opener-pos-tagger-en-es 2.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/README.md +79 -0
- data/bin/pos-tagger-en +13 -0
- data/bin/pos-tagger-es +13 -0
- data/bin/pos-tagger-fr +13 -0
- data/bin/pos-tagger-it +13 -0
- data/bin/pos-tagger-nl +13 -0
- data/core/target/ehu-pos-1.0.jar +0 -0
- data/lib/opener/pos_taggers/en/version.rb +7 -0
- data/lib/opener/pos_taggers/en.rb +118 -0
- data/opener-pos-tagger-en-es.gemspec +27 -0
- metadata +114 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 057739e4c1a1282039f21cfc81467a5193578825
|
4
|
+
data.tar.gz: 22a50f89e3f63158ccabd9471d8dea434a11adbc
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 1736f4efcf334f7ff2c835e68df764c96af65e0d688105b313f6b31c06df9591db231984339c50b92a7c64d08e4a8811328eb62ec8b9eec340e7d62e85549030
|
7
|
+
data.tar.gz: 4813bf565fe3480ef1adb04faaee0c766fa4b16058cbdc6782fca5ff3d80fc24e7fd2bcf8e4c4b348e95237e2e413cabb1e1a78e4cda906dc26e77c58f8ab4c6
|
data/README.md
ADDED
@@ -0,0 +1,79 @@
|
|
1
|
+
[![Build Status](https://drone.io/github.com/opener-project/pos-tagger-en-es/status.png)](https://drone.io/github.com/opener-project/pos-tagger-en-es/latest)
|
2
|
+
|
3
|
+
# English, Spanish, Dutch, Italian, French POS Tagger
|
4
|
+
|
5
|
+
**Modified to also do Dutch**
|
6
|
+
|
7
|
+
This repository contains the source code for the English & Spanish POS tagger of the
|
8
|
+
OpeNER project.
|
9
|
+
|
10
|
+
English perceptron models have been trained and evaluated using the WSJ
|
11
|
+
treebank as explained in K. Toutanova, D. Klein, and C. D. Manning.
|
12
|
+
Feature-rich part-of-speech tagging with a cyclic dependency network. In
|
13
|
+
Proceedings of HLT-NAACL’03, 2003. Currently we obtain a performance of 96.48%
|
14
|
+
vs 97.24% obtained by Toutanova et al. (2003).
|
15
|
+
|
16
|
+
Spanish Maximum Entropy models have been trained and evaluated using the Ancora
|
17
|
+
corpus; it was randomly divided in 90% for training (440K words) and 10% testing
|
18
|
+
(70K words), obtaining a performance of 98.88%.
|
19
|
+
|
20
|
+
## Requirements
|
21
|
+
|
22
|
+
* Java 1.7 or newer
|
23
|
+
* Ruby 1.9.2 or newer
|
24
|
+
* Maven
|
25
|
+
* Bundler
|
26
|
+
|
27
|
+
## Installation
|
28
|
+
|
29
|
+
Using RubyGems:
|
30
|
+
|
31
|
+
gem install opener-pos-tagger-en-es
|
32
|
+
|
33
|
+
Using Bundler:
|
34
|
+
|
35
|
+
gem 'opener-pos-tagger-en-es',
|
36
|
+
:git => 'git@github.com/opener-project/pos-tagger-en-es.git',
|
37
|
+
:branch => 'master'
|
38
|
+
|
39
|
+
Using specific install:
|
40
|
+
|
41
|
+
gem install specific_install
|
42
|
+
gem specific_install opener-pos-tagger-en-es \
|
43
|
+
-l https://github.com/opener-project/pos-tagger-en-es.git
|
44
|
+
|
45
|
+
## Usage
|
46
|
+
|
47
|
+
cat some_input_file.kaf | pos-tagger-en-es
|
48
|
+
|
49
|
+
## Contributing
|
50
|
+
|
51
|
+
First make sure all the required dependencies are installed:
|
52
|
+
|
53
|
+
bundle install
|
54
|
+
|
55
|
+
Then compile the required Java code:
|
56
|
+
|
57
|
+
bundle exec rake java:compile
|
58
|
+
|
59
|
+
For this you'll need to have Java 1.7 and Maven installed. These requirements
|
60
|
+
are verified for you before the Rake task calls Maven.
|
61
|
+
|
62
|
+
## Testing
|
63
|
+
|
64
|
+
To run the tests (which are powered by Cucumber), simply run the following:
|
65
|
+
|
66
|
+
bundle exec rake
|
67
|
+
|
68
|
+
This will take care of verifying the requirements, installing the required Java
|
69
|
+
packages and running the tests.
|
70
|
+
|
71
|
+
For more information on the available Rake tasks run the following:
|
72
|
+
|
73
|
+
bundle exec rake -T
|
74
|
+
|
75
|
+
## Structure
|
76
|
+
|
77
|
+
This repository comes in two parts: a collection of Java source files and Ruby
|
78
|
+
source files. The Java code can be found in the `core/` directory, everything
|
79
|
+
else will be Ruby source code.
|
data/bin/pos-tagger-en
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require_relative '../lib/opener/pos_taggers/en'
|
4
|
+
|
5
|
+
# STDIN.tty? returns `false` if data is being piped into the current process.
|
6
|
+
if STDIN.tty?
|
7
|
+
input = nil
|
8
|
+
else
|
9
|
+
input = STDIN.read
|
10
|
+
end
|
11
|
+
|
12
|
+
kernel = Opener::POSTaggers::EN.new(:args => ARGV)
|
13
|
+
puts kernel.run(input)
|
data/bin/pos-tagger-es
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require_relative '../lib/opener/pos_taggers/en'
|
4
|
+
|
5
|
+
# STDIN.tty? returns `false` if data is being piped into the current process.
|
6
|
+
if STDIN.tty?
|
7
|
+
input = nil
|
8
|
+
else
|
9
|
+
input = STDIN.read
|
10
|
+
end
|
11
|
+
|
12
|
+
kernel = Opener::POSTaggers::ES.new(:args => ARGV)
|
13
|
+
puts kernel.run(input)
|
data/bin/pos-tagger-fr
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require_relative '../lib/opener/pos_taggers/en'
|
4
|
+
|
5
|
+
# STDIN.tty? returns `false` if data is being piped into the current process.
|
6
|
+
if STDIN.tty?
|
7
|
+
input = nil
|
8
|
+
else
|
9
|
+
input = STDIN.read
|
10
|
+
end
|
11
|
+
|
12
|
+
kernel = Opener::POSTaggers::FR.new(:args => ARGV)
|
13
|
+
puts kernel.run(input)
|
data/bin/pos-tagger-it
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require_relative '../lib/opener/pos_taggers/en'
|
4
|
+
|
5
|
+
# STDIN.tty? returns `false` if data is being piped into the current process.
|
6
|
+
if STDIN.tty?
|
7
|
+
input = nil
|
8
|
+
else
|
9
|
+
input = STDIN.read
|
10
|
+
end
|
11
|
+
|
12
|
+
kernel = Opener::POSTaggers::IT.new(:args => ARGV)
|
13
|
+
puts kernel.run(input)
|
data/bin/pos-tagger-nl
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require_relative '../lib/opener/pos_taggers/en'
|
4
|
+
|
5
|
+
# STDIN.tty? returns `false` if data is being piped into the current process.
|
6
|
+
if STDIN.tty?
|
7
|
+
input = nil
|
8
|
+
else
|
9
|
+
input = STDIN.read
|
10
|
+
end
|
11
|
+
|
12
|
+
kernel = Opener::POSTaggers::NL.new(:args => ARGV)
|
13
|
+
puts kernel.run(input)
|
Binary file
|
@@ -0,0 +1,118 @@
|
|
1
|
+
require 'open3'
|
2
|
+
require 'stringio'
|
3
|
+
|
4
|
+
require 'java'
|
5
|
+
|
6
|
+
require File.expand_path('../../../../core/target/ehu-pos-1.0.jar', __FILE__)
|
7
|
+
|
8
|
+
import 'java.io.InputStreamReader'
|
9
|
+
import 'ixa.kaflib.KAFDocument'
|
10
|
+
import 'ehu.pos.Annotate'
|
11
|
+
import 'ehu.pos.Resources'
|
12
|
+
import 'ehu.lemmatize.MorfologikLemmatizer'
|
13
|
+
import 'ehu.lemmatize.Dictionary'
|
14
|
+
|
15
|
+
require_relative 'en/version'
|
16
|
+
|
17
|
+
module Opener
|
18
|
+
module POSTaggers
|
19
|
+
##
|
20
|
+
# The POS tagger that supports English and Spanish.
|
21
|
+
#
|
22
|
+
# @!attribute [r] args
|
23
|
+
# @return [Array]
|
24
|
+
# @!attribute [r] options
|
25
|
+
# @return [Hash]
|
26
|
+
#
|
27
|
+
class EN
|
28
|
+
attr_reader :args, :options
|
29
|
+
|
30
|
+
##
|
31
|
+
# The default language to use.
|
32
|
+
#
|
33
|
+
# @return [String]
|
34
|
+
#
|
35
|
+
DEFAULT_LANGUAGE = 'en'.freeze
|
36
|
+
|
37
|
+
##
|
38
|
+
# @param [Hash] options
|
39
|
+
#
|
40
|
+
# @option options [Array] :args The commandline arguments to pass to the
|
41
|
+
# underlying Python script.
|
42
|
+
#
|
43
|
+
def initialize(options = {})
|
44
|
+
@args = options.delete(:args) || []
|
45
|
+
@options = options
|
46
|
+
end
|
47
|
+
|
48
|
+
##
|
49
|
+
# Runs the command and returns the output of STDOUT, STDERR and the
|
50
|
+
# process information.
|
51
|
+
#
|
52
|
+
# @param [String] input The input to tag.
|
53
|
+
# @return [Array]
|
54
|
+
#
|
55
|
+
def run(input)
|
56
|
+
input = StringIO.new(input) unless input.kind_of?(IO)
|
57
|
+
reader = InputStreamReader.new(input.to_inputstream)
|
58
|
+
kaf = KAFDocument.create_from_stream(reader)
|
59
|
+
annotator = Java::ehu.pos.Annotate.new(language)
|
60
|
+
|
61
|
+
kaf.addLinguisticProcessor("terms","ehu-pos-"+language,"now","1.0");
|
62
|
+
annotator.annotatePOSToKAF(kaf, lemmatizer, language)
|
63
|
+
|
64
|
+
return kaf.to_string
|
65
|
+
end
|
66
|
+
|
67
|
+
protected
|
68
|
+
|
69
|
+
def dictionary
|
70
|
+
Resources.new.getBinaryDict(language)
|
71
|
+
end
|
72
|
+
|
73
|
+
def lemmatizer
|
74
|
+
MorfologikLemmatizer.new(dictionary)
|
75
|
+
end
|
76
|
+
|
77
|
+
##
|
78
|
+
# @return [String]
|
79
|
+
#
|
80
|
+
def language
|
81
|
+
return options[:language] || DEFAULT_LANGUAGE
|
82
|
+
end
|
83
|
+
end # EN
|
84
|
+
|
85
|
+
class ES < EN
|
86
|
+
##
|
87
|
+
# @return [String]
|
88
|
+
#
|
89
|
+
def language
|
90
|
+
return 'es'
|
91
|
+
end
|
92
|
+
end # ES
|
93
|
+
|
94
|
+
class NL < EN
|
95
|
+
def language
|
96
|
+
return 'nl'
|
97
|
+
end
|
98
|
+
end # NL
|
99
|
+
|
100
|
+
class IT < EN
|
101
|
+
##
|
102
|
+
# @return [String]
|
103
|
+
#
|
104
|
+
def language
|
105
|
+
return 'it'
|
106
|
+
end
|
107
|
+
end # IT
|
108
|
+
|
109
|
+
class FR < EN
|
110
|
+
##
|
111
|
+
# @return [String]
|
112
|
+
#
|
113
|
+
def language
|
114
