sgd-1.3/ 0000755 0000765 0000765 00000000000 11141047026 012360 5 ustar leonb leonb 0000000 0000000 sgd-1.3/COPYING 0000644 0000765 0000765 00000016727 10700526244 013434 0 ustar leonb leonb 0000000 0000000 GNU LESSER GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc.
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
This version of the GNU Lesser General Public License incorporates
the terms and conditions of version 3 of the GNU General Public
License, supplemented by the additional permissions listed below.
0. Additional Definitions.
As used herein, "this License" refers to version 3 of the GNU Lesser
General Public License, and the "GNU GPL" refers to version 3 of the GNU
General Public License.
"The Library" refers to a covered work governed by this License,
other than an Application or a Combined Work as defined below.
An "Application" is any work that makes use of an interface provided
by the Library, but which is not otherwise based on the Library.
Defining a subclass of a class defined by the Library is deemed a mode
of using an interface provided by the Library.
A "Combined Work" is a work produced by combining or linking an
Application with the Library. The particular version of the Library
with which the Combined Work was made is also called the "Linked
Version".
The "Minimal Corresponding Source" for a Combined Work means the
Corresponding Source for the Combined Work, excluding any source code
for portions of the Combined Work that, considered in isolation, are
based on the Application, and not on the Linked Version.
The "Corresponding Application Code" for a Combined Work means the
object code and/or source code for the Application, including any data
and utility programs needed for reproducing the Combined Work from the
Application, but excluding the System Libraries of the Combined Work.
1. Exception to Section 3 of the GNU GPL.
You may convey a covered work under sections 3 and 4 of this License
without being bound by section 3 of the GNU GPL.
2. Conveying Modified Versions.
If you modify a copy of the Library, and, in your modifications, a
facility refers to a function or data to be supplied by an Application
that uses the facility (other than as an argument passed when the
facility is invoked), then you may convey a copy of the modified
version:
a) under this License, provided that you make a good faith effort to
ensure that, in the event an Application does not supply the
function or data, the facility still operates, and performs
whatever part of its purpose remains meaningful, or
b) under the GNU GPL, with none of the additional permissions of
this License applicable to that copy.
3. Object Code Incorporating Material from Library Header Files.
The object code form of an Application may incorporate material from
a header file that is part of the Library. You may convey such object
code under terms of your choice, provided that, if the incorporated
material is not limited to numerical parameters, data structure
layouts and accessors, or small macros, inline functions and templates
(ten or fewer lines in length), you do both of the following:
a) Give prominent notice with each copy of the object code that the
Library is used in it and that the Library and its use are
covered by this License.
b) Accompany the object code with a copy of the GNU GPL and this license
document.
4. Combined Works.
You may convey a Combined Work under terms of your choice that,
taken together, effectively do not restrict modification of the
portions of the Library contained in the Combined Work and reverse
engineering for debugging such modifications, if you also do each of
the following:
a) Give prominent notice with each copy of the Combined Work that
the Library is used in it and that the Library and its use are
covered by this License.
b) Accompany the Combined Work with a copy of the GNU GPL and this license
document.
c) For a Combined Work that displays copyright notices during
execution, include the copyright notice for the Library among
these notices, as well as a reference directing the user to the
copies of the GNU GPL and this license document.
d) Do one of the following:
0) Convey the Minimal Corresponding Source under the terms of this
License, and the Corresponding Application Code in a form
suitable for, and under terms that permit, the user to
recombine or relink the Application with a modified version of
the Linked Version to produce a modified Combined Work, in the
manner specified by section 6 of the GNU GPL for conveying
Corresponding Source.
1) Use a suitable shared library mechanism for linking with the
Library. A suitable mechanism is one that (a) uses at run time
a copy of the Library already present on the user's computer
system, and (b) will operate properly with a modified version
of the Library that is interface-compatible with the Linked
Version.
e) Provide Installation Information, but only if you would otherwise
be required to provide such information under section 6 of the
GNU GPL, and only to the extent that such information is
necessary to install and execute a modified version of the
Combined Work produced by recombining or relinking the
Application with a modified version of the Linked Version. (If
you use option 4d0, the Installation Information must accompany
the Minimal Corresponding Source and Corresponding Application
Code. If you use option 4d1, you must provide the Installation
Information in the manner specified by section 6 of the GNU GPL
for conveying Corresponding Source.)
