11 11:25:40 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge ../mosesdecoder into perf_moses2

Browse Source
This commit is contained in:
Hieu Hoang 2016-06-01 21:03:37 +01:00
commit 1c9220049b
12 changed files with 1493 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mert/Jamfile
View File

@ -31,6 +31,8 @@ Point.cpp
PerScorer.cpp
HwcmScorer.cpp
InternalTree.cpp
M2.cpp
M2Scorer.cpp
Scorer.cpp
ScorerFactory.cpp
Optimizer.cpp

56
mert/M2.cpp Normal file
View File

@ -0,0 +1,56 @@
#include <boost/algorithm/string.hpp>
#include "M2.h"
namespace MosesTuning {
namespace M2 {
bool Annot::lowercase = true;
std::string Annot::transform(const std::string& e) {
std::string temp = e;
if(lowercase) {
boost::erase_all(temp, " ");
return ToLower(temp);
}
else
return e;
}
const std::string ToLower(const std::string& str)
{
std::string lc(str);
std::transform(lc.begin(), lc.end(), lc.begin(), (int(*)(int))std::tolower);
return lc;
}
Edit operator+(Edit& e1, Edit& e2) {
std::string edit;
if(e1.edit.size() > 0 && e2.edit.size() > 0)
edit = e1.edit + " " + e2.edit;
else if(e1.edit.size() > 0)
edit = e1.edit;
else if(e2.edit.size() > 0)
edit = e2.edit;
return Edit(e1.cost + e2.cost, e1.changed + e2.changed, e1.unchanged + e2.unchanged, edit);
}
Edge operator+(Edge e1, Edge e2) {
return Edge(e1.v, e2.u, e1.edit + e2.edit);
}
std::ostream& operator<<(std::ostream& o, Sentence s) {
for(Sentence::iterator it = s.begin(); it != s.end(); it++)
o << *it << " ";
return o;
}
}
}

