opener-opinion-detector-basic 2.0.0 → 2.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +2 -0
- data/ext/hack/Rakefile +0 -2
- data/lib/opener/opinion_detector_basic/version.rb +1 -1
- data/opener-opinion-detector-basic.gemspec +0 -1
- data/task/compile.rake +1 -1
- data/task/requirements.rake +0 -1
- metadata +2 -142
- data/core/vendor/src/crfsuite/AUTHORS +0 -1
- data/core/vendor/src/crfsuite/COPYING +0 -27
- data/core/vendor/src/crfsuite/ChangeLog +0 -103
- data/core/vendor/src/crfsuite/INSTALL +0 -236
- data/core/vendor/src/crfsuite/Makefile.am +0 -19
- data/core/vendor/src/crfsuite/Makefile.in +0 -783
- data/core/vendor/src/crfsuite/README +0 -183
- data/core/vendor/src/crfsuite/aclocal.m4 +0 -9018
- data/core/vendor/src/crfsuite/autogen.sh +0 -38
- data/core/vendor/src/crfsuite/compile +0 -143
- data/core/vendor/src/crfsuite/config.guess +0 -1502
- data/core/vendor/src/crfsuite/config.h.in +0 -198
- data/core/vendor/src/crfsuite/config.sub +0 -1714
- data/core/vendor/src/crfsuite/configure +0 -14273
- data/core/vendor/src/crfsuite/configure.in +0 -149
- data/core/vendor/src/crfsuite/crfsuite.sln +0 -42
- data/core/vendor/src/crfsuite/depcomp +0 -630
- data/core/vendor/src/crfsuite/example/chunking.py +0 -49
- data/core/vendor/src/crfsuite/example/crfutils.py +0 -179
- data/core/vendor/src/crfsuite/example/ner.py +0 -270
- data/core/vendor/src/crfsuite/example/pos.py +0 -78
- data/core/vendor/src/crfsuite/example/template.py +0 -88
- data/core/vendor/src/crfsuite/frontend/Makefile.am +0 -29
- data/core/vendor/src/crfsuite/frontend/Makefile.in +0 -640
- data/core/vendor/src/crfsuite/frontend/dump.c +0 -116
- data/core/vendor/src/crfsuite/frontend/frontend.vcxproj +0 -129
- data/core/vendor/src/crfsuite/frontend/iwa.c +0 -273
- data/core/vendor/src/crfsuite/frontend/iwa.h +0 -65
- data/core/vendor/src/crfsuite/frontend/learn.c +0 -439
- data/core/vendor/src/crfsuite/frontend/main.c +0 -137
- data/core/vendor/src/crfsuite/frontend/option.c +0 -93
- data/core/vendor/src/crfsuite/frontend/option.h +0 -86
- data/core/vendor/src/crfsuite/frontend/readdata.h +0 -38
- data/core/vendor/src/crfsuite/frontend/reader.c +0 -136
- data/core/vendor/src/crfsuite/frontend/tag.c +0 -427
- data/core/vendor/src/crfsuite/genbinary.sh.in +0 -15
- data/core/vendor/src/crfsuite/include/Makefile.am +0 -11
- data/core/vendor/src/crfsuite/include/Makefile.in +0 -461
- data/core/vendor/src/crfsuite/include/crfsuite.h +0 -1063
- data/core/vendor/src/crfsuite/include/crfsuite.hpp +0 -555
- data/core/vendor/src/crfsuite/include/crfsuite_api.hpp +0 -400
- data/core/vendor/src/crfsuite/include/os.h +0 -61
- data/core/vendor/src/crfsuite/install-sh +0 -520
- data/core/vendor/src/crfsuite/lib/cqdb/COPYING +0 -28
- data/core/vendor/src/crfsuite/lib/cqdb/Makefile.am +0 -21
- data/core/vendor/src/crfsuite/lib/cqdb/Makefile.in +0 -549
- data/core/vendor/src/crfsuite/lib/cqdb/cqdb.vcxproj +0 -86
- data/core/vendor/src/crfsuite/lib/cqdb/include/cqdb.h +0 -524
- data/core/vendor/src/crfsuite/lib/cqdb/src/cqdb.c +0 -587
- data/core/vendor/src/crfsuite/lib/cqdb/src/lookup3.c +0 -976
- data/core/vendor/src/crfsuite/lib/crf/Makefile.am +0 -46
- data/core/vendor/src/crfsuite/lib/crf/Makefile.in +0 -721
- data/core/vendor/src/crfsuite/lib/crf/crf.vcxproj +0 -216
- data/core/vendor/src/crfsuite/lib/crf/src/crf1d.h +0 -353
- data/core/vendor/src/crfsuite/lib/crf/src/crf1d_context.c +0 -705
- data/core/vendor/src/crfsuite/lib/crf/src/crf1d_encode.c +0 -943
- data/core/vendor/src/crfsuite/lib/crf/src/crf1d_feature.c +0 -352
- data/core/vendor/src/crfsuite/lib/crf/src/crf1d_model.c +0 -994
- data/core/vendor/src/crfsuite/lib/crf/src/crf1d_tag.c +0 -550
