UjjwalVIT commited on
Commit
77b3126
1 Parent(s): 9fe6001

Upload 17 files

Browse files
.gitattributes CHANGED
@@ -34,3 +34,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  stanford-ner.jar filter=lfs diff=lfs merge=lfs -text
 
 
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  stanford-ner.jar filter=lfs diff=lfs merge=lfs -text
37
+ stanford_model/stanford-ner-4.2.0-javadoc.jar filter=lfs diff=lfs merge=lfs -text
38
+ stanford_model/stanford-ner-4.2.0-sources.jar filter=lfs diff=lfs merge=lfs -text
39
+ stanford_model/stanford-ner-4.2.0.jar filter=lfs diff=lfs merge=lfs -text
stanford_model/LICENSE.txt ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ GNU GENERAL PUBLIC LICENSE
2
+ Version 2, June 1991
3
+
4
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
5
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
6
+ Everyone is permitted to copy and distribute verbatim copies
7
+ of this license document, but changing it is not allowed.
8
+
9
+ Preamble
10
+
11
+ The licenses for most software are designed to take away your
12
+ freedom to share and change it. By contrast, the GNU General Public
13
+ License is intended to guarantee your freedom to share and change free
14
+ software--to make sure the software is free for all its users. This
15
+ General Public License applies to most of the Free Software
16
+ Foundation's software and to any other program whose authors commit to
17
+ using it. (Some other Free Software Foundation software is covered by
18
+ the GNU Lesser General Public License instead.) You can apply it to
19
+ your programs, too.
20
+
21
+ When we speak of free software, we are referring to freedom, not
22
+ price. Our General Public Licenses are designed to make sure that you
23
+ have the freedom to distribute copies of free software (and charge for
24
+ this service if you wish), that you receive source code or can get it
25
+ if you want it, that you can change the software or use pieces of it
26
+ in new free programs; and that you know you can do these things.
27
+
28
+ To protect your rights, we need to make restrictions that forbid
29
+ anyone to deny you these rights or to ask you to surrender the rights.
30
+ These restrictions translate to certain responsibilities for you if you
31
+ distribute copies of the software, or if you modify it.
32
+
33
+ For example, if you distribute copies of such a program, whether
34
+ gratis or for a fee, you must give the recipients all the rights that
35
+ you have. You must make sure that they, too, receive or can get the
36
+ source code. And you must show them these terms so they know their
37
+ rights.
38
+
39
+ We protect your rights with two steps: (1) copyright the software, and
40
+ (2) offer you this license which gives you legal permission to copy,
41
+ distribute and/or modify the software.
42
+
43
+ Also, for each author's protection and ours, we want to make certain
44
+ that everyone understands that there is no warranty for this free
45
+ software. If the software is modified by someone else and passed on, we
46
+ want its recipients to know that what they have is not the original, so
47
+ that any problems introduced by others will not reflect on the original
48
+ authors' reputations.
49
+
50
+ Finally, any free program is threatened constantly by software
51
+ patents. We wish to avoid the danger that redistributors of a free
52
+ program will individually obtain patent licenses, in effect making the
53
+ program proprietary. To prevent this, we have made it clear that any
54
+ patent must be licensed for everyone's free use or not licensed at all.
55
+
56
+ The precise terms and conditions for copying, distribution and
57
+ modification follow.
58
+
59
+ GNU GENERAL PUBLIC LICENSE
60
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
61
+
62
+ 0. This License applies to any program or other work which contains
63
+ a notice placed by the copyright holder saying it may be distributed
64
+ under the terms of this General Public License. The "Program", below,
65
+ refers to any such program or work, and a "work based on the Program"
66
+ means either the Program or any derivative work under copyright law:
67
+ that is to say, a work containing the Program or a portion of it,
68
+ either verbatim or with modifications and/or translated into another
69
+ language. (Hereinafter, translation is included without limitation in
70
+ the term "modification".) Each licensee is addressed as "you".
71
+
72
+ Activities other than copying, distribution and modification are not
73
+ covered by this License; they are outside its scope. The act of
74
+ running the Program is not restricted, and the output from the Program
75
+ is covered only if its contents constitute a work based on the
76
+ Program (independent of having been made by running the Program).
77
+ Whether that is true depends on what the Program does.
78
+
79
+ 1. You may copy and distribute verbatim copies of the Program's
80
+ source code as you receive it, in any medium, provided that you
81
+ conspicuously and appropriately publish on each copy an appropriate
82
+ copyright notice and disclaimer of warranty; keep intact all the
83
+ notices that refer to this License and to the absence of any warranty;
84
+ and give any other recipients of the Program a copy of this License
85
+ along with the Program.
86
+
87
+ You may charge a fee for the physical act of transferring a copy, and
88
+ you may at your option offer warranty protection in exchange for a fee.
89
+
90
+ 2. You may modify your copy or copies of the Program or any portion
91
+ of it, thus forming a work based on the Program, and copy and
92
+ distribute such modifications or work under the terms of Section 1
93
+ above, provided that you also meet all of these conditions:
94
+
95
+ a) You must cause the modified files to carry prominent notices
96
+ stating that you changed the files and the date of any change.
97
+
98
+ b) You must cause any work that you distribute or publish, that in
99
+ whole or in part contains or is derived from the Program or any
100
+ part thereof, to be licensed as a whole at no charge to all third
101
+ parties under the terms of this License.
102
+
103
+ c) If the modified program normally reads commands interactively
104
+ when run, you must cause it, when started running for such
105
+ interactive use in the most ordinary way, to print or display an
106
+ announcement including an appropriate copyright notice and a
107
+ notice that there is no warranty (or else, saying that you provide
108
+ a warranty) and that users may redistribute the program under
109
+ these conditions, and telling the user how to view a copy of this
110
+ License. (Exception: if the Program itself is interactive but
111
+ does not normally print such an announcement, your work based on
112
+ the Program is not required to print an announcement.)