480
mert/M2.h Normal file
View File

@ -0,0 +1,480 @@
#pragma once
#include <cmath>
#include <string>
#include <vector>
#include <set>
#include <map>
#include <queue>
#include <iostream>
#include <fstream>
#include <iterator>
#include <algorithm>
#include <limits>
#include <sstream>
#include <boost/algorithm/string.hpp>
namespace MosesTuning {
namespace M2 {
typedef std::vector<float> Stats;
typedef std::vector<std::string> Sentence;
std::ostream& operator<<(std::ostream& o, Sentence s);
const std::string ToLower(const std::string& str);
struct Annot {
size_t i;
size_t j;
std::string type;
std::string edit;
size_t annotator;
bool operator<(Annot a) const {
return i < a.i || (i == a.i && j < a.j)
|| (i == a.i && j == a.j && annotator < a.annotator)
|| (i == a.i && j == a.j && annotator == a.annotator && transform(edit) < transform(a.edit));
}
bool operator==(Annot a) const {
return (!(*this < a) && !(a < *this));
}
static std::string transform(const std::string& e);
static bool lowercase;
};
typedef std::set<Annot> Annots;
typedef std::set<size_t> Users;
struct Unit {
Sentence first;
Annots second;
Users third;
};
typedef std::vector<Unit> M2File;
struct Edit {
Edit(float c = 1.0, size_t ch = 0, size_t unch = 1, std::string e = "")
: cost(c), changed(ch), unchanged(unch), edit(e) {}
float cost;
size_t changed;
size_t unchanged;
std::string edit;
};
Edit operator+(Edit& e1, Edit& e2);
struct Vertex {
Vertex(size_t a = 0, size_t b = 0) : i(a), j(b) {}
bool operator<(const Vertex &v) const {
return i < v.i || (i == v.i && j < v.j);
}
bool operator==(const Vertex &v) const {
return i == v.i && j == v.j;
}
size_t i;
size_t j;
};
struct Edge {
Edge(Vertex vv = Vertex(), Vertex uu = Vertex(), Edit editt = Edit())
: v(vv), u(uu), edit(editt) {}
bool operator<(const Edge &e) const {
return v < e.v || (v == e.v && u < e.u);
}
Vertex v;
Vertex u;
Edit edit;
};
Edge operator+(Edge e1, Edge e2);
typedef std::vector<size_t> Row;
typedef std::vector<Row> Matrix;
struct Info {
Info(Vertex vv = Vertex(), Edit editt = Edit())
: v(vv), edit(editt) {}
bool operator<(const Info &i) const {
return v < i.v;
}
Vertex v;
Edit edit;
};
typedef std::set<Info> Track;
typedef std::vector<Track> TrackRow;
typedef std::vector<TrackRow> TrackMatrix;
typedef std::set<Vertex> Vertices;
typedef std::set<Edge> Edges;
class M2 {
private:
M2File m_m2;
size_t m_max_unchanged;
float m_beta;
bool m_lowercase;
bool m_verbose;
public:
M2() : m_max_unchanged(2), m_beta(0.5), m_lowercase(true), m_verbose(false) { }
M2(size_t max_unchanged, float beta, bool truecase, bool verbose = false)
: m_max_unchanged(max_unchanged), m_beta(beta), m_lowercase(!truecase), m_verbose(verbose) {
if(!m_lowercase) {
Annot::lowercase = false;
}
}
float Beta() {
return m_beta;
}
void ReadM2(const std::string& filename) {
std::ifstream m2file(filename.c_str());
std::string line;
Unit unit;
bool first = true;
while(std::getline(m2file, line)) {
if(line.size() > 2) {
if(line.substr(0, 2) == "S ") {
if(!first) {
if(unit.third.empty())
unit.third.insert(0);
m_m2.push_back(unit);
}
first = false;
unit.first = Sentence();
unit.second = Annots();
std::string sentenceLine = line.substr(2);
boost::split(unit.first, sentenceLine, boost::is_any_of(" "), boost::token_compress_on);
}
if(line.substr(0, 2) == "A ") {
std::string annotLine = line.substr(2);
std::vector<std::string> annot;
boost::iter_split(annot, annotLine, boost::algorithm::first_finder("|||"));
if(annot[1] != "noop") {
Annot a;
std::stringstream rangeStr(annot[0]);
rangeStr >> a.i >> a.j;
a.type = annot[1];
a.edit = annot[2];
std::stringstream annotStr(annot[5]);
annotStr >> a.annotator;
unit.third.insert(a.annotator);
unit.second.insert(a);
}
else {
std::stringstream annotStr(annot[5]);
size_t annotator;
annotStr >> annotator;
unit.third.insert(annotator);
}
}
}
}
if(unit.third.empty())
unit.third.insert(0);
m_m2.push_back(unit);
}
size_t LevenshteinMatrix(const Sentence &s1, const Sentence &s2, Matrix &d, TrackMatrix &bt) {
size_t n = s1.size();
size_t m = s2.size();
if (n == 0)
return m;
if (m == 0)
return n;
d.resize(n + 1, Row(m + 1, 0));
bt.resize(n + 1, TrackRow(m + 1));
for(size_t i = 0; i <= n; ++i) {
d[i][0] = i;
if(i > 0)
bt[i][0].insert(Info(Vertex(i - 1, 0), Edit(1, 1, 0, "")));
}
for(size_t j = 0; j <= m; ++j) {
d[0][j] = j;
if(j > 0)
bt[0][j].insert(Info(Vertex(0, j - 1), Edit(1, 1, 0, s2[j - 1])));
}
int cost;
for(size_t i = 1; i <= n; ++i) {
for(size_t j = 1; j <= m; ++j) {
if(Annot::transform(s1[i-1]) == Annot::transform(s2[j-1]))
cost = 0;
else
cost = 2;
size_t left = d[i][j - 1] + 1;
size_t down = d[i - 1][j] + 1;
size_t diag = d[i - 1][j - 1] + cost;
d[i][j] = std::min(left, std::min(down, diag));
if(d[i][j] == left)
bt[i][j].insert(Info(Vertex(i, j - 1), Edit(1, 1, 0, s2[j - 1])));
if(d[i][j] == down)
bt[i][j].insert(Info(Vertex(i - 1, j), Edit(1, 1, 0, "")));
if(d[i][j] == diag)
bt[i][j].insert(Info(Vertex(i - 1, j - 1), cost ? Edit(1, 1, 0, s2[j - 1]) : Edit(1, 0, 1, s2[j - 1]) ));
}
}
return d[n][m];
}
void BuildGraph(const TrackMatrix &bt, Vertices &V, Edges &E) {
Vertex start(bt.size() - 1, bt[0].size() - 1);
