CRF++结果评估：准确率与F1值计算方法

#!/usr/bin/perl -w
# conlleval: evaluate result of processing CoNLL-2000 shared task
# usage:     conlleval [-l] [-r] [-d delimiterTag] [-o oTag] < file
#            README: http://www.clips.uantwerpen.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://www.clips.uantwerpen.be/conll2000/chunking/
# started:   1998-09-25
# version:   2004-01-26
# author:    Erik Tjong Kim Sang <erikt@uia.ua.ac.be>

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 $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