treat 0.2.5 → 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE +3 -3
- data/README.md +33 -0
- data/files/INFO +1 -0
- data/lib/treat.rb +40 -105
- data/lib/treat/ai.rb +12 -0
- data/lib/treat/ai/classifiers/id3.rb +27 -0
- data/lib/treat/categories.rb +82 -35
- data/lib/treat/categorizable.rb +44 -0
- data/lib/treat/classification.rb +61 -0
- data/lib/treat/configurable.rb +115 -0
- data/lib/treat/data_set.rb +42 -0
- data/lib/treat/dependencies.rb +24 -0
- data/lib/treat/downloader.rb +87 -0
- data/lib/treat/entities.rb +68 -66
- data/lib/treat/entities/abilities.rb +10 -0
- data/lib/treat/entities/abilities/buildable.rb +327 -0
- data/lib/treat/entities/abilities/checkable.rb +31 -0
- data/lib/treat/entities/abilities/copyable.rb +45 -0
- data/lib/treat/entities/abilities/countable.rb +51 -0
- data/lib/treat/entities/abilities/debuggable.rb +83 -0
- data/lib/treat/entities/abilities/delegatable.rb +123 -0
- data/lib/treat/entities/abilities/doable.rb +62 -0
- data/lib/treat/entities/abilities/exportable.rb +11 -0
- data/lib/treat/entities/abilities/iterable.rb +115 -0
- data/lib/treat/entities/abilities/magical.rb +83 -0
- data/lib/treat/entities/abilities/registrable.rb +74 -0
- data/lib/treat/entities/abilities/stringable.rb +91 -0
- data/lib/treat/entities/entities.rb +104 -0
- data/lib/treat/entities/entity.rb +122 -245
- data/lib/treat/exception.rb +4 -4
- data/lib/treat/extractors.rb +77 -80
- data/lib/treat/extractors/keywords/tf_idf.rb +56 -22
- data/lib/treat/extractors/language/what_language.rb +50 -45
- data/lib/treat/extractors/name_tag/stanford.rb +55 -0
- data/lib/treat/extractors/tf_idf/native.rb +87 -0
- data/lib/treat/extractors/time/chronic.rb +55 -0
- data/lib/treat/extractors/time/nickel.rb +86 -62
- data/lib/treat/extractors/time/ruby.rb +53 -0
- data/lib/treat/extractors/topic_words/lda.rb +67 -58
- data/lib/treat/extractors/topics/reuters.rb +100 -87
- data/lib/treat/formatters.rb +39 -35
- data/lib/treat/formatters/readers/abw.rb +49 -29
- data/lib/treat/formatters/readers/autoselect.rb +37 -33
- data/lib/treat/formatters/readers/doc.rb +19 -13
- data/lib/treat/formatters/readers/html.rb +52 -30
- data/lib/treat/formatters/readers/image.rb +41 -40
- data/lib/treat/formatters/readers/odt.rb +59 -45
- data/lib/treat/formatters/readers/pdf.rb +28 -25
- data/lib/treat/formatters/readers/txt.rb +12 -15
- data/lib/treat/formatters/readers/xml.rb +73 -36
- data/lib/treat/formatters/serializers/xml.rb +80 -79
- data/lib/treat/formatters/serializers/yaml.rb +19 -18
- data/lib/treat/formatters/unserializers/autoselect.rb +12 -22
- data/lib/treat/formatters/unserializers/xml.rb +94 -99
- data/lib/treat/formatters/unserializers/yaml.rb +20 -19
- data/lib/treat/formatters/visualizers/dot.rb +132 -132
- data/lib/treat/formatters/visualizers/standoff.rb +52 -44
- data/lib/treat/formatters/visualizers/tree.rb +26 -29
- data/lib/treat/groupable.rb +153 -0
- data/lib/treat/helpers/decimal_point_escaper.rb +22 -0
- data/lib/treat/inflectors.rb +50 -45
- data/lib/treat/inflectors/cardinalizers/linguistics.rb +40 -0
- data/lib/treat/inflectors/conjugators/linguistics.rb +55 -0
- data/lib/treat/inflectors/declensors/active_support.rb +31 -0
- data/lib/treat/inflectors/declensors/english.rb +38 -0
- data/lib/treat/inflectors/declensors/english/inflect.rb +288 -0
- data/lib/treat/inflectors/declensors/linguistics.rb +49 -0
- data/lib/treat/inflectors/ordinalizers/linguistics.rb +17 -0
- data/lib/treat/inflectors/stemmers/porter.rb +160 -0