113
+
114
+ These requirements apply to the modified work as a whole. If
115
+ identifiable sections of that work are not derived from the Program,
116
+ and can be reasonably considered independent and separate works in
117
+ themselves, then this License, and its terms, do not apply to those
118
+ sections when you distribute them as separate works. But when you
119
+ distribute the same sections as part of a whole which is a work based
120
+ on the Program, the distribution of the whole must be on the terms of
121
+ this License, whose permissions for other licensees extend to the
122
+ entire whole, and thus to each and every part regardless of who wrote it.
123
+
124
+ Thus, it is not the intent of this section to claim rights or contest
125
+ your rights to work written entirely by you; rather, the intent is to
126
+ exercise the right to control the distribution of derivative or
127
+ collective works based on the Program.
128
+
129
+ In addition, mere aggregation of another work not based on the Program
130
+ with the Program (or with a work based on the Program) on a volume of
131
+ a storage or distribution medium does not bring the other work under
132
+ the scope of this License.
133
+
134
+ 3. You may copy and distribute the Program (or a work based on it,
135
+ under Section 2) in object code or executable form under the terms of
136
+ Sections 1 and 2 above provided that you also do one of the following:
137
+
138
+ a) Accompany it with the complete corresponding machine-readable
139
+ source code, which must be distributed under the terms of Sections
140
+ 1 and 2 above on a medium customarily used for software interchange; or,
141
+
142
+ b) Accompany it with a written offer, valid for at least three
143
+ years, to give any third party, for a charge no more than your
144
+ cost of physically performing source distribution, a complete
145
+ machine-readable copy of the corresponding source code, to be
146
+ distributed under the terms of Sections 1 and 2 above on a medium
147
+ customarily used for software interchange; or,
148
+
149
+ c) Accompany it with the information you received as to the offer
150
+ to distribute corresponding source code. (This alternative is
151
+ allowed only for noncommercial distribution and only if you
152
+ received the program in object code or executable form with such
153
+ an offer, in accord with Subsection b above.)
154
+
155
+ The source code for a work means the preferred form of the work for
156
+ making modifications to it. For an executable work, complete source
157
+ code means all the source code for all modules it contains, plus any
158
+ associated interface definition files, plus the scripts used to
159
+ control compilation and installation of the executable. However, as a
160
+ special exception, the source code distributed need not include
161
+ anything that is normally distributed (in either source or binary
162
+ form) with the major components (compiler, kernel, and so on) of the
163
+ operating system on which the executable runs, unless that component
164
+ itself accompanies the executable.
165
+
166
+ If distribution of executable or object code is made by offering
167
+ access to copy from a designated place, then offering equivalent
168
+ access to copy the source code from the same place counts as
169
+ distribution of the source code, even though third parties are not
170
+ compelled to copy the source along with the object code.
171
+
172
+ 4. You may not copy, modify, sublicense, or distribute the Program
173
+ except as expressly provided under this License. Any attempt
174
+ otherwise to copy, modify, sublicense or distribute the Program is
175
+ void, and will automatically terminate your rights under this License.
176
+ However, parties who have received copies, or rights, from you under
177
+ this License will not have their licenses terminated so long as such
178
+ parties remain in full compliance.
179
+
180
+ 5. You are not required to accept this License, since you have not
181
+ signed it. However, nothing else grants you permission to modify or
182
+ distribute the Program or its derivative works. These actions are
183
+ prohibited by law if you do not accept this License. Therefore, by
184
+ modifying or distributing the Program (or any work based on the
185
+ Program), you indicate your acceptance of this License to do so, and
186
+ all its terms and conditions for copying, distributing or modifying
187
+ the Program or works based on it.
188
+
189
+ 6. Each time you redistribute the Program (or any work based on the
190
+ Program), the recipient automatically receives a license from the
191
+ original licensor to copy, distribute or modify the Program subject to
192
+ these terms and conditions. You may not impose any further
193
+ restrictions on the recipients' exercise of the rights granted herein.
194
+ You are not responsible for enforcing compliance by third parties to
195
+ this License.
196
+
197
+ 7. If, as a consequence of a court judgment or allegation of patent
198
+ infringement or for any other reason (not limited to patent issues),
199
+ conditions are imposed on you (whether by court order, agreement or
200
+ otherwise) that contradict the conditions of this License, they do not
201
+ excuse you from the conditions of this License. If you cannot
202
+ distribute so as to satisfy simultaneously your obligations under this
203
+ License and any other pertinent obligations, then as a consequence you
204
+ may not distribute the Program at all. For example, if a patent
205
+ license would not permit royalty-free redistribution of the Program by
206
+ all those who receive copies directly or indirectly through you, then
207
+ the only way you could satisfy both it and this License would be to
208
+ refrain entirely from distribution of the Program.
209
+
210
+ If any portion of this section is held invalid or unenforceable under
211
+ any particular circumstance, the balance of the section is intended to
212
+ apply and the section as a whole is intended to apply in other
213
+ circumstances.
214
+
215
+ It is not the purpose of this section to induce you to infringe any
216
+ patents or other property right claims or to contest validity of any
217
+ such claims; this section has the sole purpose of protecting the
218
+ integrity of the free software distribution system, which is
219
+ implemented by public license practices. Many people have made
220
+ generous contributions to the wide range of software distributed
221
+ through that system in reliance on consistent application of that
222
+ system; it is up to the author/donor to decide if he or she is willing
223
+ to distribute software through any other system and a licensee cannot
224
+ impose that choice.
225
+
226
+ This section is intended to make thoroughly clear what is believed to
227
+ be a consequence of the rest of this License.
228
+
229
+ 8. If the distribution and/or use of the Program is restricted in
230
+ certain countries either by patents or by copyrighted interfaces, the
231
+ original copyright holder who places the Program under this License
232
+ may add an explicit geographical distribution limitation excluding
233
+ those countries, so that distribution is permitted only in or among
234
+ countries not thus excluded. In such case, this License incorporates
235
+ the limitation as if written in the body of this License.
236
+
237
+ 9. The Free Software Foundation may publish revised and/or new versions
238
+ of the General Public License from time to time. Such new versions will
239
+ be similar in spirit to the present version, but may differ in detail to
240
+ address new problems or concerns.