std::queue<Vertex> Q;
Q.push(start);
while(!Q.empty()) {
Vertex v = Q.front();
Q.pop();
if(V.count(v) > 0)
continue;
V.insert(v);
for(Track::iterator it = bt[v.i][v.j].begin();
it != bt[v.i][v.j].end(); ++it) {
Edge e(it->v, v, it->edit);
E.insert(e);
if(V.count(e.v) == 0)
Q.push(e.v);
}
}
Edges newE;
do {
newE.clear();
for(Edges::iterator it1 = E.begin(); it1 != E.end(); ++it1) {
for(Edges::iterator it2 = E.begin(); it2 != E.end(); ++it2) {
if(it1->u == it2->v) {
Edge e = *it1 + *it2;
if(e.edit.changed > 0 &&
e.edit.unchanged <= m_max_unchanged &&
E.count(e) == 0)
newE.insert(e);
}
}
}
E.insert(newE.begin(), newE.end());
} while(newE.size() > 0);
}
void AddWeights(Edges &E, const Unit &u, size_t aid) {
for(Edges::iterator it1 = E.begin(); it1 != E.end(); ++it1) {
if(it1->edit.changed > 0) {
const_cast<float&>(it1->edit.cost) += 0.001;
for(Annots::iterator it2 = u.second.begin(); it2 != u.second.end(); ++it2) {
// if matches an annotator
if(it1->v.i == it2->i && it1->u.i == it2->j
&& Annot::transform(it1->edit.edit) == Annot::transform(it2->edit)
&& it2->annotator == aid) {
int newWeight = -(m_max_unchanged + 1) * E.size();
const_cast<float&>(it1->edit.cost) = newWeight;
}
}
}
}
}
void BellmanFord(Vertices &V, Edges &E) {
Vertex source(0, 0);
std::map<Vertex, float> distance;
std::map<Vertex, Vertex> predecessor;
for(Vertices::iterator it = V.begin(); it != V.end(); ++it) {
if(*it == source)
distance[*it] = 0;
else {
distance[*it] = std::numeric_limits<float>::infinity();
}
}
for(size_t i = 1; i < V.size(); ++i) {
for(Edges::iterator it = E.begin(); it != E.end(); ++it) {
if(distance[it->v] + it->edit.cost < distance[it->u]) {
distance[it->u] = distance[it->v] + it->edit.cost;
predecessor[it->u] = it->v;
}
}
}
Edges newE;
Vertex v = *V.rbegin();
while(true) {
//std::cout << predecessor[v] << " -> " << v << std::endl;
Edges::iterator it = E.find(Edge(predecessor[v], v));
if(it != E.end()) {
Edge f = *it;
//std::cout << f << std::endl;
newE.insert(f);
v = predecessor[v];
if(v == source)
break;
}
else {
std::cout << "Error" << std::endl;
break;
}
}
E.clear();
E.insert(newE.begin(), newE.end());
}
void AddStats(const std::vector<Edges> &Es, const Unit &u, Stats &stats, size_t line) {
std::map<size_t, Stats> statsPerAnnotator;
for(std::set<size_t>::iterator it = u.third.begin();
it != u.third.end(); ++it) {
statsPerAnnotator[*it] = Stats(4, 0);
}
for(Annots::iterator it = u.second.begin(); it != u.second.end(); it++)
statsPerAnnotator[it->annotator][2]++;
for(std::set<size_t>::iterator ait = u.third.begin();
ait != u.third.end(); ++ait) {
for(Edges::iterator eit = Es[*ait].begin(); eit != Es[*ait].end(); ++eit) {
if(eit->edit.changed > 0) {
statsPerAnnotator[*ait][1]++;
Annot f;
f.i = eit->v.i;
f.j = eit->u.i;
f.annotator = *ait;
f.edit = eit->edit.edit;
for(Annots::iterator fit = u.second.begin(); fit != u.second.end(); fit++) {
if(f == *fit)
statsPerAnnotator[*ait][0]++;
}
}
}
}
size_t bestAnnot = 0;
float bestF = -1;
for(std::set<size_t>::iterator it = u.third.begin();
it != u.third.end(); ++it) {
Stats localStats = stats;
localStats[0] += statsPerAnnotator[*it][0];
localStats[1] += statsPerAnnotator[*it][1];
localStats[2] += statsPerAnnotator[*it][2];
if(m_verbose)
std::cerr << *it << " : " << localStats[0] << " " << localStats[1] << " " << localStats[2] << std::endl;
float f = FScore(localStats);
if(m_verbose)
std::cerr << f << std::endl;
if(f > bestF) {
bestF = f;
bestAnnot = *it;
}
}
if(m_verbose)
std::cerr << ">> Chosen Annotator for line " << line + 1 << " : " << bestAnnot << std::endl;
stats[0] += statsPerAnnotator[bestAnnot][0];
stats[1] += statsPerAnnotator[bestAnnot][1];
stats[2] += statsPerAnnotator[bestAnnot][2];
}
void SufStats(const std::string &sStr, size_t i, Stats &stats) {
std::string temp = sStr;
Sentence s;
boost::split(s, temp, boost::is_any_of(" "), boost::token_compress_on);
Unit &unit = m_m2[i];
Matrix d;
TrackMatrix bt;
size_t distance = LevenshteinMatrix(unit.first, s, d, bt);
std::vector<Vertices> Vs(unit.third.size());
std::vector<Edges> Es(unit.third.size());
if(distance > unit.first.size()) {
std::cerr << "Levenshtein distance is greater than source size." << std::endl;
stats[0] = 0;
stats[1] = distance;
stats[2] = 0;
stats[3] = unit.first.size();
return;
}
else if(distance > 0) {
for(size_t j = 0; j < unit.third.size(); j++) {
BuildGraph(bt, Vs[j], Es[j]);
AddWeights(Es[j], unit, j);
BellmanFord(Vs[j], Es[j]);
}
}
AddStats(Es, unit, stats, i);
stats[3] = unit.first.size();
}
float FScore(const Stats& stats) {
float p = 1.0;
if(stats[1] != 0)
p = (float)stats[0] / (float)stats[1];
float r = 1.0;
if(stats[2] != 0)
r = (float)stats[0] / (float)stats[2];
float denom = (m_beta * m_beta * p + r);
float f = 0.0;
if(denom != 0)
f = ((1 + m_beta * m_beta) * p * r) / denom;
return f;
}
void FScore(const Stats& stats, float &p, float &r, float &f) {
p = 1.0;
if(stats[1] != 0)
p = (float)stats[0] / (float)stats[1];
r = 1.0;
if(stats[2] != 0)
r = (float)stats[0] / (float)stats[2];
float denom = (m_beta * m_beta * p + r);
f = 0.0;
if(denom != 0)
f = ((1 + m_beta * m_beta) * p * r) / denom;
}
};
}
}