- data/core/vendor/src/crfsuite/lib/crf/src/crfsuite.c +0 -492
- data/core/vendor/src/crfsuite/lib/crf/src/crfsuite_internal.h +0 -236
- data/core/vendor/src/crfsuite/lib/crf/src/crfsuite_train.c +0 -272
- data/core/vendor/src/crfsuite/lib/crf/src/dataset.c +0 -106
- data/core/vendor/src/crfsuite/lib/crf/src/dictionary.c +0 -118
- data/core/vendor/src/crfsuite/lib/crf/src/holdout.c +0 -80
- data/core/vendor/src/crfsuite/lib/crf/src/logging.c +0 -91
- data/core/vendor/src/crfsuite/lib/crf/src/logging.h +0 -48
- data/core/vendor/src/crfsuite/lib/crf/src/params.c +0 -335
- data/core/vendor/src/crfsuite/lib/crf/src/params.h +0 -80
- data/core/vendor/src/crfsuite/lib/crf/src/quark.c +0 -172
- data/core/vendor/src/crfsuite/lib/crf/src/quark.h +0 -46
- data/core/vendor/src/crfsuite/lib/crf/src/rumavl.c +0 -1107
- data/core/vendor/src/crfsuite/lib/crf/src/rumavl.h +0 -160
- data/core/vendor/src/crfsuite/lib/crf/src/train_arow.c +0 -408
- data/core/vendor/src/crfsuite/lib/crf/src/train_averaged_perceptron.c +0 -242
- data/core/vendor/src/crfsuite/lib/crf/src/train_l2sgd.c +0 -507
- data/core/vendor/src/crfsuite/lib/crf/src/train_lbfgs.c +0 -338
- data/core/vendor/src/crfsuite/lib/crf/src/train_passive_aggressive.c +0 -435
- data/core/vendor/src/crfsuite/lib/crf/src/vecmath.h +0 -341
- data/core/vendor/src/crfsuite/ltmain.sh +0 -8413
- data/core/vendor/src/crfsuite/missing +0 -376
- data/core/vendor/src/crfsuite/swig/Makefile.am +0 -13
- data/core/vendor/src/crfsuite/swig/Makefile.in +0 -365
- data/core/vendor/src/crfsuite/swig/crfsuite.cpp +0 -2
- data/core/vendor/src/crfsuite/swig/export.i +0 -32
- data/core/vendor/src/crfsuite/swig/python/README +0 -92
- data/core/vendor/src/crfsuite/swig/python/crfsuite.py +0 -329
- data/core/vendor/src/crfsuite/swig/python/export_wrap.cpp +0 -14355
- data/core/vendor/src/crfsuite/swig/python/export_wrap.h +0 -63
- data/core/vendor/src/crfsuite/swig/python/prepare.sh +0 -9
- data/core/vendor/src/crfsuite/swig/python/sample_tag.py +0 -52
- data/core/vendor/src/crfsuite/swig/python/sample_train.py +0 -68
- data/core/vendor/src/crfsuite/swig/python/setup.py +0 -44
- data/core/vendor/src/crfsuite/win32/stdint.h +0 -679
- data/core/vendor/src/liblbfgs/AUTHORS +0 -1
- data/core/vendor/src/liblbfgs/COPYING +0 -22
- data/core/vendor/src/liblbfgs/ChangeLog +0 -120
- data/core/vendor/src/liblbfgs/INSTALL +0 -231
- data/core/vendor/src/liblbfgs/Makefile.am +0 -10
- data/core/vendor/src/liblbfgs/Makefile.in +0 -638
- data/core/vendor/src/liblbfgs/NEWS +0 -0
- data/core/vendor/src/liblbfgs/README +0 -71
- data/core/vendor/src/liblbfgs/aclocal.m4 +0 -6985
- data/core/vendor/src/liblbfgs/autogen.sh +0 -38
- data/core/vendor/src/liblbfgs/config.guess +0 -1411
- data/core/vendor/src/liblbfgs/config.h.in +0 -64
- data/core/vendor/src/liblbfgs/config.sub +0 -1500
- data/core/vendor/src/liblbfgs/configure +0 -21146
- data/core/vendor/src/liblbfgs/configure.in +0 -107
- data/core/vendor/src/liblbfgs/depcomp +0 -522
- data/core/vendor/src/liblbfgs/include/lbfgs.h +0 -745
- data/core/vendor/src/liblbfgs/install-sh +0 -322
- data/core/vendor/src/liblbfgs/lbfgs.sln +0 -26
- data/core/vendor/src/liblbfgs/lib/Makefile.am +0 -24
- data/core/vendor/src/liblbfgs/lib/Makefile.in +0 -499
- data/core/vendor/src/liblbfgs/lib/arithmetic_ansi.h +0 -133
- data/core/vendor/src/liblbfgs/lib/arithmetic_sse_double.h +0 -294
- data/core/vendor/src/liblbfgs/lib/arithmetic_sse_float.h +0 -298
- data/core/vendor/src/liblbfgs/lib/lbfgs.c +0 -1371
- data/core/vendor/src/liblbfgs/lib/lib.vcxproj +0 -95
- data/core/vendor/src/liblbfgs/ltmain.sh +0 -6426
- data/core/vendor/src/liblbfgs/missing +0 -353
