From ac045a11c1f0e1d4ae25f0db47061113fc3ae2e1 Mon Sep 17 00:00:00 2001
From: Tetsuo Kiso <tetsuo-s@is.naist.jp>
Date: Thu, 6 Dec 2012 22:08:33 +0900
Subject: Speed up N-gram counts when running extractor.

By replacing std::map with boost::unordered_map.

Runtime of extractor on 100-best lists of 2679 sentences:

Before:
real    0m35.314s
user    0m34.030s
sys     0m1.280s

Ater:
real    0m26.729s
user    0m25.420s
sys     0m1.310s
---
 mert/BleuScorer.cpp |  1 +
 mert/Ngram.h        | 11 ++++++-----
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/mert/BleuScorer.cpp b/mert/BleuScorer.cpp
index ba662680c..a3ba16b13 100644
--- a/mert/BleuScorer.cpp
+++ b/mert/BleuScorer.cpp
@@ -62,6 +62,7 @@ size_t BleuScorer::CountNgrams(const string& line, NgramCounts& counts,
     }
     for (size_t i = 0; i < encoded_tokens.size()-k+1; ++i) {
       vector<int> ngram;
+      ngram.reserve(encoded_tokens.size());
       for (size_t j = i; j < i+k && j < encoded_tokens.size(); ++j) {
         ngram.push_back(encoded_tokens[j]);
       }
diff --git a/mert/Ngram.h b/mert/Ngram.h
index d3e8041a3..811f21f27 100644
--- a/mert/Ngram.h
+++ b/mert/Ngram.h
@@ -2,12 +2,13 @@
 #define MERT_NGRAM_H_
 
 #include <vector>
-#include <map>
 #include <string>
 
+#include <boost/unordered_map.hpp>
+
 namespace MosesTuning
 {
-  
+
 /** A simple STL-std::map based n-gram counts. Basically, we provide
  * typical accessors and mutaors, but we intentionally does not allow
  * erasing elements.
@@ -35,8 +36,8 @@ class NgramCounts {
 
   typedef std::vector<int> Key;
   typedef int Value;
-  typedef std::map<Key, Value, NgramComparator>::iterator iterator;
-  typedef std::map<Key, Value, NgramComparator>::const_iterator const_iterator;
+  typedef boost::unordered_map<Key, Value>::iterator iterator;
+  typedef boost::unordered_map<Key, Value>::const_iterator const_iterator;
 
   NgramCounts() : kDefaultCount(1) { }
   virtual ~NgramCounts() { }
@@ -95,7 +96,7 @@ class NgramCounts {
 
  private:
   const int kDefaultCount;
-  std::map<Key, Value, NgramComparator> m_counts;
+  boost::unordered_map<Key, Value> m_counts;
 };
 
 }
-- 
cgit v1.2.3