5. Combined Libraries.
You may place library facilities that are a work based on the
Library side by side in a single library together with other library
facilities that are not Applications and are not covered by this
License, and convey such a combined library under terms of your
choice, if you do both of the following:
a) Accompany the combined library with a copy of the same work based
on the Library, uncombined with any other library facilities,
conveyed under the terms of this License.
b) Give prominent notice with the combined library that part of it
is a work based on the Library, and explaining where to find the
accompanying uncombined form of the same work.
6. Revised Versions of the GNU Lesser General Public License.
The Free Software Foundation may publish revised and/or new versions
of the GNU Lesser General Public License from time to time. Such new
versions will be similar in spirit to the present version, but may
differ in detail to address new problems or concerns.
Each version is given a distinguishing version number. If the
Library as you received it specifies that a certain numbered version
of the GNU Lesser General Public License "or any later version"
applies to it, you have the option of following the terms and
conditions either of that published version or of any later version
published by the Free Software Foundation. If the Library as you
received it does not specify a version number of the GNU Lesser
General Public License, you may choose any version of the GNU Lesser
General Public License ever published by the Free Software Foundation.
If the Library as you received it specifies that a proxy can decide
whether future versions of the GNU Lesser General Public License shall
apply, that proxy's public statement of acceptance of any version is
permanent authorization for you to choose that version for the
Library.
sgd-1.3/crf/ 0000755 0000765 0000765 00000000000 11141047026 013132 5 ustar leonb leonb 0000000 0000000 sgd-1.3/crf/conlleval 0000755 0000765 0000765 00000031175 10656702702 015057 0 ustar leonb leonb 0000000 0000000 #!/usr/bin/perl -w
# conlleval: evaluate result of processing CoNLL-2000 shared task
# usage: conlleval [-l] [-r] [-d delimiterTag] [-o oTag] < file
# README: http://cnts.uia.ac.be/conll2000/chunking/output.html
# options: l: generate LaTeX output for tables like in
# http://cnts.uia.ac.be/conll2003/ner/example.tex
# r: accept raw result tags (without B- and I- prefix;
# assumes one word per chunk)
# d: alternative delimiter tag (default is single space)
# o: alternative outside tag (default is O)
# note: the file should contain lines with items separated
# by $delimiter characters (default space). The final
# two items should contain the correct tag and the
# guessed tag in that order. Sentences should be
# separated from each other by empty lines or lines
# with $boundary fields (default -X-).
# url: http://lcg-www.uia.ac.be/conll2000/chunking/
# started: 1998-09-25
# version: 2004-01-26
# author: Erik Tjong Kim Sang
use strict;
my $false = 0;
my $true = 42;
my $boundary = "-X-"; # sentence boundary
my $correct; # current corpus chunk tag (I,O,B)
my $correctChunk = 0; # number of correctly identified chunks
my $correctTags = 0; # number of correct chunk tags
my $correctType; # type of current corpus chunk tag (NP,VP,etc.)