- data/core/vendor/src/liblbfgs/sample/Makefile.am +0 -15
- data/core/vendor/src/liblbfgs/sample/Makefile.in +0 -433
- data/core/vendor/src/liblbfgs/sample/sample.c +0 -81
- data/core/vendor/src/liblbfgs/sample/sample.cpp +0 -126
- data/core/vendor/src/liblbfgs/sample/sample.vcxproj +0 -105
- data/core/vendor/src/svm_light/LICENSE.txt +0 -59
- data/core/vendor/src/svm_light/Makefile +0 -105
- data/core/vendor/src/svm_light/kernel.h +0 -40
- data/core/vendor/src/svm_light/svm_classify.c +0 -197
- data/core/vendor/src/svm_light/svm_common.c +0 -985
- data/core/vendor/src/svm_light/svm_common.h +0 -301
- data/core/vendor/src/svm_light/svm_hideo.c +0 -1062
- data/core/vendor/src/svm_light/svm_learn.c +0 -4147
- data/core/vendor/src/svm_light/svm_learn.h +0 -169
- data/core/vendor/src/svm_light/svm_learn_main.c +0 -397
- data/core/vendor/src/svm_light/svm_loqo.c +0 -211
- data/task/c.rake +0 -36
- data/task/submodules.rake +0 -5
@@ -1,550 +0,0 @@
|
|
1
|
-
/*
|
2
|
-
* CRF1d tagger (implementation of crfsuite_model_t and crfsuite_tagger_t).
|
3
|
-
*
|
4
|
-
* Copyright (c) 2007-2010, Naoaki Okazaki
|
5
|
-
* All rights reserved.
|
6
|
-
*
|
7
|
-
* Redistribution and use in source and binary forms, with or without
|
8
|
-
* modification, are permitted provided that the following conditions are met:
|
9
|
-
* * Redistributions of source code must retain the above copyright
|
10
|
-
* notice, this list of conditions and the following disclaimer.
|
11
|
-
* * Redistributions in binary form must reproduce the above copyright
|
12
|
-
* notice, this list of conditions and the following disclaimer in the
|
13
|
-
* documentation and/or other materials provided with the distribution.
|
14
|
-
* * Neither the names of the authors nor the names of its contributors
|
15
|
-
* may be used to endorse or promote products derived from this
|
16
|
-
* software without specific prior written permission.
|
17
|
-
*
|
18
|
-
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
19
|
-
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
20
|
-
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
21
|
-
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
|
22
|
-
* OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
23
|
-
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
24
|
-
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
25
|
-
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
26
|
-
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
27
|
-
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
28
|
-
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
29
|
-
*/
|
30
|
-
|
31
|
-
/* $Id$ */
|
32
|
-
|
33
|
-
#ifdef HAVE_CONFIG_H
|
34
|
-
#include <config.h>
|
35
|
-
#endif/*HAVE_CONFIG_H*/
|
36
|
-
|
37
|
-
#include <os.h>
|
38
|
-
|
39
|
-
#include <math.h>
|
40
|
-
#include <stdio.h>
|
41
|
-
#include <stdlib.h>
|
42
|
-
#include <string.h>
|
43
|
-
|
44
|
-
#include <crfsuite.h>
|
45
|
-
|
46
|
-
#include "crf1d.h"
|
47
|
-
|
48
|
-
enum {
|
49
|
-
LEVEL_NONE = 0,
|
50
|
-
LEVEL_SET,
|
51
|
-
LEVEL_ALPHABETA,
|
52
|
-
};
|
53
|
-
|
54
|
-
typedef struct {
|
55
|
-
crf1dm_t *model; /**< CRF model. */
|
56
|
-
crf1d_context_t *ctx; /**< CRF context. */
|
57
|
-
int num_labels; /**< Number of distinct output labels (L). */
|
58
|
-
int num_attributes; /**< Number of distinct attributes (A). */
|
59
|
-
int level;
|
60
|
-
} crf1dt_t;
|
61
|
-
|
62
|
-
static void crf1dt_state_score(crf1dt_t *crf1dt, const crfsuite_instance_t *inst)
|
63
|
-
{
|
64
|
-
int a, i, l, t, r, fid;
|
65
|
-
crf1dm_feature_t f;
|
66
|
-
feature_refs_t attr;
|
67
|
-
floatval_t value, *state = NULL;
|
68
|
-
crf1dm_t* model = crf1dt->model;