241
+
242
+ Each version is given a distinguishing version number. If the Program
243
+ specifies a version number of this License which applies to it and "any
244
+ later version", you have the option of following the terms and conditions
245
+ either of that version or of any later version published by the Free
246
+ Software Foundation. If the Program does not specify a version number of
247
+ this License, you may choose any version ever published by the Free Software
248
+ Foundation.
249
+
250
+ 10. If you wish to incorporate parts of the Program into other free
251
+ programs whose distribution conditions are different, write to the author
252
+ to ask for permission. For software which is copyrighted by the Free
253
+ Software Foundation, write to the Free Software Foundation; we sometimes
254
+ make exceptions for this. Our decision will be guided by the two goals
255
+ of preserving the free status of all derivatives of our free software and
256
+ of promoting the sharing and reuse of software generally.
257
+
258
+ NO WARRANTY
259
+
260
+ 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
261
+ FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
262
+ OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
263
+ PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
264
+ OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
265
+ MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
266
+ TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
267
+ PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
268
+ REPAIR OR CORRECTION.
269
+
270
+ 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
271
+ WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
272
+ REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
273
+ INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
274
+ OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
275
+ TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
276
+ YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
277
+ PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
278
+ POSSIBILITY OF SUCH DAMAGES.
279
+
280
+ END OF TERMS AND CONDITIONS
281
+
282
+ How to Apply These Terms to Your New Programs
283
+
284
+ If you develop a new program, and you want it to be of the greatest
285
+ possible use to the public, the best way to achieve this is to make it
286
+ free software which everyone can redistribute and change under these terms.
287
+
288
+ To do so, attach the following notices to the program. It is safest
289
+ to attach them to the start of each source file to most effectively
290
+ convey the exclusion of warranty; and each file should have at least
291
+ the "copyright" line and a pointer to where the full notice is found.
292
+
293
+ <one line to give the program's name and a brief idea of what it does.>
294
+ Copyright (C) <year> <name of author>
295
+
296
+ This program is free software; you can redistribute it and/or modify
297
+ it under the terms of the GNU General Public License as published by
298
+ the Free Software Foundation; either version 2 of the License, or
299
+ (at your option) any later version.
300
+
301
+ This program is distributed in the hope that it will be useful,
302
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
303
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
304
+ GNU General Public License for more details.
305
+
306
+ You should have received a copy of the GNU General Public License along
307
+ with this program; if not, write to the Free Software Foundation, Inc.,
308
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
309
+
310
+ Also add information on how to contact you by electronic and paper mail.
311
+
312
+ If the program is interactive, make it output a short notice like this
313
+ when it starts in an interactive mode:
314
+
315
+ Gnomovision version 69, Copyright (C) year name of author
316
+ Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
317
+ This is free software, and you are welcome to redistribute it
318
+ under certain conditions; type `show c' for details.
319
+
320
+ The hypothetical commands `show w' and `show c' should show the appropriate
321
+ parts of the General Public License. Of course, the commands you use may
322
+ be called something other than `show w' and `show c'; they could even be
323
+ mouse-clicks or menu items--whatever suits your program.
324
+
325
+ You should also get your employer (if you work as a programmer) or your
326
+ school, if any, to sign a "copyright disclaimer" for the program, if
327
+ necessary. Here is a sample; alter the names:
328
+
329
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the program
330
+ `Gnomovision' (which makes passes at compilers) written by James Hacker.
331
+
332
+ <signature of Ty Coon>, 1 April 1989
333
+ Ty Coon, President of Vice
334
+
335
+ This General Public License does not permit incorporating your program into
336
+ proprietary programs. If your program is a subroutine library, you may
337
+ consider it more useful to permit linking proprietary applications with the
338
+ library. If this is what you want to do, use the GNU Lesser General
339
+ Public License instead of this License.
stanford_model/NERDemo.java ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import edu.stanford.nlp.ie.AbstractSequenceClassifier;
2
+ import edu.stanford.nlp.ie.crf.*;
3
+ import edu.stanford.nlp.io.IOUtils;
4
+ import edu.stanford.nlp.ling.CoreLabel;
5
+ import edu.stanford.nlp.ling.CoreAnnotations;
6
+ import edu.stanford.nlp.sequences.DocumentReaderAndWriter;
7
+ import edu.stanford.nlp.util.Triple;
8
+
9
+ import java.util.List;
10
+
11
+
12
+ /** This is a demo of calling CRFClassifier programmatically.
13
+ * <p>
14
+ * Usage: {@code java -mx400m -cp "*" NERDemo [serializedClassifier [fileName]] }
15
+ * <p>
16
+ * If arguments aren't specified, they default to
17
+ * classifiers/english.all.3class.distsim.crf.ser.gz and some hardcoded sample text.
18
+ * If run with arguments, it shows some of the ways to get k-best labelings and
19
+ * probabilities out with CRFClassifier. If run without arguments, it shows some of
20
+ * the alternative output formats that you can get.
21
+ * <p>
22
+ * To use CRFClassifier from the command line:
23
+ * </p><blockquote>
24
+ * {@code java -mx400m edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier [classifier] -textFile [file] }
25
+ * </blockquote><p>
26
+ * Or if the file is already tokenized and one word per line, perhaps in
27
+ * a tab-separated value format with extra columns for part-of-speech tag,
28
+ * etc., use the version below (note the 's' instead of the 'x'):
29
+ * </p><blockquote>
30
+ * {@code java -mx400m edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier [classifier] -testFile [file] }
31
+ * </blockquote>
32
+ *
33
+ * @author Jenny Finkel
34
+ * @author Christopher Manning
35
+ */
36
+
37
+ public class NERDemo {
38
+
39
+ public static void main(String[] args) throws Exception {
40
+
41
+ String serializedClassifier = "classifiers/english.all.3class.distsim.crf.ser.gz";
42
+
43
+ if (args.length > 0) {
44
+ serializedClassifier = args[0];
45
+ }
46
+
47
+ AbstractSequenceClassifier<CoreLabel> classifier = CRFClassifier.getClassifier(serializedClassifier);
48
+
49
+ /* For either a file to annotate or for the hardcoded text example, this
50
+ demo file shows several ways to process the input, for teaching purposes.