135
mert/M2Scorer.cpp Normal file
View File

@ -0,0 +1,135 @@
#include "M2Scorer.h"
#include <algorithm>
#include <fstream>
#include <stdexcept>
#include <sstream>
#include <cstdlib>
#include <boost/lexical_cast.hpp>
using namespace std;
namespace MosesTuning
{
M2Scorer::M2Scorer(const string& config)
: StatisticsBasedScorer("M2Scorer", config),
beta_(Scan<float>(getConfig("beta", "0.5"))),
max_unchanged_words_(Scan<int>(getConfig("max_unchanged_words", "2"))),
truecase_(Scan<bool>(getConfig("truecase", "false"))),
verbose_(Scan<bool>(getConfig("verbose", "false"))),
m2_(max_unchanged_words_, beta_, truecase_)
{}
void M2Scorer::setReferenceFiles(const vector<string>& referenceFiles)
{
for(size_t i = 0; i < referenceFiles.size(); ++i) {
m2_.ReadM2(referenceFiles[i]);
break;
}
}
void M2Scorer::prepareStats(size_t sid, const string& text, ScoreStats& entry)
{
string sentence = trimStr(this->preprocessSentence(text));
std::vector<ScoreStatsType> stats(4, 0);
m2_.SufStats(sentence, sid, stats);
entry.set(stats);
}
float M2Scorer::calculateScore(const vector<ScoreStatsType>& comps) const
{
if (comps.size() != NumberOfScores()) {
throw runtime_error("Size of stat vector for M2Scorer is not " + NumberOfScores());
}
float beta = beta_;
float p = 0.0;
float r = 0.0;
float f = 0.0;
if(comps[1] != 0)
p = comps[0] / (double)comps[1];
else
p = 1.0;
if(comps[2] != 0)
r = comps[0] / (double)comps[2];
else
r = 1.0;
float denom = beta * beta * p + r;
if(denom != 0)
f = (1.0 + beta * beta) * p * r / denom;
else
f = 0.0;
if(verbose_)
std::cerr << comps[0] << " " << comps[1] << " " << comps[2] << std::endl;
if(verbose_)
std::cerr << p << " " << r << " " << f << std::endl;
return f;
}
float M2Scorer::getReferenceLength(const vector<ScoreStatsType>& comps) const {
return comps[3];
}
std::vector<ScoreStatsType> randomStats(float decay, int max) {
int gold = rand() % max;
int prop = rand() % max;
int corr = 0.0;
if(std::min(prop, gold) > 0)
corr = rand() % std::min(prop, gold);
//std::cerr << corr << " " << prop << " " << gold << std::endl;
std::vector<ScoreStatsType> stats(3, 0.0);
stats[0] = corr * decay;
stats[1] = prop * decay;
stats[2] = gold * decay;
return stats;
}
float sentenceM2(const std::vector<ScoreStatsType>& stats)
{
float beta = 0.5;
std::vector<ScoreStatsType> smoothStats(3, 0.0); // = randomStats(0.001, 5);
smoothStats[0] += stats[0];
smoothStats[1] += stats[1];
smoothStats[2] += stats[2];
float p = 0.0;
float r = 0.0;
float f = 0.0;
if(smoothStats[1] != 0)
p = smoothStats[0] / smoothStats[1];
else
p = 1.0;
if(smoothStats[2] != 0)
r = smoothStats[0] / smoothStats[2];
else
r = 1.0;
float denom = beta * beta * p + r;
if(denom != 0)
f = (1.0 + beta * beta) * p * r / denom;
else
f = 0.0;
return f;
}
}

52
mert/M2Scorer.h Normal file
View File

@ -0,0 +1,52 @@
#ifndef MERT_M2_SCORER_H_
#define MERT_M2_SCORER_H_
#include <string>
#include <vector>
#include <functional>
#include "Types.h"
#include "Util.h"
#include "StatisticsBasedScorer.h"
#include "M2.h"
namespace MosesTuning
{
/**
* M2Scorer class can compute CoNLL m2 F-score.
*/
class M2Scorer: public StatisticsBasedScorer
{
public:
explicit M2Scorer(const std::string& config);
virtual void setReferenceFiles(const std::vector<std::string>& referenceFiles);
virtual void prepareStats(std::size_t sid, const std::string& text, ScoreStats& entry);
virtual std::size_t NumberOfScores() const {
return 4;
}
virtual float calculateScore(const std::vector<ScoreStatsType>& comps) const;
virtual float getReferenceLength(const std::vector<ScoreStatsType>& comps) const;
private:
float beta_;
int max_unchanged_words_;
bool truecase_;
bool verbose_;
M2::M2 m2_;
std::map<std::pair<size_t, std::string>, std::vector<ScoreStatsType> > seen_;
// no copying allowed
M2Scorer(const M2Scorer&);
M2Scorer& operator=(const M2Scorer&);
};
float sentenceM2 (const std::vector<ScoreStatsType>& stats);
}
#endif // MERT_M2_SCORER_H_

4
mert/ScorerFactory.cpp
View File

@ -11,6 +11,7 @@
#include "SemposScorer.h"
#include "PermutationScorer.h"
#include "MeteorScorer.h"
#include "M2Scorer.h"
#include "HwcmScorer.h"
#include "Reference.h"
@ -34,6 +35,7 @@ vector<string> ScorerFactory::getTypes()
types.push_back(string("LRSCORE"));
types.push_back(string("METEOR"));
types.push_back(string("HWCM"));
types.push_back(string("M2SCORER"));
return types;
}
@ -54,6 +56,8 @@ Scorer* ScorerFactory::getScorer(const string& type, const string& config)
return new CderScorer(config, false);
} else if (type == "SEMPOS") {
return new SemposScorer(config);
} else if (type == "M2SCORER") {
return new M2Scorer(config);
} else if ((type == "HAMMING") || (type == "KENDALL")) {
return (PermutationScorer*) new PermutationScorer(type, config);
} else if (type == "METEOR") {