|
69
|
-
crf1d_context_t* ctx = crf1dt->ctx;
|
70
|
-
const crfsuite_item_t* item = NULL;
|
71
|
-
const int T = inst->num_items;
|
72
|
-
const int L = crf1dt->num_labels;
|
73
|
-
|
74
|
-
/* Loop over the items in the sequence. */
|
75
|
-
for (t = 0;t < T;++t) {
|
76
|
-
item = &inst->items[t];
|
77
|
-
state = STATE_SCORE(ctx, t);
|
78
|
-
|
79
|
-
/* Loop over the contents (attributes) attached to the item. */
|
80
|
-
for (i = 0;i < item->num_contents;++i) {
|
81
|
-
/* Access the list of state features associated with the attribute. */
|
82
|
-
a = item->contents[i].aid;
|
83
|
-
crf1dm_get_attrref(model, a, &attr);
|
84
|
-
/* A scale usually represents the atrribute frequency in the item. */
|
85
|
-
value = item->contents[i].value;
|
86
|
-
|
87
|
-
/* Loop over the state features associated with the attribute. */
|
88
|
-
for (r = 0;r < attr.num_features;++r) {
|
89
|
-
/* The state feature #(attr->fids[r]), which is represented by
|
90
|
-
the attribute #a, outputs the label #(f->dst). */
|
91
|
-
fid = crf1dm_get_featureid(&attr, r);
|
92
|
-
crf1dm_get_feature(model, fid, &f);
|
93
|
-
l = f.dst;
|
94
|
-
state[l] += f.weight * value;
|
95
|
-
}
|
96
|
-
}
|
97
|
-
}
|
98
|
-
}
|
99
|
-
|
100
|
-
static void crf1dt_transition_score(crf1dt_t* crf1dt)
|
101
|
-
{
|
102
|
-
int i, r, fid;
|
103
|
-
crf1dm_feature_t f;
|
104
|
-
feature_refs_t edge;
|
105
|
-
floatval_t *trans = NULL;
|
106
|
-
crf1dm_t* model = crf1dt->model;
|
107
|
-
crf1d_context_t* ctx = crf1dt->ctx;
|
108
|
-
const int L = crf1dt->num_labels;
|
109
|
-
|
110
|
-
/* Compute transition scores between two labels. */
|
111
|
-
for (i = 0;i < L;++i) {
|
112
|
-
trans = TRANS_SCORE(ctx, i);
|
113
|
-
crf1dm_get_labelref(model, i, &edge);
|
114
|
-
for (r = 0;r < edge.num_features;++r) {
|
115
|
-
/* Transition feature from #i to #(f->dst). */
|
116
|
-
fid = crf1dm_get_featureid(&edge, r);
|
117
|
-
crf1dm_get_feature(model, fid, &f);
|
118
|
-
trans[f.dst] = f.weight;
|
119
|
-
}
|
120
|
-
}
|
121
|
-
}
|
122
|
-
|
123
|
-
static void crf1dt_set_level(crf1dt_t *crf1dt, int level)
|
124
|
-
{
|
125
|
-
int prev = crf1dt->level;
|
126
|
-
crf1d_context_t* ctx = crf1dt->ctx;
|
127
|
-
|
128
|
-
if (level <= LEVEL_ALPHABETA && prev < LEVEL_ALPHABETA) {
|
129
|
-
crf1dc_exp_state(ctx);
|
130
|
-
crf1dc_alpha_score(ctx);
|
131
|
-
crf1dc_beta_score(ctx);
|
132
|
-
}
|
133
|
-
|
134
|
-
crf1dt->level = level;
|
135
|
-
}
|
136
|
-
|
137
|
-
static void crf1dt_delete(crf1dt_t* crf1dt)
|
138
|
-
{
|
139
|
-
/* Note: we don't own the model object (crf1t->model). */
|
140
|
-
if (crf1dt->ctx != NULL) {
|
141
|
-
crf1dc_delete(crf1dt->ctx);
|
142
|
-
crf1dt->ctx = NULL;
|
143
|
-
}
|
144
|
-
free(crf1dt);
|
145
|
-
}
|
146
|
-
|
147
|
-
static crf1dt_t *crf1dt_new(crf1dm_t* crf1dm)
|
148
|
-
{
|
149
|
-
crf1dt_t* crf1dt = NULL;
|
150
|
-
|
151
|
-
crf1dt = (crf1dt_t*)calloc(1, sizeof(crf1dt_t));
|
152
|
-
if (crf1dt != NULL) {
|
153
|
-
crf1dt->num_labels = crf1dm_get_num_labels(crf1dm);
|
154
|
-
crf1dt->num_attributes = crf1dm_get_num_attrs(crf1dm);
|
155
|
-
crf1dt->model = crf1dm;
|
156
|
-
crf1dt->ctx = crf1dc_new(CTXF_VITERBI | CTXF_MARGINALS, crf1dt->num_labels, 0);
|
157
|
-
if (crf1dt->ctx != NULL) {
|
158
|
-
crf1dc_reset(crf1dt->ctx, RF_TRANS);
|
159
|
-
crf1dt_transition_score(crf1dt);
|
160
|
-
crf1dc_exp_transition(crf1dt->ctx);
|
161
|
-
} else {
|
162
|
-
crf1dt_delete(crf1dt);
|
163
|
-
crf1dt = NULL;
|
164
|
-
}
|
165
|
-
crf1dt->level = LEVEL_NONE;
|
166
|
-
}
|
167
|
-
|
168
|
-
return crf1dt;
|
169
|
-
}
|
170
|
-
|
171
|
-
|
172
|
-
|
173
|
-
/*
|
174
|
-
* Implementation of crfsuite_tagger_t object.