51
+ */
52
+
53
+ if (args.length > 1) {
54
+
55
+ /* For the file, it shows (1) how to run NER on a String, (2) how
56
+ to get the entities in the String with character offsets, and
57
+ (3) how to run NER on a whole file (without loading it into a String).
58
+ */
59
+
60
+ String fileContents = IOUtils.slurpFile(args[1]);
61
+ List<List<CoreLabel>> out = classifier.classify(fileContents);
62
+ for (List<CoreLabel> sentence : out) {
63
+ for (CoreLabel word : sentence) {
64
+ System.out.print(word.word() + '/' + word.get(CoreAnnotations.AnswerAnnotation.class) + ' ');
65
+ }
66
+ System.out.println();
67
+ }
68
+
69
+ System.out.println("---");
70
+ out = classifier.classifyFile(args[1]);
71
+ for (List<CoreLabel> sentence : out) {
72
+ for (CoreLabel word : sentence) {
73
+ System.out.print(word.word() + '/' + word.get(CoreAnnotations.AnswerAnnotation.class) + ' ');
74
+ }
75
+ System.out.println();
76
+ }
77
+
78
+ System.out.println("---");
79
+ List<Triple<String, Integer, Integer>> list = classifier.classifyToCharacterOffsets(fileContents);
80
+ for (Triple<String, Integer, Integer> item : list) {
81
+ System.out.println(item.first() + ": " + fileContents.substring(item.second(), item.third()));
82
+ }
83
+ System.out.println("---");
84
+ System.out.println("Ten best entity labelings");
85
+ DocumentReaderAndWriter<CoreLabel> readerAndWriter = classifier.makePlainTextReaderAndWriter();
86
+ classifier.classifyAndWriteAnswersKBest(args[1], 10, readerAndWriter);
87
+
88
+ System.out.println("---");
89
+ System.out.println("Per-token marginalized probabilities");
90
+ classifier.printProbs(args[1], readerAndWriter);
91
+
92
+ // -- This code prints out the first order (token pair) clique probabilities.
93
+ // -- But that output is a bit overwhelming, so we leave it commented out by default.
94
+ // System.out.println("---");
95
+ // System.out.println("First Order Clique Probabilities");
96
+ // ((CRFClassifier) classifier).printFirstOrderProbs(args[1], readerAndWriter);
97
+
98
+ } else {
99
+
100
+ /* For the hard-coded String, it shows how to run it on a single
101
+ sentence, and how to do this and produce several formats, including
102
+ slash tags and an inline XML output format. It also shows the full
103
+ contents of the {@code CoreLabel}s that are constructed by the
104
+ classifier. And it shows getting out the probabilities of different
105
+ assignments and an n-best list of classifications with probabilities.
106
+ */
107
+
108
+ String[] example = {"Good afternoon Rajat Raina, how are you today?",
109
+ "I go to school at Stanford University, which is located in California." };
110
+ for (String str : example) {
111
+ System.out.println(classifier.classifyToString(str));
112
+ }
113
+ System.out.println("---");
114
+
115
+ for (String str : example) {
116
+ // This one puts in spaces and newlines between tokens, so just print not println.
117
+ System.out.print(classifier.classifyToString(str, "slashTags", false));
118
+ }
119
+ System.out.println("---");
120
+
121
+ for (String str : example) {
122
+ // This one is best for dealing with the output as a TSV (tab-separated column) file.
123
+ // The first column gives entities, the second their classes, and the third the remaining text in a document
124
+ System.out.print(classifier.classifyToString(str, "tabbedEntities", false));
125
+ }
126
+ System.out.println("---");
127
+
128
+ for (String str : example) {
129
+ System.out.println(classifier.classifyWithInlineXML(str));
130
+ }
131
+ System.out.println("---");
132
+
133
+ for (String str : example) {
134
+ System.out.println(classifier.classifyToString(str, "xml", true));
135
+ }
136
+ System.out.println("---");
137
+
138
+ for (String str : example) {
139
+ System.out.print(classifier.classifyToString(str, "tsv", false));
140
+ }
141
+ System.out.println("---");
142
+
143
+ // This gets out entities with character offsets
144
+ int j = 0;
145
+ for (String str : example) {
146
+ j++;
147
+ List<Triple<String,Integer,Integer>> triples = classifier.classifyToCharacterOffsets(str);
148
+ for (Triple<String,Integer,Integer> trip : triples) {
149
+ System.out.printf("%s over character offsets [%d, %d) in sentence %d.%n",
150
+ trip.first(), trip.second(), trip.third, j);
151
+ }
152
+ }
153
+ System.out.println("---");
154
+
155
+ // This prints out all the details of what is stored for each token
156
+ int i=0;
157
+ for (String str : example) {
158
+ for (List<CoreLabel> lcl : classifier.classify(str)) {
159
+ for (CoreLabel cl : lcl) {
160
+ System.out.print(i++ + ": ");
161
+ System.out.println(cl.toShorterString());
162
+ }
163
+ }
164
+ }
165
+
166
+ System.out.println("---");
167
+
168
+ }
169
+ }
170
+
171
+ }
stanford_model/README.txt ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Stanford NER - v4.2.0 - 2020-11-17
2
+ ----------------------------------------------
3
+
4
+ This package provides a high-performance machine learning based named
5
+ entity recognition system, including facilities to train models from
6
+ supervised training data and pre-trained models for English.
7
+
8
+ (c) 2002-2020. The Board of Trustees of The Leland
9
+ Stanford Junior University. All Rights Reserved.
10
+
11
+ Original CRF code by Jenny Finkel.
12
+ Additional modules, features, internationalization, compaction, and
13
+ support code by Christopher Manning, Dan Klein, Christopher Cox, Huy Nguyen
14
+ Shipra Dingare, Anna Rafferty, and John Bauer.
15
+ This release prepared by Jason Bolton.