363
moses/FF/CorrectionPattern.cpp Normal file
View File

@ -0,0 +1,363 @@
#include <sstream>
#include "CorrectionPattern.h"
#include "moses/Phrase.h"
#include "moses/TargetPhrase.h"
#include "moses/InputPath.h"
#include "moses/Hypothesis.h"
#include "moses/ChartHypothesis.h"
#include "moses/ScoreComponentCollection.h"
#include "moses/TranslationOption.h"
#include "util/string_piece_hash.hh"
#include "util/exception.hh"
#include <functional>
#include <algorithm>
#include <boost/foreach.hpp>
#include <boost/algorithm/string.hpp>
#include "Diffs.h"
namespace Moses
{
using namespace std;
std::string MakePair(const std::string &s1, const std::string &s2, bool general) {
std::vector<std::string> sourceList;
std::vector<std::string> targetList;
if(general) {
Diffs diffs = CreateDiff(s1, s2);
size_t i = 0, j = 0;
char lastType = 'm';
std::string source, target;
std::string match;
int count = 1;
BOOST_FOREACH(Diff type, diffs) {
if(type == 'm') {
if(lastType != 'm') {
sourceList.push_back(source);
targetList.push_back(target);
}
source.clear();
target.clear();
if(s1[i] == '+') {
if(match.size() >= 3) {
sourceList.push_back("(\\w{3,})·");
std::string temp = "1";
sprintf((char*)temp.c_str(), "%d", count);
targetList.push_back("\\" + temp + "·");
count++;
}
else {
sourceList.push_back(match + "·");
targetList.push_back(match + "·");
}
match.clear();
}
else
match.push_back(s1[i]);
i++;
j++;
}
else if(type == 'd') {
if(s1[i] == '+')
source += "·";
else
source.push_back(s1[i]);
i++;
}
else if(type == 'i') {
if(s2[j] == '+')
target += "·";
else
target.push_back(s2[j]);
j++;
}
if(type != 'm' && !match.empty()) {
if(match.size() >= 3) {
sourceList.push_back("(\\w{3,})");
std::string temp = "1";
sprintf((char*)temp.c_str(), "%d", count);
targetList.push_back("\\" + temp);
count++;
}
else {
sourceList.push_back(match);
targetList.push_back(match);
}
match.clear();
}
lastType = type;
}
if(lastType != 'm') {
sourceList.push_back(source);
targetList.push_back(target);
}
if(!match.empty()) {
if(match.size() >= 3) {
sourceList.push_back("(\\w{3,})");
std::string temp = "1";
sprintf((char*)temp.c_str(), "%d", count);
targetList.push_back("\\"+ temp);
count++;
}
else {
sourceList.push_back(match);
targetList.push_back(match);
}
}
match.clear();
}
else {
std::string cs1 = s1;
std::string cs2 = s2;
boost::replace_all(cs1, "+", "·");
boost::replace_all(cs2, "+", "·");
sourceList.push_back(cs1);
targetList.push_back(cs2);
}
std::stringstream out;
out << "sub(«";
out << boost::join(sourceList, "");
out << "»,«";
out << boost::join(targetList, "");
out << "»)";
return out.str();
}
std::string CorrectionPattern::CreateSinglePattern(const Tokens &s1, const Tokens &s2) const {
std::stringstream out;
if(s1.empty()) {
out << "ins(«" << boost::join(s2, "·") << "»)";
return out.str();
}
else if(s2.empty()) {
out << "del(«" << boost::join(s1, "·") << "»)";
return out.str();
}
else {
typename Tokens::value_type v1 = boost::join(s1, "+");
typename Tokens::value_type v2 = boost::join(s2, "+");
out << MakePair(v1, v2, m_general);
return out.str();
}
}
std::vector<std::string> GetContext(size_t pos,
size_t len,
size_t window,
const InputType &input,
const InputPath &inputPath,
const std::vector<FactorType>& factorTypes,
bool isRight) {
const Sentence& sentence = static_cast<const Sentence&>(input);
const Range& range = inputPath.GetWordsRange();
int leftPos = range.GetStartPos() + pos - len - 1;
int rightPos = range.GetStartPos() + pos;
std::vector<std::string> contexts;
for(int length = 1; length <= (int)window; ++length) {
std::vector<std::string> current;
if(!isRight) {
for(int i = 0; i < length; i++) {
if(leftPos - i >= 0) {
current.push_back(sentence.GetWord(leftPos - i).GetString(factorTypes, false));
}
else {
current.push_back("<s>");
}
}
if(current.back() == "<s>" && current.size() >= 2 && current[current.size()-2] == "<s>")
continue;
std::reverse(current.begin(), current.end());
contexts.push_back("left(«" + boost::join(current, "·") + "»)_");
}
if(isRight) {
for(int i = 0; i < length; i++) {
if(rightPos + i < (int)sentence.GetSize()) {
current.push_back(sentence.GetWord(rightPos + i).GetString(factorTypes, false));
}
else {
current.push_back("</s>");
}
}
if(current.back() == "</s>" && current.size() >= 2 && current[current.size()-2] == "</s>")
continue;
contexts.push_back("_right(«" + boost::join(current, "·") + "»)");
}
}
return contexts;
}
std::vector<std::string>
CorrectionPattern::CreatePattern(const Tokens &s1,
const Tokens &s2,
const InputType &input,
const InputPath &inputPath) const {
Diffs diffs = CreateDiff(s1, s2);
size_t i = 0, j = 0;
char lastType = 'm';
std::vector<std::string> patternList;
Tokens source, target;
BOOST_FOREACH(Diff type, diffs) {
if(type == 'm') {
if(lastType != 'm') {
std::string pattern = CreateSinglePattern(source, target);
patternList.push_back(pattern);
if(m_context > 0) {
std::vector<std::string> leftContexts = GetContext(i, source.size(), m_context, input, inputPath, m_contextFactors, false);
std::vector<std::string> rightContexts = GetContext(i, source.size(), m_context, input, inputPath, m_contextFactors, true);
BOOST_FOREACH(std::string left, leftContexts)
patternList.push_back(left + pattern);
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(pattern + right);
BOOST_FOREACH(std::string left, leftContexts)
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(left + pattern + right);
}
}
source.clear();
target.clear();
if(s1[i] != s2[j]) {
source.push_back(s1[i]);
target.push_back(s2[j]);
}
i++;
j++;
}
else if(type == 'd') {
source.push_back(s1[i]);
i++;
}
else if(type == 'i') {
target.push_back(s2[j]);
j++;
}
lastType = type;
}
if(lastType != 'm') {
std::string pattern = CreateSinglePattern(source, target);
patternList.push_back(pattern);
if(m_context > 0) {
std::vector<std::string> leftContexts = GetContext(i, source.size(), m_context, input, inputPath, m_contextFactors, false);
std::vector<std::string> rightContexts = GetContext(i, source.size(), m_context, input, inputPath, m_contextFactors, true);
BOOST_FOREACH(std::string left, leftContexts)
patternList.push_back(left + pattern);
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(pattern + right);
BOOST_FOREACH(std::string left, leftContexts)
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(left + pattern + right);
}
}
return patternList;
}
CorrectionPattern::CorrectionPattern(const std::string &line)
: StatelessFeatureFunction(0, line), m_factors(1, 0), m_general(false),
m_context(0), m_contextFactors(1, 0)
{
std::cerr << "Initializing correction pattern feature.." << std::endl;
ReadParameters();
}
void CorrectionPattern::SetParameter(const std::string& key, const std::string& value)
{
if (key == "factor") {
m_factors = std::vector<FactorType>(1, Scan<FactorType>(value));
} else if (key == "context-factor") {
m_contextFactors = std::vector<FactorType>(1, Scan<FactorType>(value));
} else if (key == "general") {
m_general = Scan<bool>(value);
} else if (key == "context") {
m_context = Scan<size_t>(value);
} else {
StatelessFeatureFunction::SetParameter(key, value);
}
}
void CorrectionPattern::EvaluateWithSourceContext(const InputType &input
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore) const
{
ComputeFeatures(input, inputPath, targetPhrase, &scoreBreakdown);
}
void CorrectionPattern::ComputeFeatures(
const InputType &input,
const InputPath &inputPath,
const TargetPhrase& target,
ScoreComponentCollection* accumulator) const
{
const Phrase &source = inputPath.GetPhrase();
std::vector<std::string> sourceTokens;
for(size_t i = 0; i < source.GetSize(); ++i)
sourceTokens.push_back(source.GetWord(i).GetString(m_factors, false));
std::vector<std::string> targetTokens;
for(size_t i = 0; i < target.GetSize(); ++i)
targetTokens.push_back(target.GetWord(i).GetString(m_factors, false));
std::vector<std::string> patternList = CreatePattern(sourceTokens, targetTokens, input, inputPath);
for(size_t i = 0; i < patternList.size(); ++i)
accumulator->PlusEquals(this, patternList[i], 1);
/*
BOOST_FOREACH(std::string w, sourceTokens)
std::cerr << w << " ";
std::cerr << std::endl;
BOOST_FOREACH(std::string w, targetTokens)
std::cerr << w << " ";
std::cerr << std::endl;
BOOST_FOREACH(std::string w, patternList)
std::cerr << w << " ";
std::cerr << std::endl << std::endl;
*/
}
bool CorrectionPattern::IsUseable(const FactorMask &mask) const
{
bool ret = true;
for(size_t i = 0; i < m_factors.size(); ++i)
ret = ret && mask[m_factors[i]];
for(size_t i = 0; i < m_contextFactors.size(); ++i)
ret = ret && mask[m_contextFactors[i]];
return ret;
}
}