|
175
|
-
* This object is instantiated only by a crfsuite_model_t object.
|
176
|
-
*/
|
177
|
-
|
178
|
-
static int tagger_addref(crfsuite_tagger_t* tagger)
|
179
|
-
{
|
180
|
-
/* This object is owned only by a crfsuite_model_t object. */
|
181
|
-
return tagger->nref;
|
182
|
-
}
|
183
|
-
|
184
|
-
static int tagger_release(crfsuite_tagger_t* tagger)
|
185
|
-
{
|
186
|
-
/* This object is owned only by a crfsuite_model_t object. */
|
187
|
-
return tagger->nref;
|
188
|
-
}
|
189
|
-
|
190
|
-
static int tagger_set(crfsuite_tagger_t* tagger, crfsuite_instance_t *inst)
|
191
|
-
{
|
192
|
-
crf1dt_t* crf1dt = (crf1dt_t*)tagger->internal;
|
193
|
-
crf1d_context_t* ctx = crf1dt->ctx;
|
194
|
-
crf1dc_set_num_items(ctx, inst->num_items);
|
195
|
-
crf1dc_reset(crf1dt->ctx, RF_STATE);
|
196
|
-
crf1dt_state_score(crf1dt, inst);
|
197
|
-
crf1dt->level = LEVEL_SET;
|
198
|
-
return 0;
|
199
|
-
}
|
200
|
-
|
201
|
-
static int tagger_length(crfsuite_tagger_t* tagger)
|
202
|
-
{
|
203
|
-
crf1dt_t* crf1dt = (crf1dt_t*)tagger->internal;
|
204
|
-
crf1d_context_t* ctx = crf1dt->ctx;
|
205
|
-
return ctx->num_items;
|
206
|
-
}
|
207
|
-
|
208
|
-
static int tagger_viterbi(crfsuite_tagger_t* tagger, int *labels, floatval_t *ptr_score)
|
209
|
-
{
|
210
|
-
floatval_t score;
|
211
|
-
crf1dt_t* crf1dt = (crf1dt_t*)tagger->internal;
|
212
|
-
crf1d_context_t* ctx = crf1dt->ctx;
|
213
|
-
|
214
|
-
score = crf1dc_viterbi(ctx, labels);
|
215
|
-
if (ptr_score != NULL) {
|
216
|
-
*ptr_score = score;
|
217
|
-
}
|
218
|
-
|
219
|
-
return 0;
|
220
|
-
}
|
221
|
-
|
222
|
-
static int tagger_score(crfsuite_tagger_t* tagger, int *path, floatval_t *ptr_score)
|
223
|
-
{
|
224
|
-
floatval_t score;
|
225
|
-
crf1dt_t* crf1dt = (crf1dt_t*)tagger->internal;
|
226
|
-
crf1d_context_t* ctx = crf1dt->ctx;
|
227
|
-
score = crf1dc_score(ctx, path);
|
228
|
-
if (ptr_score != NULL) {
|
229
|
-
*ptr_score = score;
|
230
|
-
}
|
231
|
-
return 0;
|
232
|
-
}
|
233
|
-
|
234
|
-
static int tagger_lognorm(crfsuite_tagger_t* tagger, floatval_t *ptr_norm)
|
235
|
-
{
|
236
|
-
crf1dt_t* crf1dt = (crf1dt_t*)tagger->internal;
|
237
|
-
crf1dt_set_level(crf1dt, LEVEL_ALPHABETA);
|
238
|
-
*ptr_norm = crf1dc_lognorm(crf1dt->ctx);
|
239
|
-
return 0;
|
240
|
-
}
|
241
|
-
|
242
|
-
static int tagger_marginal_point(crfsuite_tagger_t *tagger, int l, int t, floatval_t *ptr_prob)
|
243
|
-
{
|
244
|
-
crf1dt_t* crf1dt = (crf1dt_t*)tagger->internal;
|
245
|
-
crf1dt_set_level(crf1dt, LEVEL_ALPHABETA);
|
246
|
-
*ptr_prob = crf1dc_marginal_point(crf1dt->ctx, l, t);
|
247
|
-
return 0;
|
248
|
-
}
|
249
|
-
|
250
|
-
static int tagger_marginal_path(crfsuite_tagger_t *tagger, const int *path, int begin, int end, floatval_t *ptr_prob)
|
251
|
-
{
|
252
|
-
crf1dt_t* crf1dt = (crf1dt_t*)tagger->internal;
|
253
|
-
crf1dt_set_level(crf1dt, LEVEL_ALPHABETA);
|
254
|
-
*ptr_prob = crf1dc_marginal_path(crf1dt->ctx, path, begin, end);
|
255
|
-
return 0;
|
256
|
-
}
|
257
|
-
|
258
|
-
|
259
|
-
|
260
|
-
/*
|
261
|
-
* Implementation of crfsuite_dictionary_t object for attributes.
