From 0172721855098ca02b207231a654dffa5e4eb1c9 Mon Sep 17 00:00:00 2001
From: redpony <redpony@ec762483-ff6d-05da-a07a-a48fb63a330f>
Date: Tue, 22 Jun 2010 05:12:27 +0000
Subject: initial checkin

git-svn-id: https://ws10smt.googlecode.com/svn/trunk@2 ec762483-ff6d-05da-a07a-a48fb63a330f
---
 vest/fast_score.cc | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 74 insertions(+)
 create mode 100644 vest/fast_score.cc

(limited to 'vest/fast_score.cc')

diff --git a/vest/fast_score.cc b/vest/fast_score.cc
new file mode 100644
index 00000000..cf743b4f
--- /dev/null
+++ b/vest/fast_score.cc
@@ -0,0 +1,74 @@
+#include <iostream>
+#include <vector>
+
+#include <boost/program_options.hpp>
+#include <boost/program_options/variables_map.hpp>
+
+#include "filelib.h"
+#include "tdict.h"
+#include "scorer.h"
+
+using namespace std;
+namespace po = boost::program_options;
+
+void InitCommandLine(int argc, char** argv, po::variables_map* conf) {
+  po::options_description opts("Configuration options");
+  opts.add_options()
+        ("reference,r",po::value<vector<string> >(), "[REQD] Reference translation(s) (tokenized text file)")
+        ("loss_function,l",po::value<string>()->default_value("ibm_bleu"), "Scoring metric (ibm_bleu, nist_bleu, koehn_bleu, ter, combi)")
+        ("in_file,i", po::value<string>()->default_value("-"), "Input file")
+        ("help,h", "Help");
+  po::options_description dcmdline_options;
+  dcmdline_options.add(opts);
+  po::store(parse_command_line(argc, argv, dcmdline_options), *conf);
+  bool flag = false;
+  if (!conf->count("reference")) {
+    cerr << "Please specify one or more references using -r <REF1.TXT> -r <REF2.TXT> ...\n";
+    flag = true;
+  }
+  if (flag || conf->count("help")) {
+    cerr << dcmdline_options << endl;
+    exit(1);
+  }
+}
+
+int main(int argc, char** argv) {
+  po::variables_map conf;
+  InitCommandLine(argc, argv, &conf);
+  const string loss_function = conf["loss_function"].as<string>();
+  ScoreType type = ScoreTypeFromString(loss_function);
+  DocScorer ds(type, conf["reference"].as<vector<string> >(), "");
+  cerr << "Loaded " << ds.size() << " references for scoring with " << loss_function << endl;
+
+  ReadFile rf(conf["in_file"].as<string>());
+  Score* acc = NULL;
+  istream& in = *rf.stream();
+  int lc = 0;
+  while(in) {
+    string line;
+    getline(in, line);
+    if (line.empty()) continue;
+    vector<WordID> sent;
+    TD::ConvertSentence(line, &sent);
+    Score* sentscore = ds[lc]->ScoreCandidate(sent);
+    if (!acc) { acc = sentscore->GetZero(); }
+    acc->PlusEquals(*sentscore);
+    delete sentscore;
+    ++lc;
+  }
+  assert(lc > 0);
+  if (lc > ds.size()) {
+    cerr << "Too many (" << lc << ") translations in input, expected " << ds.size() << endl;
+    return 1;
+  }
+  if (lc != ds.size())
+    cerr << "Fewer sentences in hyp (" << lc << ") than refs ("
+         << ds.size() << "): scoring partial set!\n";
+  float score = acc->ComputeScore();
+  string details;
+  acc->ScoreDetails(&details);
+  delete acc;
+  cerr << details << endl;
+  cout << score << endl;
+  return 0;
+}
-- 
cgit v1.2.3