|
+
return 'fr'
|
115
|
+
end
|
116
|
+
end # FR
|
117
|
+
end # POSTaggers
|
118
|
+
end # Opener
|
@@ -0,0 +1,27 @@
|
|
1
|
+
require File.expand_path('../lib/opener/pos_taggers/en/version', __FILE__)
|
2
|
+
|
3
|
+
Gem::Specification.new do |gem|
|
4
|
+
gem.name = "opener-pos-tagger-en-es"
|
5
|
+
gem.version = Opener::POSTaggers::EN::VERSION
|
6
|
+
gem.authors = ["development@olery.com"]
|
7
|
+
gem.summary = "POS tagging for english, spanish, dutch, italian and french"
|
8
|
+
gem.description = gem.summary
|
9
|
+
gem.homepage = "http://opener-project.github.com/"
|
10
|
+
gem.has_rdoc = "yard"
|
11
|
+
gem.required_ruby_version = ">= 1.9.2"
|
12
|
+
|
13
|
+
gem.files = Dir.glob([
|
14
|
+
'core/target/ehu-pos-*.jar',
|
15
|
+
'lib/**/*',
|
16
|
+
'*.gemspec',
|
17
|
+
'README.md'
|
18
|
+
]).select { |file| File.file?(file) }
|
19
|
+
|
20
|
+
gem.executables = Dir.glob('bin/*').map { |file| File.basename(file) }
|
21
|
+
|
22
|
+
gem.add_dependency 'opener-build-tools'
|
23
|
+
|
24
|
+
gem.add_development_dependency 'rspec'
|
25
|
+
gem.add_development_dependency 'cucumber'
|
26
|
+
gem.add_development_dependency 'rake'
|
27
|
+
end
|
metadata
ADDED
@@ -0,0 +1,114 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: opener-pos-tagger-en-es
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 2.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- development@olery.com
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-05-20 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: opener-build-tools
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rspec
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: cucumber
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: POS tagging for english, spanish, dutch, italian and french
|
70
|
+
email:
|
71
|
+
executables:
|
72
|
+
- pos-tagger-nl
|
73
|
+
- pos-tagger-en
|
74
|
+
- pos-tagger-fr
|
75
|
+
- pos-tagger-es
|
76
|
+
- pos-tagger-it
|
77
|
+
extensions: []
|
78
|
+
extra_rdoc_files: []
|
79
|
+
files:
|
80
|
+
- README.md
|
81
|
+
- bin/pos-tagger-en
|
82
|
+
- bin/pos-tagger-es
|
83
|
+
- bin/pos-tagger-fr
|
84
|
+
- bin/pos-tagger-it
|
85
|
+
- bin/pos-tagger-nl
|
86
|
+
- core/target/ehu-pos-1.0.jar
|
87
|
+
- lib/opener/pos_taggers/en.rb
|
88
|
+
- lib/opener/pos_taggers/en/version.rb
|
89
|
+
- opener-pos-tagger-en-es.gemspec
|
90
|
+
homepage: http://opener-project.github.com/
|
91
|
+
licenses: []
|
92
|
+
metadata: {}
|
93
|
+
post_install_message:
|
94
|
+
rdoc_options: []
|
95
|
+
require_paths:
|
96
|
+
- lib
|
97
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - ">="
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: 1.9.2
|
102
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
103
|
+
requirements:
|
104
|
+
- - ">="
|
105
|
+
- !ruby/object:Gem::Version
|
106
|
+
version: '0'
|
107
|
+
requirements: []
|
108
|
+
rubyforge_project:
|
109
|
+
rubygems_version: 2.2.2
|
110
|
+
signing_key:
|
111
|
+
specification_version: 4
|
112
|
+
summary: POS tagging for english, spanish, dutch, italian and french
|
113
|
+
test_files: []
|
114
|
+
has_rdoc: yard
|