|
262
|
-
* This object is instantiated only by a crfsuite_model_t object.
|
263
|
-
*/
|
264
|
-
|
265
|
-
static int model_attrs_addref(crfsuite_dictionary_t* dic)
|
266
|
-
{
|
267
|
-
/* This object is owned only by a crfsuite_model_t object. */
|
268
|
-
return dic->nref;
|
269
|
-
}
|
270
|
-
|
271
|
-
static int model_attrs_release(crfsuite_dictionary_t* dic)
|
272
|
-
{
|
273
|
-
/* This object is owned and freed only by a crfsuite_model_t object. */
|
274
|
-
return dic->nref;
|
275
|
-
}
|
276
|
-
|
277
|
-
static int model_attrs_get(crfsuite_dictionary_t* dic, const char *str)
|
278
|
-
{
|
279
|
-
/* This object is ready only. */
|
280
|
-
return CRFSUITEERR_NOTSUPPORTED;
|
281
|
-
}
|
282
|
-
|
283
|
-
static int model_attrs_to_id(crfsuite_dictionary_t* dic, const char *str)
|
284
|
-
{
|
285
|
-
crf1dm_t *crf1dm = (crf1dm_t*)dic->internal;
|
286
|
-
return crf1dm_to_aid(crf1dm, str);
|
287
|
-
}
|
288
|
-
|
289
|
-
static int model_attrs_to_string(crfsuite_dictionary_t* dic, int id, char const **pstr)
|
290
|
-
{
|
291
|
-
crf1dm_t *crf1dm = (crf1dm_t*)dic->internal;
|
292
|
-
*pstr = crf1dm_to_attr(crf1dm, id);
|
293
|
-
return 0;
|
294
|
-
}
|
295
|
-
|
296
|
-
static int model_attrs_num(crfsuite_dictionary_t* dic)
|
297
|
-
{
|
298
|
-
crf1dm_t *crf1dm = (crf1dm_t*)dic->internal;
|
299
|
-
return crf1dm_get_num_attrs(crf1dm);
|
300
|
-
}
|
301
|
-
|
302
|
-
static void model_attrs_free(crfsuite_dictionary_t* dic, const char *str)
|
303
|
-
{
|
304
|
-
/* all strings are freed on the release of the dictionary object. */
|
305
|
-
}
|
306
|
-
|
307
|
-
|
308
|
-
|
309
|
-
|
310
|
-
/*
|
311
|
-
* Implementation of crfsuite_dictionary_t object for labels.
|
312
|
-
* This object is instantiated only by a crfsuite_model_t object.
|
313
|
-
*/
|
314
|
-
|
315
|
-
static int model_labels_addref(crfsuite_dictionary_t* dic)
|
316
|
-
{
|
317
|
-
/* This object is owned only by a crfsuite_model_t object. */
|
318
|
-
return dic->nref;
|
319
|
-
}
|
320
|
-
|
321
|
-
static int model_labels_release(crfsuite_dictionary_t* dic)
|
322
|
-
{
|
323
|
-
/* This object is owned and freed only by a crfsuite_model_t object. */
|
324
|
-
return dic->nref;
|
325
|
-
}
|
326
|
-
|
327
|
-
static int model_labels_get(crfsuite_dictionary_t* dic, const char *str)
|
328
|
-
{
|
329
|
-
/* This object is ready only. */
|
330
|
-
return CRFSUITEERR_NOTSUPPORTED;
|
331
|
-
}
|
332
|
-
|
333
|
-
static int model_labels_to_id(crfsuite_dictionary_t* dic, const char *str)
|
334
|
-
{
|
335
|
-
crf1dm_t *crf1dm = (crf1dm_t*)dic->internal;
|
336
|
-
return crf1dm_to_lid(crf1dm, str);
|
337
|
-
}
|
338
|
-
|
339
|
-
static int model_labels_to_string(crfsuite_dictionary_t* dic, int id, char const **pstr)
|
340
|
-
{
|
341
|
-
crf1dm_t *crf1dm = (crf1dm_t*)dic->internal;
|
342
|
-
*pstr = crf1dm_to_label(crf1dm, id);
|
343
|
-
return 0;
|
344
|
-
}
|
345
|
-
|
346
|
-
static int model_labels_num(crfsuite_dictionary_t* dic)
|
347
|
-
{
|
348
|
-
crf1dm_t *crf1dm = (crf1dm_t*)dic->internal;
|
349
|
-
return crf1dm_get_num_labels(crf1dm);
|
350
|
-
}
|
351
|
-
|
352
|
-
static void model_labels_free(crfsuite_dictionary_t* dic, const char *str)
|
353
|
-
{
|
354
|
-
/* all strings are freed on the release of the dictionary object. */
|
355
|
-
}
|
356
|
-
|
357
|
-
|
358
|
-
|
359
|
-
/*
|
360
|
-
* Implementation of crfsuite_model_t object.