my $delimiter = " "; # field delimiter
my $FB1 = 0.0; # FB1 score (Van Rijsbergen 1979)
my $firstItem; # first feature (for sentence boundary checks)
my $foundCorrect = 0; # number of chunks in corpus
my $foundGuessed = 0; # number of identified chunks
my $guessed; # current guessed chunk tag
my $guessedType; # type of current guessed chunk tag
my $i; # miscellaneous counter
my $inCorrect = $false; # currently processed chunk is correct until now
my $lastCorrect = "O"; # previous chunk tag in corpus
my $latex = 0; # generate LaTeX formatted output
my $lastCorrectType = ""; # type of previously identified chunk tag
my $lastGuessed = "O"; # previously identified chunk tag
my $lastGuessedType = ""; # type of previous chunk tag in corpus
my $lastType; # temporary storage for detecting duplicates
my $line; # line
my $nbrOfFeatures = -1; # number of features per line
my $precision = 0.0; # precision score
my $oTag = "O"; # outside tag, default O
my $raw = 0; # raw input: add B to every token
my $quiet = 0; # only display summary line
my $recall = 0.0; # recall score
my $tokenCounter = 0; # token counter (ignores sentence breaks)
my %correctChunk = (); # number of correctly identified chunks per type
my %foundCorrect = (); # number of chunks in corpus per type
my %foundGuessed = (); # number of identified chunks per type
my @features; # features on line
my @sortedTypes; # sorted list of chunk type names
# sanity check
while (@ARGV and $ARGV[0] =~ /^-/) {
if ($ARGV[0] eq "-l") { $latex = 1; shift(@ARGV); }
elsif ($ARGV[0] eq "-r") { $raw = 1; shift(@ARGV); }
elsif ($ARGV[0] eq "-q") { $quiet = 1; shift(@ARGV); }
elsif ($ARGV[0] eq "-d") {
shift(@ARGV);
if (not defined $ARGV[0]) {
die "conlleval: -d requires delimiter character";
}
$delimiter = shift(@ARGV);
} elsif ($ARGV[0] eq "-o") {
shift(@ARGV);
if (not defined $ARGV[0]) {
die "conlleval: -o requires delimiter character";
}
$oTag = shift(@ARGV);
} else { die "conlleval: unknown argument $ARGV[0]\n"; }
}
if (@ARGV) { die "conlleval: unexpected command line argument\n"; }
# process input
while () {
chomp($line = $_);
@features = split(/$delimiter/,$line);
if ($nbrOfFeatures < 0) { $nbrOfFeatures = $#features; }
elsif ($nbrOfFeatures != $#features and @features != 0) {
printf STDERR "unexpected number of features: %d (%d)\n",
$#features+1,$nbrOfFeatures+1;
exit(1);
}
if (@features == 0 or
$features[0] eq $boundary) { @features = ($boundary,"O","O"); }
if (@features < 2) {
die "conlleval: unexpected number of features in line $line\n";
}
if ($raw) {
if ($features[$#features] eq $oTag) { $features[$#features] = "O"; }
if ($features[$#features-1] eq $oTag) { $features[$#features-1] = "O"; }
if ($features[$#features] ne "O") {
$features[$#features] = "B-$features[$#features]";
}
if ($features[$#features-1] ne "O") {
$features[$#features-1] = "B-$features[$#features-1]";
}
}
# 20040126 ET code which allows hyphens in the types
if ($features[$#features] =~ /^([^-]*)-(.*)$/) {
$guessed = $1;
$guessedType = $2;
} else {
$guessed = $features[$#features];
$guessedType = "";
}
pop(@features);
if ($features[$#features] =~ /^([^-]*)-(.*)$/) {
$correct = $1;
$correctType = $2;
} else {
$correct = $features[$#features];
$correctType = "";
}
pop(@features);
# ($guessed,$guessedType) = split(/-/,pop(@features));
# ($correct,$correctType) = split(/-/,pop(@features));
$guessedType = $guessedType ? $guessedType : "";
$correctType = $correctType ? $correctType : "";
$firstItem = shift(@features);
# 1999-06-26 sentence breaks should always be counted as out of chunk
if ( $firstItem eq $boundary ) { $guessed = "O"; }
if ($inCorrect) {
if ( &endOfChunk($lastCorrect,$correct,$lastCorrectType,$correctType) and
&endOfChunk($lastGuessed,$guessed,$lastGuessedType,$guessedType) and
$lastGuessedType eq $lastCorrectType) {
$inCorrect=$false;
$correctChunk++;
$correctChunk{$lastCorrectType} = $correctChunk{$lastCorrectType} ?
$correctChunk{$lastCorrectType}+1 : 1;
} elsif (
&endOfChunk($lastCorrect,$correct,$lastCorrectType,$correctType) !=
&endOfChunk($lastGuessed,$guessed,$lastGuessedType,$guessedType) or
$guessedType ne $correctType ) {
$inCorrect=$false;
}
}
if ( &startOfChunk($lastCorrect,$correct,$lastCorrectType,$correctType) and
&startOfChunk($lastGuessed,$guessed,$lastGuessedType,$guessedType) and
$guessedType eq $correctType) { $inCorrect = $true; }
if ( &startOfChunk($lastCorrect,$correct,$lastCorrectType,$correctType) ) {
$foundCorrect++;
$foundCorrect{$correctType} = $foundCorrect{$correctType} ?