73
moses/FF/CorrectionPattern.h Normal file
View File

@ -0,0 +1,73 @@
#ifndef moses_CorrectionPattern_h
#define moses_CorrectionPattern_h
#include <string>
#include <boost/unordered_set.hpp>
#include "StatelessFeatureFunction.h"
#include "moses/FactorCollection.h"
#include "moses/AlignmentInfo.h"
namespace Moses
{
typedef std::vector<std::string> Tokens;
/** Sets the features for length of source phrase, target phrase, both.
*/
class CorrectionPattern : public StatelessFeatureFunction
{
private:
std::vector<FactorType> m_factors;
bool m_general;
size_t m_context;
std::vector<FactorType> m_contextFactors;
public:
CorrectionPattern(const std::string &line);
bool IsUseable(const FactorMask &mask) const;
void EvaluateInIsolation(const Phrase &source
, const TargetPhrase &targetPhrase
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection &estimatedFutureScore) const
{}
virtual void EvaluateWithSourceContext(const InputType &input
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore = NULL) const;
void EvaluateTranslationOptionListWithSourceContext(const InputType &input
, const TranslationOptionList &translationOptionList) const
{}
void EvaluateWhenApplied(const Hypothesis& hypo,
ScoreComponentCollection* accumulator) const
{}
void EvaluateWhenApplied(const ChartHypothesis &hypo,
ScoreComponentCollection* accumulator) const
{}
void ComputeFeatures(const InputType &input,
const InputPath &inputPath,
const TargetPhrase& targetPhrase,
ScoreComponentCollection* accumulator) const;
void SetParameter(const std::string& key, const std::string& value);
std::vector<std::string> CreatePattern(const Tokens &s1,
const Tokens &s2,
const InputType &input,
const InputPath &inputPath) const;
std::string CreateSinglePattern(const Tokens &s1, const Tokens &s2) const;
};
}
#endif // moses_CorrectionPattern_h