|
361
|
-
* This object is instantiated by crf1m_model_create() function.
|
362
|
-
*/
|
363
|
-
|
364
|
-
typedef struct {
|
365
|
-
crf1dm_t* crf1dm;
|
366
|
-
|
367
|
-
crfsuite_dictionary_t* attrs;
|
368
|
-
crfsuite_dictionary_t* labels;
|
369
|
-
crfsuite_tagger_t* tagger;
|
370
|
-
} model_internal_t;
|
371
|
-
|
372
|
-
static int model_addref(crfsuite_model_t* model)
|
373
|
-
{
|
374
|
-
return crfsuite_interlocked_increment(&model->nref);
|
375
|
-
}
|
376
|
-
|
377
|
-
static int model_release(crfsuite_model_t* model)
|
378
|
-
{
|
379
|
-
int count = crfsuite_interlocked_decrement(&model->nref);
|
380
|
-
if (count == 0) {
|
381
|
-
/* This instance is being destroyed. */
|
382
|
-
model_internal_t* internal = (model_internal_t*)model->internal;
|
383
|
-
crf1dt_delete((crf1dt_t*)internal->tagger->internal);
|
384
|
-
free(internal->tagger);
|
385
|
-
free(internal->labels);
|
386
|
-
free(internal->attrs);
|
387
|
-
crf1dm_close(internal->crf1dm);
|
388
|
-
free(internal);
|
389
|
-
free(model);
|
390
|
-
}
|
391
|
-
return count;
|
392
|
-
}
|
393
|
-
|
394
|
-
static int model_get_tagger(crfsuite_model_t* model, crfsuite_tagger_t** ptr_tagger)
|
395
|
-
{
|
396
|
-
model_internal_t* internal = (model_internal_t*)model->internal;
|
397
|
-
/* We don't increment the reference counter. */
|
398
|
-
*ptr_tagger = internal->tagger;
|
399
|
-
return 0;
|
400
|
-
}
|
401
|
-
|
402
|
-
static int model_get_labels(crfsuite_model_t* model, crfsuite_dictionary_t** ptr_labels)
|
403
|
-
{
|
404
|
-
model_internal_t* internal = (model_internal_t*)model->internal;
|
405
|
-
/* We don't increment the reference counter. */
|
406
|
-
*ptr_labels = internal->labels;
|
407
|
-
return 0;
|
408
|
-
}
|
409
|
-
|
410
|
-
static int model_get_attrs(crfsuite_model_t* model, crfsuite_dictionary_t** ptr_attrs)
|
411
|
-
{
|
412
|
-
model_internal_t* internal = (model_internal_t*)model->internal;
|
413
|
-
/* We don't increment the reference counter. */
|
414
|
-
*ptr_attrs = internal->attrs;
|
415
|
-
return 0;
|
416
|
-
}
|
417
|
-
|
418
|
-
static int model_dump(crfsuite_model_t* model, FILE *fpo)
|
419
|
-
{
|
420
|
-
model_internal_t* internal = (model_internal_t*)model->internal;
|
421
|
-
crf1dm_dump(internal->crf1dm, fpo);
|
422
|
-
return 0;
|
423
|
-
}
|
424
|
-
|
425
|
-
static int crf1m_model_create(const char *filename, crfsuite_model_t** ptr_model)
|
426
|
-
{
|
427
|
-
int ret = 0;
|
428
|
-
crf1dm_t *crf1dm = NULL;
|
429
|
-
crf1dt_t *crf1dt = NULL;
|
430
|
-
crfsuite_model_t *model = NULL;
|
431
|
-
model_internal_t *internal = NULL;
|
432
|
-
crfsuite_tagger_t *tagger = NULL;
|
433
|
-
crfsuite_dictionary_t *attrs = NULL, *labels = NULL;
|
434
|
-
|
435
|
-
*ptr_model = NULL;
|
436
|
-
|
437
|
-
/* Open the model file. */
|
438
|
-
crf1dm = crf1dm_new(filename);
|
439
|
-
if (crf1dm == NULL) {
|
440
|
-
ret = CRFSUITEERR_INCOMPATIBLE;
|
441
|
-
goto error_exit;
|
442
|
-
}
|
443
|
-
|
444
|
-
/* Construct a tagger based on the model. */
|
445
|
-
crf1dt = crf1dt_new(crf1dm);
|
446
|
-
if (crf1dt == NULL) {
|
447
|
-
ret = CRFSUITEERR_OUTOFMEMORY;
|
448
|
-
goto error_exit;
|
449
|
-
}
|
450
|
-
|
451
|
-
/* Create an instance of internal data attached to the model. */
|
452
|
-
internal = (model_internal_t*)calloc(1, sizeof(model_internal_t));
|
453
|
-
if (internal == NULL) {
|
454
|
-
ret = CRFSUITEERR_OUTOFMEMORY;
|
455
|
-
goto error_exit;
|
456
