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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
|
// $Id$
/***********************************************************************
Moses - factored phrase-based language decoder
Copyright (C) 2006 University of Edinburgh
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
***********************************************************************/
#pragma once
#include <list>
#include <limits>
#include <vector>
#define PROJECT_NAME "moses"
#ifndef BOS_
#define BOS_ "<s>" //Beginning of sentence symbol
#endif
#ifndef EOS_
#define EOS_ "</s>" //End of sentence symbol
#endif
#define UNKNOWN_FACTOR "UNK"
#define EPSILON "*EPS*"
#define NOT_FOUND std::numeric_limits<size_t>::max()
#define MAX_NGRAM_SIZE 20
const size_t DEFAULT_MAX_HYPOSTACK_SIZE = 200;
const size_t DEFAULT_MAX_TRANS_OPT_SIZE = 50;
const size_t DEFAULT_MAX_PART_TRANS_OPT_SIZE = 10000;
const size_t DEFAULT_MAX_PHRASE_LENGTH = 20;
const size_t ARRAY_SIZE_INCR = 10; //amount by which a phrase gets resized when necessary
const float LOWEST_SCORE = -100.0f;
const float DEFAULT_BEAM_WIDTH = 0.00001f;
const size_t DEFAULT_VERBOSE_LEVEL = 1;
/////////////////////////////////////////////////
// for those using autoconf/automake
#if HAVE_CONFIG_H
#include "config.h"
#define TRACE_ENABLE 1 // REMOVE after we figure this out
# ifdef HAVE_SRILM
# define LM_SRI 1
# else
# undef LM_SRI
# endif
# ifdef HAVE_IRSTLM
# define LM_IRST 1
# endif
#endif
/////////////////////////////////////////////////
// enums.
// must be 0, 1, 2, ..., unless otherwise stated
// can only be 2 at the moment
const int NUM_LANGUAGES = 2;
const size_t MAX_NUM_FACTORS = 4;
enum FactorDirection
{
Input, //! Source factors
Output //! Target factors
};
enum DecodeType
{
Translate
,Generate
,InsertNullFertilityWord //! an optional step that attempts to insert a few closed-class words to improve LM scores
};
namespace LexReorderType
{
enum LexReorderType //TODO explain values
{
Backward
,Forward
,Bidirectional
,Fe
,F
};
}
namespace DistortionOrientationType
{
enum DistortionOrientationOptions
{
Monotone, //distinguish only between monotone and non-monotone as possible orientations
Msd //further separate non-monotone into swapped and discontinuous
};
}
enum LMType
{
SingleFactor
,MultiFactor
};
enum LMImplementation
{
SRI = 0
,IRST = 1
,Skip = 2
,Joint = 3
,Internal = 4
};
enum InputTypeEnum
{
SentenceInput = 0
,ConfusionNetworkInput = 1
,WordLatticeInput = 2
};
enum XmlInputType
{
XmlPassThrough = 0,
XmlIgnore = 1,
XmlExclusive = 2,
XmlInclusive = 3
};
enum DictionaryFind
{
Best
,All
};
// typedef
typedef size_t FactorType;
#ifdef WIN32
#include <BaseTsd.h>
#else
#include <stdint.h>
typedef uint32_t UINT32;
#endif
class TranslationOption;
typedef std::vector<TranslationOption*> TranslationOptionList;
|