- data/lib/treat/inflectors/stemmers/porter_c.rb +24 -0
- data/lib/treat/inflectors/stemmers/uea.rb +28 -0
- data/lib/treat/installer.rb +308 -0
- data/lib/treat/kernel.rb +105 -27
- data/lib/treat/languages.rb +122 -88
- data/lib/treat/languages/arabic.rb +15 -15
- data/lib/treat/languages/chinese.rb +15 -15
- data/lib/treat/languages/dutch.rb +15 -15
- data/lib/treat/languages/english.rb +61 -62
- data/lib/treat/languages/french.rb +19 -19
- data/lib/treat/languages/german.rb +20 -20
- data/lib/treat/languages/greek.rb +15 -15
- data/lib/treat/languages/italian.rb +16 -16
- data/lib/treat/languages/polish.rb +15 -15
- data/lib/treat/languages/portuguese.rb +15 -15
- data/lib/treat/languages/russian.rb +15 -15
- data/lib/treat/languages/spanish.rb +16 -16
- data/lib/treat/languages/swedish.rb +16 -16
- data/lib/treat/lexicalizers.rb +34 -55
- data/lib/treat/lexicalizers/categorizers/from_tag.rb +54 -0
- data/lib/treat/lexicalizers/sensers/wordnet.rb +57 -0
- data/lib/treat/lexicalizers/sensers/wordnet/synset.rb +71 -0
- data/lib/treat/lexicalizers/taggers/brill.rb +70 -0
- data/lib/treat/lexicalizers/taggers/brill/patch.rb +61 -0
- data/lib/treat/lexicalizers/taggers/lingua.rb +90 -0
- data/lib/treat/lexicalizers/taggers/stanford.rb +97 -0
- data/lib/treat/linguistics.rb +9 -0
- data/lib/treat/linguistics/categories.rb +11 -0
- data/lib/treat/linguistics/tags.rb +422 -0
- data/lib/treat/loaders/linguistics.rb +30 -0
- data/lib/treat/loaders/stanford.rb +27 -0
- data/lib/treat/object.rb +1 -0
- data/lib/treat/processors.rb +37 -44
- data/lib/treat/processors/chunkers/autoselect.rb +16 -0
- data/lib/treat/processors/chunkers/html.rb +71 -0
- data/lib/treat/processors/chunkers/txt.rb +18 -24
- data/lib/treat/processors/parsers/enju.rb +253 -208
- data/lib/treat/processors/parsers/stanford.rb +130 -131
- data/lib/treat/processors/segmenters/punkt.rb +79 -45
- data/lib/treat/processors/segmenters/stanford.rb +46 -48
- data/lib/treat/processors/segmenters/tactful.rb +43 -36
- data/lib/treat/processors/tokenizers/perl.rb +124 -92
- data/lib/treat/processors/tokenizers/ptb.rb +81 -0
- data/lib/treat/processors/tokenizers/punkt.rb +48 -42
- data/lib/treat/processors/tokenizers/stanford.rb +39 -38
- data/lib/treat/processors/tokenizers/tactful.rb +64 -55
- data/lib/treat/proxies.rb +52 -35
- data/lib/treat/retrievers.rb +26 -16
- data/lib/treat/retrievers/indexers/ferret.rb +47 -26
- data/lib/treat/retrievers/searchers/ferret.rb +69 -50
- data/lib/treat/tree.rb +241 -183
- data/spec/collection.rb +123 -0
- data/spec/document.rb +93 -0
- data/spec/entity.rb +408 -0
- data/spec/languages.rb +25 -0
- data/spec/phrase.rb +146 -0
- data/spec/samples/mathematicians/archimedes.abw +34 -0
- data/spec/samples/mathematicians/euler.html +21 -0
- data/spec/samples/mathematicians/gauss.pdf +0 -0
- data/spec/samples/mathematicians/leibniz.txt +13 -0
- data/spec/samples/mathematicians/newton.doc +0 -0
- data/spec/sandbox.rb +5 -0
- data/spec/token.rb +109 -0
- data/spec/treat.rb +52 -0
- data/spec/tree.rb +117 -0
- data/spec/word.rb +110 -0
- data/spec/zone.rb +66 -0
- data/tmp/INFO +1 -1
- metadata +100 -201
- data/INSTALL +0 -1
- data/README +0 -3
- data/TODO +0 -28
- data/lib/economist/half_cocked_basel.txt +0 -16
- data/lib/economist/hungarys_troubles.txt +0 -46
- data/lib/economist/indias_slowdown.txt +0 -15
- data/lib/economist/merkozy_rides_again.txt +0 -24
- data/lib/economist/prada_is_not_walmart.txt +0 -9
- data/lib/economist/to_infinity_and_beyond.txt +0 -15
- data/lib/ferret/_11.cfs +0 -0