16
+
17
+ LICENSE
18
+
19
+ The software is licensed under the full GPL v2+. Please see the file LICENCE.txt
20
+
21
+ For more information, bug reports, and fixes, contact:
22
+ Christopher Manning
23
+ Dept of Computer Science, Gates 2A
24
+ Stanford CA 94305-9020
25
+ USA
26
+ java-nlp-support@lists.stanford.edu
27
+ https://nlp.stanford.edu/software/CRF-NER.html
28
+
29
+ CONTACT
30
+
31
+ For questions about this distribution, please contact Stanford's JavaNLP group
32
+ at java-nlp-user@lists.stanford.edu. We provide assistance on a best-effort
33
+ basis.
34
+
35
+ TUTORIAL
36
+
37
+ Quickstart guidelines, primarily for end users who wish to use the included NER
38
+ models, are below. For further instructions on training your own NER model,
39
+ go to https://nlp.stanford.edu/software/crf-faq.html.
40
+
41
+ INCLUDED SERIALIZED MODELS / TRAINING DATA
42
+
43
+ The basic included serialized model is a 3 class NER tagger that can
44
+ label: PERSON, ORGANIZATION, and LOCATION entities. It is included as
45
+ english.all.3class.distsim.crf.ser.gz. It is trained on data from
46
+ CoNLL, MUC6, MUC7, ACE, OntoNotes, and Wikipedia.
47
+ Because this model is trained on both US
48
+ and UK newswire, it is fairly robust across the two domains.
49
+
50
+ We have also included a 4 class NER tagger trained on the CoNLL 2003
51
+ Shared Task training data that labels for PERSON, ORGANIZATION,
52
+ LOCATION, and MISC. It is named
53
+ english.conll.4class.distsim.crf.ser.gz .
54
+
55
+ A third model is trained only on data from MUC and
56
+ distinguishes between 7 different classes:
57
+ english.muc.7class.distsim.crf.ser.gz.
58
+
59
+ All of the serialized classifiers come in two versions, one trained to
60
+ basically expected standard written English capitalization, and the other
61
+ to ignore capitalization information. The case-insensitive versions
62
+ of the three models available on the Stanford NER webpage.
63
+ These models use a distributional similarity lexicon to improve performance
64
+ (by between 1.5%-3% F-measure). The distributional similarity features
65
+ make the models perform substantially better, but they require rather
66
+ more memory. The distsim models are included in the release package.
67
+ The nodistsim versions of the same models may be available on the
68
+ Stanford NER webpage.
69
+
70
+ Finally, we have models for other languages, including two German models,
71
+ a Chinese model, and a Spanish model. The files for these models can be
72
+ found at:
73
+
74
+ http://nlp.stanford.edu/software/CRF-NER.html
75
+
76
+
77
+ QUICKSTART INSTRUCTIONS
78
+
79
+ This NER system requires Java 1.8 or later.
80
+
81
+ Providing java is on your PATH, you should be able to run an NER GUI
82
+ demonstration by just clicking. It might work to double-click on the
83
+ stanford-ner.jar archive but this may well fail as the operating system
84
+ does not give Java enough memory for our NER system, so it is safer to
85
+ instead double click on the ner-gui.bat icon (Windows) or ner-gui.sh
86
+ (Linux/Unix/MacOSX). Then, using the top option from the Classifier
87
+ menu, load a CRF classifier from the classifiers directory of the
88
+ distribution. You can then `either load a text file or web page from
89
+ the File menu, or decide to use the default text in the window. Finally,
90
+ you can now named entity tag the text by pressing the Run NER button.
91
+
92
+ From a command line, you need to have java on your PATH and the
93
+ stanford-ner.jar file and the lib directory in your CLASSPATH. (The way of doing this depends on
94
+ your OS/shell.) The supplied ner.bat and ner.sh should work to allow
95
+ you to tag a single file. For example, for Windows:
96
+
97
+ ner file
98
+
99
+ Or on Unix/Linux you should be able to parse the test file in the distribution
100
+ directory with the command:
101
+
102
+ java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier classifiers/english.all.3class.distsim.crf.ser.gz -textFile sample.txt
103
+
104
+ Here's an output option that will print out entities and their class to
105
+ the first two columns of a tab-separated columns output file:
106
+
107
+ java -mx600m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier classifiers/english.all.3class.distsim.crf.ser.gz -outputFormat tabbedEntities -textFile sample.txt > sample.tsv
108
+
109
+ When run from a jar file, you also have the option of using a serialized
110
+ classifier contained in the jar file.
111
+
112
+ USING FULL STANFORD CORENLP NER FUNCTIONALITY
113
+
114
+ This standalone distribution also allows access to the full NER
115
+ capabilities of the Stanford CoreNLP pipeline. These capabilities
116
+ can be accessed via the NERClassifierCombiner class.
117
+ NERClassifierCombiner allows for multiple CRFs to be used together,
118
+ and has options for recognizing numeric sequence patterns and time
119
+ patterns with the rule-based NER of SUTime.
120
+
121
+ Suppose one combines three CRF's CRF-1,CRF-2, and CRF-3 with the
122
+ NERClassifierCombiner. When the NERClassiferCombiner runs, it will
123
+ first apply the NER tags of CRF-1 to the text, then it will apply
124
+ CRF-2's NER tags to any tokens not tagged by CRF-1 and so on. If
125
+ the option ner.combinationMode is set to NORMAL (default), any label
126
+ applied by CRF-1 cannot be applied by subsequent CRF's. For instance
127
+ if CRF-1 applies the LOCATION tag, no other CRF's LOCATION tag will be
128
+ used. If ner.combinationMode is set to HIGH_RECALL, this limitation
129
+ will be deactivated.
130
+
131
+ To use NERClassifierCombiner at the command-line, the jars in lib
132
+ and stanford-ner.jar must be in the CLASSPATH. Here is an example command:
133
+
134
+ java -mx2g edu.stanford.nlp.ie.NERClassifierCombiner -ner.model \
135
+ classifiers/english.conll.4class.distsim.crf.ser.gz,classifiers/english.muc.7class.distsim.crf.ser.gz \
136
+ -ner.useSUTime false -textFile sample-w-time.txt
137
+
138
+ Let's break this down a bit. The flag "-ner.model" should be followed by a
139
+ list of CRF's to be combined by the NERClassifierCombiner. Some serialized
140
+ CRF's are provided in the classifiers directory. In this example the CRF's
141
+ trained on the CONLL 4 class data and the MUC 7 class data are being combined.
142
+
143
+ When the flag "-ner.useSUTime" is followed by "false", SUTime is shut off. You should
144
+ note that when the "false" is omitted, the text "4 days ago" suddenly is
145
+ tagged with DATE. These are the kinds of phrases SUTime can identify.
146
+
147
+ NERClassifierCombiner can be run on different types of input as well. Here is
148
+ an example which is run on CONLL style input:
149
+
150
+ java -mx2g edu.stanford.nlp.ie.NERClassifierCombiner -ner.model \
151
+ classifiers/english.conll.4class.distsim.crf.ser.gz,classifiers/english.muc.7class.distsim.crf.ser.gz \
152
+ -map word=0,answer=1 -testFile sample-conll-file.txt
153
+
154
+ It is crucial to include the "-map word=0,answer=1" , which is specifying that
155
+ the input test file has the words in the first column and the answer labels
156
+ in the second column.
157
+
158
+ It is also possible to serialize and load an NERClassifierCombiner.
159
+
160
+ This command loads the three sample crfs with combinationMode=HIGH_RECALL
161
+ and SUTime=false, and dumps them to a file named
162
+ test_serialized_ncc.ncc.ser.gz
163
+
164
+ java -mx2g edu.stanford.nlp.ie.NERClassifierCombiner -ner.model \
165
+ classifiers/english.conll.4class.distsim.crf.ser.gz,classifiers/english.muc.7class.distsim.crf.ser.gz,\
166
+ classifiers/english.all.3class.distsim.crf.ser.gz -ner.useSUTime false \
167
+ -ner.combinationMode HIGH_RECALL -serializeTo test.serialized.ncc.ncc.ser.gz
168
+
169
+ An example serialized NERClassifierCombiner with these settings is supplied in
170
+ the classifiers directory. Here is an example of loading that classifier and
171
+ running it on the sample CONLL data:
172
+
173
+ java -mx2g edu.stanford.nlp.ie.NERClassifierCombiner -loadClassifier \
174
+ classifiers/example.serialized.ncc.ncc.ser.gz -map word=0,answer=1 \
175
+ -testFile sample-conll-file.txt
176
+
177
+ For a more exhaustive description of NERClassifierCombiner go to
178
+ http://nlp.stanford.edu/software/ncc-faq.html
179
+
180
+ PROGRAMMATIC USE
181
+
182
+ The NERDemo file illustrates a couple of ways of calling the system
183
+ programatically. You should get the same results from
184
+
185
+ java -cp stanford-ner.jar:lib/*:. -mx300m NERDemo classifiers/english.all.3class.distsim.crf.ser.gz sample.txt
186
+
187
+ as from using CRFClassifier. For more information on API calls, look in
188
+ the enclosed javadoc directory: load index.html in a browser and look
189
+ first at the edu.stanford.nlp.ie.crf package and CRFClassifier class.
190
+ If you wish to train your own NER systems, look also at the
191
+ edu.stanford.nlp.ie package NERFeatureFactory class.
192
+
193
+
194
+ SERVER VERSION
195
+
196
+ The NER code may also be run as a server listening on a socket:
197
+
198
+ java -mx1000m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.NERServer 1234
199
+
200
+ You can specify which model to load with flags, either one on disk:
201
+
202
+ java -mx1000m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.NERServer -loadClassifier classifiers/all.3class.crf.ser.gz 1234
203
+
204
+ Or if you have put a model inside the jar file, as a resource under, say, models:
205
+
206
+ java -mx1000m -cp stanford-ner.jar:lib/* edu.stanford.nlp.ie.NERServer -loadClassifier models/all.3class.crf.ser.gz 1234
207
+
208
+
209
+ RUNNING CLASSIFIERS FROM INSIDE A JAR FILE
210
+
211
+ The software can run any serialized classifier from within a jar file by
212
+ following the -loadClassifier flag by some resource available within a
213
+ jar file on the CLASSPATH. An end user can make
214
+ their own jar files with the desired NER models contained inside.
215
+ This allows single jar file deployment.
216
+
217
+
218
+ PERFORMANCE GUIDELINES
219
+
220
+ Performance depends on many factors. Speed and memory use depend on
221
+ hardware, operating system, and JVM. Accuracy depends on the data
222
+ tested on. Nevertheless, in the belief that something is better than
223
+ nothing, here are some statistics from one machine on one test set, in
224
+ semi-realistic conditions (where the test data is somewhat varied).
225
+
226
+ ner-eng-ie.crf-3-all2006-distsim.ser.gz (older version of ner-eng-ie.crf-3-all2008-distsim.ser.gz)
227
+ Memory: 320MB (on a 32 bit machine)
228
+ PERSON ORGANIZATION LOCATION
229
+ 91.88 82.91 88.21
230
+
231
+
232
+ --------------------
233
+ CHANGES
234
+ --------------------
235
+
236
+ 2020-11-17 4.2.0 Update for compatibility
237
+
238
+ 2020-05-10 4.0.0 Update to UDv2.0 tokenization
239
+
240
+ 2018-10-16 3.9.2 Update for compatibility
241
+
242
+ 2018-02-27 3.9.1 KBP ner models for Chinese and Spanish
243
+
244
+ 2017-06-09 3.8.0 Updated for compatibility
245
+
246
+ 2016-10-31 3.7.0 Improved Chinese NER
247
+
248
+ 2015-12-09 3.6.0 Updated for compatibility
249
+
250
+ 2015-04-20 3.5.2 synch standalone and CoreNLP functionality
251
+
252
+ 2015-01-29 3.5.1 Substantial accuracy improvements
253
+
254
+ 2014-10-26 3.5.0 Upgrade to Java 1.8
255
+
256
+ 2014-08-27 3.4.1 Add Spanish models
257
+
258
+ 2014-06-16 3.4 Fix serialization bug
259
+
260
+ 2014-01-04 3.3.1 Bugfix release
261
+
262
+ 2013-11-12 3.3.0 Update for compatibility
263
+
264
+ 2013-11-12 3.3.0 Update for compatibility
265
+
266
+ 2013-06-19 3.2.0 Improve handling of line-by-line input
267
+
268
+ 2013-04-04 1.2.8 nthreads option
269
+
270
+ 2012-11-11 1.2.7 Improved English 3 class model by including
271
+ data from Wikipedia, release Chinese model
272
+
273
+ 2012-07-09 1.2.6 Minor bug fixes
274
+
275
+ 2012-05-22 1.2.5 Fix encoding issue
276
+
277
+ 2012-04-07 1.2.4 Caseless version of English models supported
278
+
279
+ 2012-01-06 1.2.3 Minor bug fixes
280
+
281
+ 2011-09-14 1.2.2 Improved thread safety
282
+
283
+ 2011-06-19 1.2.1 Models reduced in size but on average improved
284
+ in accuracy (improved distsim clusters)
285
+
286
+ 2011-05-16 1.2 Normal download includes 3, 4, and 7
287
+ class models. Updated for compatibility
288
+ with other software releases.
289
+
290
+ 2009-01-16 1.1.1 Minor bug and usability fixes, changed API
291
+
292
+ 2008-05-07 1.1 Additional feature flags, various code updates
293
+
294
+ 2006-09-18 1.0 Initial release
295
+
stanford_model/build.xml ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!-- build.xml file for ant for JavaNLP -->
2
+
3
+ <!-- Before using this, unjar the sources' jar file into the src/ directory! -->
4
+
5
+ <!-- A "project" describes a set of targets that may be requested
6
+ when Ant is executed. The "default" attribute defines the
7
+ target which is executed if no specific target is requested,
8
+ and the "basedir" attribute defines the current working directory
9
+ from which Ant executes the requested task. This is normally
10
+ set to the current working directory.
11
+ -->
12
+
13
+ <project name="JavaNLP" default="compile" basedir=".">
14
+
15
+ <property name="build.home" value="${basedir}/classes"/>
16
+ <property name="build.tests" value="${basedir}/classes"/>
17
+ <property name="docs.home" value="${basedir}/docs"/>
18
+ <property name="src.home" value="${basedir}/src"/>
19
+ <property name="javadoc.home" value="${basedir}/javadoc"/>
20
+
21
+
22
+ <!-- ==================== Compilation Control Options ==================== -->
23
+
24
+ <!--
25
+
26
+ These properties control option settings on the Javac compiler when it
27
+ is invoked using the <javac> task.
28
+
29
+ compile.debug Should compilation include the debug option?
30
+
31
+ compile.deprecation Should compilation include the deprecation option?
32
+
33
+ compile.optimize Should compilation include the optimize option?
34
+
35
+ compile.source Source version compatibility
36
+
37
+ compile.target Target class version compatibility
38
+
39
+ -->
40
+
41
+ <property name="compile.debug" value="true"/>
42
+ <property name="compile.deprecation" value="false"/>
43
+ <property name="compile.optimize" value="true"/>
44
+ <property name="compile.source" value="1.8" />
45
+ <property name="compile.target" value="1.8" />
46
+ <property name="compile.encoding" value="utf-8" />
47
+
48
+
49
+
50
+
51
+ <!-- ==================== All Target ====================================== -->
52
+
53
+ <!--
54
+
55
+ The "all" target is a shortcut for running the "clean" target followed
56
+ by the "compile" target, to force a complete recompile.
57
+
58
+ -->
59
+
60
+ <target name="all" depends="clean,compile"
61
+ description="Clean build and dist directories, then compile"/>
62
+
63
+
64
+
65
+ <!-- ==================== Clean Target ==================================== -->
66
+
67
+ <!--
68
+
69
+ The "clean" target deletes any previous "build" and "dist" directory,
70
+ so that you can be ensured the application can be built from scratch.
71
+
72
+ -->
73
+
74
+ <target name="clean" description="Delete old classes">
75
+ <delete dir="${build.home}/edu"/>
76
+ </target>
77
+
78
+
79
+
80
+ <!-- ==================== Compile Target ================================== -->
81
+
82
+ <!--
83
+
84
+ The "compile" target transforms source files (from your "src" directory)
85
+ into object files in the appropriate location in the build directory.
86
+ This example assumes that you will be including your classes in an
87
+ unpacked directory hierarchy under "/WEB-INF/classes".
88
+
89
+ -->
90
+
91
+ <target name="compile" depends="prepare"
92
+ description="Compile Java sources">
93
+
94
+ <!-- Compile Java classes as necessary -->
95
+ <mkdir dir="${build.home}"/>
96
+ <javac srcdir="${src.home}"
97
+ destdir="${build.home}"
98
+ debug="${compile.debug}"
99
+ encoding="${compile.encoding}"
100
+ deprecation="${compile.deprecation}"
101
+ optimize="${compile.optimize}"
102
+ source="${compile.source}"
103
+ target="${compile.target}"
104
+ includeantruntime="false">
105
+ <compilerarg value="-Xmaxerrs"/>
106
+ <compilerarg value="20"/>
107
+ <classpath>
108
+ <fileset dir="${basedir}/lib">
109
+ <include name="*.jar"/>
110
+ <exclude name="javanlp*"/>
111
+ </fileset>
112
+ </classpath>
113
+ <!-- <compilerarg value="-Xlint"/> -->
114
+ </javac>
115
+
116
+ <!-- Copy application resources -->
117
+ <!--
118
+ <copy todir="${build.home}/WEB-INF/classes">
119
+ <fileset dir="${src.home}" excludes="**/*.java"/>
120
+ </copy>
121
+ -->
122
+
123
+ </target>
124
+
125
+
126
+ <!-- ==================== Javadoc Target ================================== -->
127
+
128
+ <!--
129
+
130
+ The "javadoc" target creates Javadoc API documentation for the Java
131
+ classes included in your application. Normally, this is only required
132
+ when preparing a distribution release, but is available as a separate
133
+ target in case the developer wants to create Javadocs independently.
134
+
135
+ -->
136
+
137
+ <target name="javadoc" depends="compile"
138
+ description="Create Javadoc API documentation">
139
+
140
+ <mkdir dir="${javadoc.home}"/>
141
+ <javadoc sourcepath="${src.home}"
142
+ destdir="${javadoc.home}"
143
+ maxmemory="1g"
144
+ author="true"
145
+ source="${compile.source}"
146
+ overview="${src.home}/edu/stanford/nlp/overview.html"
147
+ doctitle="Stanford JavaNLP API Documentation"
148
+ windowtitle="Stanford JavaNLP API"
149
+ encoding="${compile.encoding}"
150
+ docencoding="${compile.encoding}"
151
+ charset="${compile.encoding}"
152
+ packagenames="*">
153
+ <!-- Allow @generated, @modifiable and @ordered tags -->
154
+ <tag name="generated" scope="all" description="Generated" />
155
+ <tag name="modifiable" scope="all" description="Modifiable" />
156
+ <tag name="ordered" scope="all" description="Ordered" />
157
+ <!-- Depends on lib and classes folders -->
158
+ <classpath>
159
+ <fileset dir="${basedir}/lib">
160
+ <include name="*.jar"/>
161
+ <exclude name="javanlp*"/>
162
+ </fileset>
163
+ <pathelement path="${build.home}" />
164
+ </classpath>
165
+ <bottom><![CDATA[<font size="2"><a href="https://nlp.stanford.edu" target="_top">Stanford NLP Group</a></font>]]></bottom>
166
+ <link href="https://docs.oracle.com/javase/8/docs/api/"/>
167
+ </javadoc>
168
+
169
+ </target>
170
+
171
+
172
+ <!-- ==================== Prepare Target ================================== -->
173
+
174
+ <!--
175
+
176
+ The "prepare" target is used to create the "build" destination directory,
177
+ and copy the static contents of your web application to it. If you need
178
+ to copy static files from external dependencies, you can customize the
179
+ contents of this task.
180
+
181
+ Normally, this task is executed indirectly when needed.
182
+
183
+ -->
184
+
185
+ <target name="prepare">
186
+
187
+ <!-- Create build directories as needed -->
188
+ <mkdir dir="${build.home}"/>
189
+
190
+ </target>
191
+
192
+ </project>
stanford_model/ner-gui.bat ADDED
@@ -0,0 +1 @@
 
 
1
+ java -mx1500m -cp "stanford-ner.jar;lib/*" edu.stanford.nlp.ie.crf.NERGUI
stanford_model/ner-gui.command ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ #!/bin/sh
2
+ java -mx500m -cp `dirname $0`/stanford-ner.jar:`dirname $0`/lib/* edu.stanford.nlp.ie.crf.NERGUI
stanford_model/ner-gui.sh ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ #!/bin/sh
2
+ scriptdir=`dirname $0`
3
+
4
+ java -mx700m -cp "$scriptdir/stanford-ner.jar:lib/*" edu.stanford.nlp.ie.crf.NERGUI
stanford_model/ner.bat ADDED
@@ -0,0 +1 @@
 
 
1
+ java -mx1000m -cp stanford-ner.jar;lib/* edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier classifiers\english.all.3class.distsim.crf.ser.gz -textFile %1
stanford_model/ner.sh ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ #!/bin/sh
2
+ scriptdir=`dirname $0`
3
+
4
+ java -mx700m -cp "$scriptdir/stanford-ner.jar:$scriptdir/lib/*" edu.stanford.nlp.ie.crf.CRFClassifier -loadClassifier $scriptdir/classifiers/english.all.3class.distsim.crf.ser.gz -textFile $1
stanford_model/sample-conll-file.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ John PERSON
2
+ Kerry PERSON
3
+ will O
4
+ fly O
5
+ to O
6
+ Paris LOCATION
7
+ this O
8
+ weekend O
9
+ . O
stanford_model/sample-w-time.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Barack Obama was born on August 4, 1961 in Honolulu, Hawaii which was 4 days
2
+ ago.
stanford_model/sample.ner.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ The/O fate/O of/O Lehman/ORGANIZATION Brothers/ORGANIZATION ,/O the/O beleaguered/O investment/O bank/O ,/O hung/O in/O the/O balance/O on/O Sunday/O as/O Federal/ORGANIZATION Reserve/ORGANIZATION officials/O and/O the/O leaders/O of/O major/O financial/O institutions/O continued/O to/O gather/O in/O emergency/O meetings/O trying/O to/O complete/O a/O plan/O to/O rescue/O the/O stricken/O bank/O ./O
2
+ Several/O possible/O plans/O emerged/O from/O the/O talks/O ,/O held/O at/O the/O Federal/ORGANIZATION Reserve/ORGANIZATION Bank/ORGANIZATION of/ORGANIZATION New/ORGANIZATION York/ORGANIZATION and/O led/O by/O Timothy/PERSON R./PERSON Geithner/PERSON ,/O the/O president/O of/O the/O New/ORGANIZATION York/ORGANIZATION Fed/ORGANIZATION ,/O and/O Treasury/ORGANIZATION Secretary/O Henry/PERSON M./PERSON Paulson/PERSON Jr./PERSON ./O
stanford_model/sample.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ The fate of Lehman Brothers, the beleaguered investment bank, hung in the balance on Sunday as Federal Reserve officials and the leaders of major financial institutions continued to gather in emergency meetings trying to complete a plan to rescue the stricken bank. Several possible plans emerged from the talks, held at the Federal Reserve Bank of New York and led by Timothy R. Geithner, the president of the New York Fed, and Treasury Secretary Henry M. Paulson Jr.
stanford_model/stanford-ner-4.2.0-javadoc.jar ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2400a6d94ec30c8aec36003e5a4d35d7f95651955220d608841566b123491bbf
3
+ size 5887473
stanford_model/stanford-ner-4.2.0-sources.jar ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67107462c51833c3073784e70d504fd1b5f5153c81eddc60ec106ae872d95b6c
3
+ size 3489930
stanford_model/stanford-ner-4.2.0.jar ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2478a64f37750c52c5aca933b4e29fa399b464ab80817946fa8f4f30c92ea60
3
+ size 4661456
stanford_model/stanford-ner.jar ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2478a64f37750c52c5aca933b4e29fa399b464ab80817946fa8f4f30c92ea60
3
+ size 4661456