Edinburgh Speech Tools  2.4-release
 All Classes Functions Variables Typedefs Enumerations Enumerator Friends Pages
scfg_test_main.cc
1 /*************************************************************************/
2 /* */
3 /* Centre for Speech Technology Research */
4 /* University of Edinburgh, UK */
5 /* Copyright (c) 1996,1997 */
6 /* All Rights Reserved. */
7 /* */
8 /* Permission is hereby granted, free of charge, to use and distribute */
9 /* this software and its documentation without restriction, including */
10 /* without limitation the rights to use, copy, modify, merge, publish, */
11 /* distribute, sublicense, and/or sell copies of this work, and to */
12 /* permit persons to whom this work is furnished to do so, subject to */
13 /* the following conditions: */
14 /* 1. The code must retain the above copyright notice, this list of */
15 /* conditions and the following disclaimer. */
16 /* 2. Any modifications must be clearly marked as such. */
17 /* 3. Original authors' names are not deleted. */
18 /* 4. The authors' names are not used to endorse or promote products */
19 /* derived from this software without specific prior written */
20 /* permission. */
21 /* */
22 /* THE UNIVERSITY OF EDINBURGH AND THE CONTRIBUTORS TO THIS WORK */
23 /* DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING */
24 /* ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT */
25 /* SHALL THE UNIVERSITY OF EDINBURGH NOR THE CONTRIBUTORS BE LIABLE */
26 /* FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES */
27 /* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN */
28 /* AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, */
29 /* ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF */
30 /* THIS SOFTWARE. */
31 /* */
32 /*************************************************************************/
33 /* Author : Alan W Black */
34 /* Date : October 1997 */
35 /*-----------------------------------------------------------------------*/
36 /* Test a stochastic context free grammar with respect to a given */
37 /* corpus. */
38 /* */
39 /* Can test against a bracket corpus or simply parse it */
40 /* */
41 /*=======================================================================*/
42 #include <cstdlib>
43 #include <cstdio>
44 #include <iostream>
45 #include <fstream>
46 #include <cstring>
47 #include "EST.h"
48 #include "EST_SCFG.h"
49 #include "siod.h"
50 
51 static EST_String outfile = "-";
52 
53 static int scfg_test_main(int argc, char **argv);
54 
55 /** @name <command>scfg_test</command> <emphasis>Test the output of a parser</emphasis>
56  @id scfg-make-manual
57  * @toc
58  */
59 
60 
61 //@{
62 
63 
64 /**@name Synopsis
65  */
66 //@{
67 
68 //@synopsis
69 
70 /**
71 
72 This program applies a stochastic context free grammar to a given
73 corpus and reports the parsing accuracy and cross bracketing
74 accuracy of the grammar with respect to the grammar.
75 
76  */
77 
78 //@}
79 
80 /**@name OPTIONS
81  */
82 //@{
83 
84 //@options
85 
86 //@}
87 
88 
89 int main(int argc, char **argv)
90 {
91 
92  scfg_test_main(argc,argv);
93 
94  exit(0);
95  return 0;
96 }
97 
98 static int scfg_test_main(int argc, char **argv)
99 {
100  // Top level function generates a probabilistic grammar
101  EST_Option al;
102  EST_StrList files;
103 
104  parse_command_line
105  (argc, argv,
106  EST_String("[options]\n")+
107  "Summary: Test a stochastic context free grammar against a corpus\n"+
108  "-grammar <ifile> Grammar file, one rule per line.\n"+
109  "-corpus <ifile> Single Corpus file, one bracketed sentence per line.\n"+
110  "-crossbrackets Measure cross bracket performance.\n"+
111  "-heap <int> {210000}\n"+
112  " Set size of Lisp heap, needed for large corpora\n"+
113  "-o <ofile> Output file for parsed sentences.\n",
114  files, al);
115 
116  if (al.present("-o"))
117  outfile = al.val("-o");
118  else
119  outfile = "-";
120 
121  siod_init(al.ival("-heap"));
122 
123  EST_SCFG_traintest grammar;
124 
125  if (al.present("-grammar"))
126  {
127  grammar.load(al.val("-grammar"));
128  }
129  else
130  {
131  cerr << "scfg_test: no grammar specified" << endl;
132  exit(1);
133  }
134 
135  if (al.present("-corpus"))
136  {
137  grammar.load_corpus(al.val("-corpus"));
138  }
139  else
140  {
141  cerr << "scfg_test: no corpus specified" << endl;
142  exit(1);
143  }
144 
145  // Test and summarise parsing of corpus
146  if (al.present("-crossbrackets"))
147  grammar.test_crossbrackets(); // parse and test brackets
148  else
149  grammar.test_corpus(); // only cross entropy
150 
151  return 0;
152 }