-
-
Save abicky/c39632a2cb0188459de2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env ruby | |
require 'optparse' | |
require 'crfsuite' | |
params = ARGV.getopts('', 'command:', 'model:') | |
FEATURE_TEMPLATES = [ | |
[[-2, 0]], | |
[[-1, 0]], | |
[[ 0, 0]], | |
[[ 1, 0]], | |
[[ 2, 0]], | |
[[-1, 0], [0, 0]], | |
[[ 0, 0], [1, 0]], | |
[[-2, 1]], | |
[[-1, 1]], | |
[[ 0, 1]], | |
[[ 1, 1]], | |
[[ 2, 1]], | |
[[-2, 1], [-1, 1]], | |
[[-1, 1], [ 0, 1]], | |
[[ 0, 1], [ 1, 1]], | |
[[ 1, 1], [ 2, 1]], | |
[[-2, 1], [-1, 1], [0, 1]], | |
[[-1, 1], [ 0, 1], [1, 1]], | |
[[ 0, 1], [ 1, 1], [2, 1]], | |
].freeze | |
class Trainer < Crfsuite::Trainer | |
def message(s) | |
print s | |
end | |
end | |
def learn(model_file) | |
trainer = Trainer.new | |
yseq = Crfsuite::StringList.new | |
items = [] | |
STDIN.each do |line| | |
line.chomp! | |
if line.empty? | |
xseq = build_sequence(items) | |
trainer.append(xseq, yseq, 0) | |
items.clear | |
yseq = Crfsuite::StringList.new | |
next | |
end | |
fields = line.split(' ') | |
yseq << fields.pop | |
items << fields | |
end | |
trainer.select('l2sgd', 'crf1d') | |
trainer.set('c2', '0.1') | |
trainer.train(model_file, -1) | |
end | |
def tag(model_file) | |
tagger = Crfsuite::Tagger.new | |
tagger.open(model_file) | |
items = [] | |
STDIN.each do |line| | |
line.chomp! | |
if line.empty? | |
xseq = build_sequence(items) | |
tagger.set(xseq) | |
tagger.viterbi | |
items.clear | |
next | |
end | |
items << line.split(' ')[0..-2] | |
end | |
end | |
def build_sequence(items) | |
xseq = Crfsuite::ItemSequence.new | |
names = [] | |
values = [] | |
items.size.times do |offset| | |
item = Crfsuite::Item.new | |
FEATURE_TEMPLATES.each do |template| | |
names.clear | |
values.clear | |
available_feature = true | |
template.each do |field| | |
idx = offset + field[0] | |
if idx < 0 || idx >= items.size | |
available_feature = false | |
break | |
end | |
value = items[idx][field[1]] | |
if value.nil? | |
available_feature = false | |
break | |
end | |
names << 'x[%d,%d]' % field | |
values << value | |
end | |
next unless available_feature | |
item << Crfsuite::Attribute.new("#{names.join('|')}=#{values.join('|')}") | |
end | |
item << Crfsuite::Attribute.new('__BOS__') if offset.zero? | |
item << Crfsuite::Attribute.new('__EOS__') if offset == items.size - 1 | |
xseq << item | |
end | |
xseq | |
end | |
case params['command'] | |
when 'learn' | |
learn(params['model']) | |
when 'tag' | |
tag(params['model']) | |
else | |
raise ArgumentError, 'Unknown command' | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment