biblicit 2.0.5 → 2.0.6
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +1 -0
- data/lib/biblicit/version.rb +1 -1
- data/parscit/INSTALL +29 -7
- data/parscit/bin/parsHed/redo.parsHed.pl +3 -2
- data/parscit/bin/redo.parsCit.pl +3 -2
- data/parscit/bin/sectLabel/genericSect/crossValidation.rb +1 -1
- data/parscit/bin/sectLabel/genericSectExtract.rb +1 -1
- data/parscit/bin/sectLabel/redo.sectLabel.pl +3 -2
- data/parscit/doc/index.html +692 -0
- data/parscit/lib/ParsCit/Config.pm +1 -1
- data/parscit/lib/ParsCit/Tr2crfpp.pm +1 -1
- data/parscit/lib/ParsHed/Config.pm +1 -1
- data/parscit/lib/ParsHed/Tr2crfpp.pm +1 -1
- data/parscit/lib/ParsHed/Tr2crfpp_token.pm +1 -1
- data/parscit/lib/SectLabel/AAMatching.pm +1949 -0
- data/parscit/lib/SectLabel/Config.pm +1 -1
- data/parscit/lib/SectLabel/Tr2crfpp.pm +2 -2
- metadata +5 -8
data/.gitignore
CHANGED
data/lib/biblicit/version.rb
CHANGED
data/parscit/INSTALL
CHANGED
@@ -40,12 +40,24 @@ These are the two scripts: citeExtract.pl and parseRefStrings.pl. The
|
|
40
40
|
second script is a subset of the first, and should be your first
|
41
41
|
target to get running.
|
42
42
|
|
43
|
-
1) You will first need to
|
44
|
-
place the binaries at crfpp/. We are using CRF++ version 0.51. To do
|
45
|
-
this follow these instructions in the crfpp directory. CRF++ is the
|
43
|
+
1) You will first need to install CRF++. CRF++ is the
|
46
44
|
core conditional random field learner, that is re-distributed in this
|
47
|
-
ParsCit software.
|
48
|
-
|
45
|
+
ParsCit software. It is due to Taku Kudo. We are using CRF++ version 0.51.
|
46
|
+
|
47
|
+
You have two options:
|
48
|
+
a) You may install CRF++ anywhere, and set the environment variable
|
49
|
+
CRFPP_HOME to tell ParsCit where to find it. CRFPP_HOME should be set
|
50
|
+
such that "$CRFPP_HOME/bin" contains the binaries crf_test and crf_learn.
|
51
|
+
For example if you run a default "make install" on Linux and those
|
52
|
+
binaries are installed to "/usr/local/bin", CRFPP_HOME should be
|
53
|
+
"/usr/local".
|
54
|
+
|
55
|
+
b) You may place the binaries in the crfpp/ directory within the ParsCit
|
56
|
+
source. You do not then need to set any environment variables, although
|
57
|
+
you may need to edit Config.pm files.
|
58
|
+
|
59
|
+
Installation methods:
|
60
|
+
a) From source, in the crfpp directory:
|
49
61
|
$ cd crfpp
|
50
62
|
# we're going to rebuild CRF 51
|
51
63
|
$ rm -Rf CRF++-0.51
|
@@ -71,9 +83,19 @@ ParsCit software. It is due to Taku Kudo.
|
|
71
83
|
$ cd .libs
|
72
84
|
$ cp -Rf * ../../.libs
|
73
85
|
|
74
|
-
|
86
|
+
b) With apt, on a Debian-based Linux distribution:
|
87
|
+
sudo apt-add-repository 'deb http://cl.naist.jp/~eric-n/ubuntu-nlp oneiric all'
|
88
|
+
sudo apt-get update
|
89
|
+
sudo apt-get install libcrf++-dev crf++
|
90
|
+
|
91
|
+
c) With Homebrew, on OS X:
|
92
|
+
brew install crf++
|
93
|
+
|
94
|
+
2) Once the binaries are placed properly, if you are not using the
|
95
|
+
CRFPP_HOME environment variable, you may need to edit the
|
75
96
|
lib/ParsCit/Config.pm file to point to the proper directories on your
|
76
|
-
machine.
|
97
|
+
machine. If you are using CRFPP_HOME, you may want to set it in
|
98
|
+
your .bashrc or .profile file.
|
77
99
|
|
78
100
|
3) Edit the shebang lines (first line) of the scripts in the bin/
|
79
101
|
directory to point to the proper versions of perl
|
@@ -18,8 +18,9 @@ my $parscitHome = "$FindBin::Bin/../..";
|
|
18
18
|
my $tr2crfppLoc = "$parscitHome/bin/parsHed/tr2crfpp_parsHed.pl";
|
19
19
|
my $convertLoc = "$parscitHome/bin/parsHed/convert2TokenLevel.pl"; #new model
|
20
20
|
my $keywordLoc = "$parscitHome/bin/parsHed/keywordGen.pl"; #new model
|
21
|
-
my $
|
22
|
-
my $
|
21
|
+
my $crfpp = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin" : "$parscitHome/crfpp";
|
22
|
+
my $crf_learnLoc = "$crfpp/crf_learn";
|
23
|
+
my $crf_testLoc = "$crfpp/crf_test";
|
23
24
|
my $conllevalLoc = "$parscitHome/bin/conlleval.pl";
|
24
25
|
### END user customizable section
|
25
26
|
|
data/parscit/bin/redo.parsCit.pl
CHANGED
@@ -10,8 +10,9 @@ $0 =~ /([^\/]+)$/; my $progname = $1;
|
|
10
10
|
my $outputVersion = "1.0";
|
11
11
|
my $parscitHome = "/home/wing.nus/services/parscit/tools/";
|
12
12
|
my $tr2crfppLoc = "$parscitHome/bin/tr2crfpp.pl";
|
13
|
-
my $
|
14
|
-
my $
|
13
|
+
my $crfpp = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin" : "$parscitHome/crfpp";
|
14
|
+
my $crf_learnLoc = "$crfpp/crf_learn";
|
15
|
+
my $crf_testLoc = "$crfpp/crf_test";
|
15
16
|
my $conllevalLoc = "$parscitHome/bin/conlleval.pl";
|
16
17
|
my $crfTemplateLoc = "$parscitHome/crfpp/traindata/parsCit.template";
|
17
18
|
### END user customizable section
|
@@ -4,7 +4,7 @@ require 'find'
|
|
4
4
|
|
5
5
|
pwd = File.dirname(__FILE__)
|
6
6
|
|
7
|
-
@CRFPP = "#{ENV['CRFPP_HOME']}/bin"
|
7
|
+
@CRFPP = ENV['CRFPP_HOME'] ? "#{ENV['CRFPP_HOME']}/bin" : "#{pwd}/../../../crfpp"
|
8
8
|
@RESOURCES = "#{pwd}/../../../crfpp/traindata/"
|
9
9
|
@TEST_DIR = "#{pwd}/run"
|
10
10
|
@CONLLEVAL = "#{pwd}/../../conlleval.pl"
|
@@ -5,7 +5,7 @@ require 'find'
|
|
5
5
|
|
6
6
|
pwd = File.dirname(__FILE__)
|
7
7
|
|
8
|
-
@CRFPP = "#{ENV['CRFPP_HOME']}/bin"
|
8
|
+
@CRFPP = ENV['CRFPP_HOME'] ? "#{ENV['CRFPP_HOME']}/bin" : "#{pwd}/../../crfpp"
|
9
9
|
@SRC = "#{pwd}/genericSect"
|
10
10
|
@DATA = "#{pwd}/../../resources/sectLabel/"
|
11
11
|
@TEST_DIR = "/tmp/"
|
@@ -27,8 +27,9 @@ my $outputVersion = "1.0";
|
|
27
27
|
|
28
28
|
my $tr2crfppLoc = "$path/tr2crfpp.pl";
|
29
29
|
my $keywordLoc = "$path/keywordGen.pl"; #new model
|
30
|
-
my $
|
31
|
-
my $
|
30
|
+
my $crfpp = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin" : "$path/../../crfpp";
|
31
|
+
my $crf_learnLoc = "$crfpp/crf_learn";
|
32
|
+
my $crf_testLoc = "$crfpp/crf_test";
|
32
33
|
my $conllevalLoc = "$path/../conlleval.pl";
|
33
34
|
### END user customizable section
|
34
35
|
|