$foundCorrect{$correctType}+1 : 1;
}
if ( &startOfChunk($lastGuessed,$guessed,$lastGuessedType,$guessedType) ) {
$foundGuessed++;
$foundGuessed{$guessedType} = $foundGuessed{$guessedType} ?
$foundGuessed{$guessedType}+1 : 1;
}
if ( $firstItem ne $boundary ) {
if ( $correct eq $guessed and $guessedType eq $correctType ) {
$correctTags++;
}
$tokenCounter++;
}
$lastGuessed = $guessed;
$lastCorrect = $correct;
$lastGuessedType = $guessedType;
$lastCorrectType = $correctType;
}
if ($inCorrect) {
$correctChunk++;
$correctChunk{$lastCorrectType} = $correctChunk{$lastCorrectType} ?
$correctChunk{$lastCorrectType}+1 : 1;
}
if (not $latex) {
# compute overall precision, recall and FB1 (default values are 0.0)
$precision = 100*$correctChunk/$foundGuessed if ($foundGuessed > 0);
$recall = 100*$correctChunk/$foundCorrect if ($foundCorrect > 0);
$FB1 = 2*$precision*$recall/($precision+$recall)
if ($precision+$recall > 0);
# print overall performance
if (not $quiet) {
printf "processed $tokenCounter tokens with $foundCorrect phrases; ";
printf "found: $foundGuessed phrases; correct: $correctChunk.\n";
}
if ($tokenCounter>0) {
printf "accuracy: %6.2f%%; ",100*$correctTags/$tokenCounter;
printf "precision: %6.2f%%; ",$precision;
printf "recall: %6.2f%%; ",$recall;
printf "FB1: %6.2f\n",$FB1;
}
}
# sort chunk type names
undef($lastType);
@sortedTypes = ();
foreach $i (sort (keys %foundCorrect,keys %foundGuessed)) {
if (not($lastType) or $lastType ne $i) {
push(@sortedTypes,($i));
}
$lastType = $i;
}
# print performance per chunk type
if (not $latex) {
if (not $quiet) {
for $i (@sortedTypes) {
$correctChunk{$i} = $correctChunk{$i} ? $correctChunk{$i} : 0;
if (not($foundGuessed{$i})) { $foundGuessed{$i} = 0; $precision = 0.0; }
else { $precision = 100*$correctChunk{$i}/$foundGuessed{$i}; }
if (not($foundCorrect{$i})) { $recall = 0.0; }
else { $recall = 100*$correctChunk{$i}/$foundCorrect{$i}; }
if ($precision+$recall == 0.0) { $FB1 = 0.0; }
else { $FB1 = 2*$precision*$recall/($precision+$recall); }
printf "%17s: ",$i;
printf "precision: %6.2f%%; ",$precision;
printf "recall: %6.2f%%; ",$recall;
printf "FB1: %6.2f %d\n",$FB1,$foundGuessed{$i};
}
}
} else {
print " & Precision & Recall & F\$_{\\beta=1} \\\\\\hline";
if (not $quiet) {
for $i (@sortedTypes) {
$correctChunk{$i} = $correctChunk{$i} ? $correctChunk{$i} : 0;
if (not($foundGuessed{$i})) { $precision = 0.0; }
else { $precision = 100*$correctChunk{$i}/$foundGuessed{$i}; }
if (not($foundCorrect{$i})) { $recall = 0.0; }
else { $recall = 100*$correctChunk{$i}/$foundCorrect{$i}; }
if ($precision+$recall == 0.0) { $FB1 = 0.0; }
else { $FB1 = 2*$precision*$recall/($precision+$recall); }
printf "\n%-7s & %6.2f\\%% & %6.2f\\%% & %6.2f \\\\",
$i,$precision,$recall,$FB1;
}
print "\\hline\n";
}
$precision = 0.0;
$recall = 0;
$FB1 = 0.0;
$precision = 100*$correctChunk/$foundGuessed if ($foundGuessed > 0);
$recall = 100*$correctChunk/$foundCorrect if ($foundCorrect > 0);
$FB1 = 2*$precision*$recall/($precision+$recall)
if ($precision+$recall > 0);
printf "Overall & %6.2f\\%% & %6.2f\\%% & %6.2f \\\\\\hline\n",
$precision,$recall,$FB1;
}
exit 0;