|
-
}
|
457
|
-
|
458
|
-
/* Create an instance of dictionary object for attributes. */
|
459
|
-
attrs = (crfsuite_dictionary_t*)calloc(1, sizeof(crfsuite_dictionary_t));
|
460
|
-
if (attrs == NULL) {
|
461
|
-
ret = CRFSUITEERR_OUTOFMEMORY;
|
462
|
-
goto error_exit;
|
463
|
-
}
|
464
|
-
attrs->internal = crf1dm;
|
465
|
-
attrs->nref = 1;
|
466
|
-
attrs->addref = model_attrs_addref;
|
467
|
-
attrs->release = model_attrs_release;
|
468
|
-
attrs->get = model_attrs_get;
|
469
|
-
attrs->to_id = model_attrs_to_id;
|
470
|
-
attrs->to_string = model_attrs_to_string;
|
471
|
-
attrs->num = model_attrs_num;
|
472
|
-
attrs->free = model_attrs_free;
|
473
|
-
|
474
|
-
/* Create an instance of dictionary object for labels. */
|
475
|
-
labels = (crfsuite_dictionary_t*)calloc(1, sizeof(crfsuite_dictionary_t));
|
476
|
-
if (labels == NULL) {
|
477
|
-
ret = CRFSUITEERR_OUTOFMEMORY;
|
478
|
-
goto error_exit;
|
479
|
-
}
|
480
|
-
labels->internal = crf1dm;
|
481
|
-
labels->nref = 1;
|
482
|
-
labels->addref = model_labels_addref;
|
483
|
-
labels->release = model_labels_release;
|
484
|
-
labels->get = model_labels_get;
|
485
|
-
labels->to_id = model_labels_to_id;
|
486
|
-
labels->to_string = model_labels_to_string;
|
487
|
-
labels->num = model_labels_num;
|
488
|
-
labels->free = model_labels_free;
|
489
|
-
|
490
|
-
/* Create an instance of tagger object. */
|
491
|
-
tagger = (crfsuite_tagger_t*)calloc(1, sizeof(crfsuite_tagger_t));
|
492
|
-
if (tagger == NULL) {
|
493
|
-
ret = CRFSUITEERR_OUTOFMEMORY;
|
494
|
-
goto error_exit;
|
495
|
-
}
|
496
|
-
tagger->internal = crf1dt;
|
497
|
-
tagger->nref = 1;
|
498
|
-
tagger->addref = tagger_addref;
|
499
|
-
tagger->release = tagger_release;
|
500
|
-
tagger->set = tagger_set;
|
501
|
-
tagger->length = tagger_length;
|
502
|
-
tagger->viterbi = tagger_viterbi;
|
503
|
-
tagger->score = tagger_score;
|
504
|
-
tagger->lognorm = tagger_lognorm;
|
505
|
-
tagger->marginal_point = tagger_marginal_point;
|
506
|
-
tagger->marginal_path = tagger_marginal_path;
|
507
|
-
|
508
|
-
/* Set the internal data for the model object. */
|
509
|
-
internal->crf1dm = crf1dm;
|
510
|
-
internal->attrs = attrs;
|
511
|
-
internal->labels = labels;
|
512
|
-
internal->tagger = tagger;
|
513
|
-
|
514
|
-
/* Create an instance of model object. */
|
515
|
-
model = (crfsuite_model_t*)calloc(1, sizeof(crfsuite_model_t));
|
516
|
-
if (model == NULL) {
|
517
|
-
ret = CRFSUITEERR_OUTOFMEMORY;
|
518
|
-
goto error_exit;
|
519
|
-
}
|
520
|
-
model->internal = internal;
|
521
|
-
model->nref = 1;
|
522
|
-
model->addref = model_addref;
|
523
|
-
model->release = model_release;
|
524
|
-
model->get_attrs = model_get_attrs;
|
525
|
-
model->get_labels = model_get_labels;
|
526
|
-
model->get_tagger = model_get_tagger;
|
527
|
-
model->dump = model_dump;
|
528
|
-
|
529
|
-
*ptr_model = model;
|
530
|
-
return 0;
|
531
|
-
|
532
|
-
error_exit:
|
533
|
-
free(tagger);
|
534
|
-
free(labels);
|
535
|
-
free(attrs);
|
536
|
-
if (crf1dt != NULL) {
|
537
|
-
crf1dt_delete(crf1dt);
|
538
|
-
}
|
539
|
-
if (crf1dm != NULL) {
|
540
|
-
crf1dm_close(crf1dm);
|
541
|
-
}
|
542
|
-
free(internal);
|
543
|
-
free(model);
|
544
|
-
return ret;
|
545
|
-
}
|
546
|
-
|
547
|
-
int crf1m_create_instance_from_file(const char *filename, void **ptr)
|
548
|
-
{
|
549
|
-
return crf1m_model_create(filename, (crfsuite_model_t**)ptr);
|
550
|
-
}
|