139
moses/FF/Diffs.h Normal file
View File

@ -0,0 +1,139 @@
#ifndef moses_Diffs_h
#define moses_Diffs_h
#include <cmath>
namespace Moses
{
typedef char Diff;
typedef std::vector<Diff> Diffs;
template <class Sequence, class Pred>
void CreateDiffRec(size_t** c,
const Sequence &s1,
const Sequence &s2,
size_t start,
size_t i,
size_t j,
Diffs& diffs,
Pred pred) {
if(i > 0 && j > 0 && pred(s1[i - 1 + start], s2[j - 1 + start])) {
CreateDiffRec(c, s1, s2, start, i - 1, j - 1, diffs, pred);
diffs.push_back(Diff('m'));
}
else if(j > 0 && (i == 0 || c[i][j-1] >= c[i-1][j])) {
CreateDiffRec(c, s1, s2, start, i, j-1, diffs, pred);
diffs.push_back(Diff('i'));
}
else if(i > 0 && (j == 0 || c[i][j-1] < c[i-1][j])) {
CreateDiffRec(c, s1, s2, start, i-1, j, diffs, pred);
diffs.push_back(Diff('d'));
}
}
template <class Sequence, class Pred>
Diffs CreateDiff(const Sequence& s1,
const Sequence& s2,
Pred pred) {
Diffs diffs;
size_t n = s2.size();
int start = 0;
int m_end = s1.size() - 1;
int n_end = s2.size() - 1;
while(start <= m_end && start <= n_end && pred(s1[start], s2[start])) {
diffs.push_back(Diff('m'));
start++;
}
while(start <= m_end && start <= n_end && pred(s1[m_end], s2[n_end])) {
m_end--;
n_end--;
}
size_t m_new = m_end - start + 1;
size_t n_new = n_end - start + 1;
size_t** c = new size_t*[m_new + 1];
for(size_t i = 0; i <= m_new; ++i) {
c[i] = new size_t[n_new + 1];
c[i][0] = 0;
}
for(size_t j = 0; j <= n_new; ++j)
c[0][j] = 0;
for(size_t i = 1; i <= m_new; ++i)
for(size_t j = 1; j <= n_new; ++j)
if(pred(s1[i - 1 + start], s2[j - 1 + start]))
c[i][j] = c[i-1][j-1] + 1;
else
c[i][j] = c[i][j-1] > c[i-1][j] ? c[i][j-1] : c[i-1][j];
CreateDiffRec(c, s1, s2, start, m_new, n_new, diffs, pred);
for(size_t i = 0; i <= m_new; ++i)
delete[] c[i];
delete[] c;
for (size_t i = n_end + 1; i < n; ++i)
diffs.push_back(Diff('m'));
return diffs;
}
template <class Sequence>
Diffs CreateDiff(const Sequence& s1, const Sequence& s2) {
return CreateDiff(s1, s2, std::equal_to<typename Sequence::value_type>());
}
template <class Sequence, class Sig, class Stats>
void AddStats(const Sequence& s1, const Sequence& s2, const Sig& sig, Stats& stats) {
if(sig.size() != stats.size())
throw "Signature size differs from score array size.";
size_t m = 0, d = 0, i = 0, s = 0;
Diffs diff = CreateDiff(s1, s2);
for(int j = 0; j < (int)diff.size(); ++j) {
if(diff[j] == 'm')
m++;
else if(diff[j] == 'd') {
d++;
int k = 0;
while(j - k >= 0 && j + 1 + k < (int)diff.size() &&
diff[j - k] == 'd' && diff[j + 1 + k] == 'i') {
d--;
s++;
k++;
}
j += k;
}
else if(diff[j] == 'i')
i++;
}
for(size_t j = 0; j < sig.size(); ++j) {
switch (sig[j]) {
case 'l': stats[j] += d + i + s; break;
case 'm': stats[j] += m; break;
case 'd': stats[j] += d; break;
case 'i': stats[j] += i; break;
case 's': stats[j] += s; break;
case 'r':
float macc = 1;
if (d + i + s + m)
macc = 1.0 - (float)(d + i + s)/(float)(d + i + s + m);
if(macc > 0)
stats[j] += log(macc);
else
stats[j] += log(1.0/(float)(d + i + s + m + 1));
break;
}
}
}
}
#endif