# endOfChunk: checks if a chunk ended between the previous and current word
# arguments: previous and current chunk tags, previous and current types
# note: this code is capable of handling other chunk representations
# than the default CoNLL-2000 ones, see EACL'99 paper of Tjong
# Kim Sang and Veenstra http://xxx.lanl.gov/abs/cs.CL/9907006
sub endOfChunk {
my $prevTag = shift(@_);
my $tag = shift(@_);
my $prevType = shift(@_);
my $type = shift(@_);
my $chunkEnd = $false;
if ( $prevTag eq "B" and $tag eq "B" ) { $chunkEnd = $true; }
if ( $prevTag eq "B" and $tag eq "O" ) { $chunkEnd = $true; }
if ( $prevTag eq "I" and $tag eq "B" ) { $chunkEnd = $true; }
if ( $prevTag eq "I" and $tag eq "O" ) { $chunkEnd = $true; }
if ( $prevTag eq "E" and $tag eq "E" ) { $chunkEnd = $true; }
if ( $prevTag eq "E" and $tag eq "I" ) { $chunkEnd = $true; }
if ( $prevTag eq "E" and $tag eq "O" ) { $chunkEnd = $true; }
if ( $prevTag eq "I" and $tag eq "O" ) { $chunkEnd = $true; }
if ($prevTag ne "O" and $prevTag ne "." and $prevType ne $type) {
$chunkEnd = $true;
}
# corrected 1998-12-22: these chunks are assumed to have length 1
if ( $prevTag eq "]" ) { $chunkEnd = $true; }
if ( $prevTag eq "[" ) { $chunkEnd = $true; }
return($chunkEnd);
}
# startOfChunk: checks if a chunk started between the previous and current word
# arguments: previous and current chunk tags, previous and current types
# note: this code is capable of handling other chunk representations
# than the default CoNLL-2000 ones, see EACL'99 paper of Tjong
# Kim Sang and Veenstra http://xxx.lanl.gov/abs/cs.CL/9907006
sub startOfChunk {
my $prevTag = shift(@_);
my $tag = shift(@_);
my $prevType = shift(@_);
my $type = shift(@_);
my $chunkStart = $false;
if ( $prevTag eq "B" and $tag eq "B" ) { $chunkStart = $true; }
if ( $prevTag eq "I" and $tag eq "B" ) { $chunkStart = $true; }
if ( $prevTag eq "O" and $tag eq "B" ) { $chunkStart = $true; }
if ( $prevTag eq "O" and $tag eq "I" ) { $chunkStart = $true; }
if ( $prevTag eq "E" and $tag eq "E" ) { $chunkStart = $true; }
if ( $prevTag eq "E" and $tag eq "I" ) { $chunkStart = $true; }
if ( $prevTag eq "O" and $tag eq "E" ) { $chunkStart = $true; }
if ( $prevTag eq "O" and $tag eq "I" ) { $chunkStart = $true; }
if ($tag ne "O" and $tag ne "." and $prevType ne $type) {
$chunkStart = $true;
}
# corrected 1998-12-22: these chunks are assumed to have length 1
if ( $tag eq "[" ) { $chunkStart = $true; }
if ( $tag eq "]" ) { $chunkStart = $true; }
return($chunkStart);
}
sgd-1.3/crf/crfsgd.cpp 0000644 0000765 0000765 00000125176 10726274466 015144 0 ustar leonb leonb 0000000 0000000 // -*- C++ -*-
// CRF with stochastic gradient
// Copyright (C) 2007- Leon Bottou
// This program 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 program 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 General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with this program; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, USA
// $Id: crfsgd.cpp,v 1.35 2007/12/07 16:47:50 cvs Exp $
#include "wrapper.h"
#include "vectors.h"
#include "matrices.h"
#include "gzstream.h"
#include "pstream.h"
#include "timer.h"
#include
#include
#include
#include