119
moses/FF/EditOps.cpp Normal file
View File

@ -0,0 +1,119 @@
#include <sstream>
#include "EditOps.h"
#include "moses/Phrase.h"
#include "moses/TargetPhrase.h"
#include "moses/Hypothesis.h"
#include "moses/ChartHypothesis.h"
#include "moses/ScoreComponentCollection.h"
#include "moses/TranslationOption.h"
#include "util/string_piece_hash.hh"
#include "util/exception.hh"
#include <functional>
#include <boost/foreach.hpp>
#include <boost/algorithm/string.hpp>
#include "Diffs.h"
namespace Moses
{
using namespace std;
std::string ParseScores(const std::string &line, const std::string& defaultScores) {
std::vector<std::string> toks = Tokenize(line);
UTIL_THROW_IF2(toks.empty(), "Empty line");
for (size_t i = 1; i < toks.size(); ++i) {
std::vector<std::string> args = TokenizeFirstOnly(toks[i], "=");
UTIL_THROW_IF2(args.size() != 2,
"Incorrect format for feature function arg: " << toks[i]);
if (args[0] == "scores") {
return args[1];
}
}
return defaultScores;
}
EditOps::EditOps(const std::string &line)
: StatelessFeatureFunction(ParseScores(line, "dis").size(), line)
, m_factorType(0), m_chars(false), m_scores(ParseScores(line, "dis"))
{
std::cerr << "Initializing EditOps feature.." << std::endl;
ReadParameters();
}
void EditOps::SetParameter(const std::string& key, const std::string& value)
{
if (key == "factor") {
m_factorType = Scan<FactorType>(value);
} else if (key == "chars") {
m_chars = Scan<bool>(value);
} else if (key == "scores") {
m_scores = value;
} else {
StatelessFeatureFunction::SetParameter(key, value);
}
}
void EditOps::Load()
{ }
void EditOps::EvaluateInIsolation(const Phrase &source
, const TargetPhrase &target
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection &estimatedFutureScore) const
{
ComputeFeatures(source, target, &scoreBreakdown);
}
void EditOps::ComputeFeatures(
const Phrase &source,
const TargetPhrase& target,
ScoreComponentCollection* accumulator) const
{
std::vector<float> ops(GetNumScoreComponents(), 0);
if(m_chars) {
std::vector<FactorType> factors;
factors.push_back(m_factorType);
std::string sourceStr = source.GetStringRep(factors);
std::string targetStr = target.GetStringRep(factors);
AddStats(sourceStr, targetStr, m_scores, ops);
}
else {
std::vector<std::string> sourceTokens;
//std::cerr << "Ed src: ";
for(size_t i = 0; i < source.GetSize(); ++i) {
if(!source.GetWord(i).IsNonTerminal())
sourceTokens.push_back(source.GetWord(i).GetFactor(m_factorType)->GetString().as_string());
//std::cerr << sourceTokens.back() << " ";
}
//std::cerr << std::endl;
std::vector<std::string> targetTokens;
//std::cerr << "Ed trg: ";
for(size_t i = 0; i < target.GetSize(); ++i) {
if(!target.GetWord(i).IsNonTerminal())
targetTokens.push_back(target.GetWord(i).GetFactor(m_factorType)->GetString().as_string());
//std::cerr << targetTokens.back() << " ";
}
//std::cerr << std::endl;
AddStats(sourceTokens, targetTokens, m_scores, ops);
}
accumulator->PlusEquals(this, ops);
}
bool EditOps::IsUseable(const FactorMask &mask) const
{
bool ret = mask[m_factorType];
return ret;
}
}

64
moses/FF/EditOps.h Normal file
View File

@ -0,0 +1,64 @@
#ifndef moses_EditOps_h
#define moses_EditOps_h
#include <string>
#include <boost/unordered_set.hpp>
#include "StatelessFeatureFunction.h"
#include "moses/FactorCollection.h"
#include "moses/AlignmentInfo.h"
namespace Moses
{
typedef std::vector<std::string> Tokens;
/** Calculates string edit operations that transform source phrase into target
* phrase using the LCS algorithm. Potentially usefule for monolingual tasks
* like paraphrasing, summarization, correction.
*/
class EditOps : public StatelessFeatureFunction
{
private:
FactorType m_factorType;
bool m_chars;
std::string m_scores;
public:
EditOps(const std::string &line);
bool IsUseable(const FactorMask &mask) const;
void Load();
virtual void EvaluateInIsolation(const Phrase &source
, const TargetPhrase &targetPhrase
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection &estimatedFutureScore) const;
void EvaluateWithSourceContext(const InputType &input
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore = NULL) const
{}
void EvaluateWhenApplied(const Hypothesis& hypo,
ScoreComponentCollection* accumulator) const
{}
void EvaluateWhenApplied(const ChartHypothesis &hypo,
ScoreComponentCollection* accumulator) const
{}
void EvaluateTranslationOptionListWithSourceContext(const InputType &input
, const TranslationOptionList &translationOptionList) const
{}
void ComputeFeatures(const Phrase &source,
const TargetPhrase& targetPhrase,
ScoreComponentCollection* accumulator) const;
void SetParameter(const std::string& key, const std::string& value);
};
}
#endif // moses_CorrectionPattern_h

6
moses/FF/Factory.cpp
View File

@ -72,6 +72,9 @@
#include "moses/Syntax/InputWeightFF.h"
#include "moses/Syntax/RuleTableFF.h"
#include "moses/FF/EditOps.h"
#include "moses/FF/CorrectionPattern.h"
#ifdef HAVE_VW
#include "moses/FF/VW/VW.h"
#include "moses/FF/VW/VWFeatureSourceBagOfWords.h"
@ -292,6 +295,9 @@ FeatureRegistry::FeatureRegistry()
MOSES_FNAME(SkeletonTranslationOptionListFeature);
MOSES_FNAME(SkeletonPT);
MOSES_FNAME(EditOps);
MOSES_FNAME(CorrectionPattern);
#ifdef HAVE_VW
MOSES_FNAME(VW);
MOSES_FNAME(VWFeatureSourceBagOfWords);