- data/lib/ferret/_14.cfs +0 -0
- data/lib/ferret/_p.cfs +0 -0
- data/lib/ferret/_s.cfs +0 -0
- data/lib/ferret/_v.cfs +0 -0
- data/lib/ferret/_y.cfs +0 -0
- data/lib/ferret/segments +0 -0
- data/lib/ferret/segments_15 +0 -0
- data/lib/treat/buildable.rb +0 -157
- data/lib/treat/category.rb +0 -33
- data/lib/treat/delegatable.rb +0 -116
- data/lib/treat/doable.rb +0 -45
- data/lib/treat/entities/collection.rb +0 -14
- data/lib/treat/entities/document.rb +0 -12
- data/lib/treat/entities/phrases.rb +0 -17
- data/lib/treat/entities/tokens.rb +0 -61
- data/lib/treat/entities/zones.rb +0 -41
- data/lib/treat/extractors/coreferences/stanford.rb +0 -69
- data/lib/treat/extractors/date/chronic.rb +0 -32
- data/lib/treat/extractors/date/ruby.rb +0 -25
- data/lib/treat/extractors/keywords/topics_tf_idf.rb +0 -48
- data/lib/treat/extractors/language/language_extractor.rb +0 -27
- data/lib/treat/extractors/named_entity_tag/stanford.rb +0 -53
- data/lib/treat/extractors/roles/naive.rb +0 -73
- data/lib/treat/extractors/statistics/frequency_in.rb +0 -16
- data/lib/treat/extractors/statistics/position_in.rb +0 -14
- data/lib/treat/extractors/statistics/tf_idf.rb +0 -104
- data/lib/treat/extractors/statistics/transition_matrix.rb +0 -105
- data/lib/treat/extractors/statistics/transition_probability.rb +0 -57
- data/lib/treat/extractors/topic_words/lda/data.dat +0 -46
- data/lib/treat/extractors/topic_words/lda/wiki.yml +0 -121
- data/lib/treat/extractors/topics/reuters/industry.xml +0 -2717
- data/lib/treat/extractors/topics/reuters/region.xml +0 -13586
- data/lib/treat/extractors/topics/reuters/topics.xml +0 -17977
- data/lib/treat/feature.rb +0 -58
- data/lib/treat/features.rb +0 -7
- data/lib/treat/formatters/visualizers/short_value.rb +0 -29
- data/lib/treat/formatters/visualizers/txt.rb +0 -45
- data/lib/treat/group.rb +0 -106
- data/lib/treat/helpers/linguistics_loader.rb +0 -18
- data/lib/treat/inflectors/cardinal_words/linguistics.rb +0 -42
- data/lib/treat/inflectors/conjugations/linguistics.rb +0 -36
- data/lib/treat/inflectors/declensions/english.rb +0 -319
- data/lib/treat/inflectors/declensions/linguistics.rb +0 -42
- data/lib/treat/inflectors/ordinal_words/linguistics.rb +0 -20
- data/lib/treat/inflectors/stem/porter.rb +0 -162
- data/lib/treat/inflectors/stem/porter_c.rb +0 -26
- data/lib/treat/inflectors/stem/uea.rb +0 -30
- data/lib/treat/install.rb +0 -59
- data/lib/treat/languages/tags.rb +0 -377
- data/lib/treat/lexicalizers/category/from_tag.rb +0 -49
- data/lib/treat/lexicalizers/linkages/naive.rb +0 -63
- data/lib/treat/lexicalizers/synsets/wordnet.rb +0 -76
- data/lib/treat/lexicalizers/tag/brill.rb +0 -91
- data/lib/treat/lexicalizers/tag/lingua.rb +0 -123
- data/lib/treat/lexicalizers/tag/stanford.rb +0 -70
- data/lib/treat/processors/segmenters/punkt/dutch.yaml +0 -9716
- data/lib/treat/processors/segmenters/punkt/english.yaml +0 -10340
- data/lib/treat/processors/segmenters/punkt/french.yaml +0 -43159
- data/lib/treat/processors/segmenters/punkt/german.yaml +0 -9572
- data/lib/treat/processors/segmenters/punkt/greek.yaml +0 -6050
- data/lib/treat/processors/segmenters/punkt/italian.yaml +0 -14748
- data/lib/treat/processors/segmenters/punkt/polish.yaml +0 -9751
- data/lib/treat/processors/segmenters/punkt/portuguese.yaml +0 -13662
- data/lib/treat/processors/segmenters/punkt/russian.yaml +0 -4237
- data/lib/treat/processors/segmenters/punkt/spanish.yaml +0 -24034
- data/lib/treat/processors/segmenters/punkt/swedish.yaml +0 -10001
- data/lib/treat/processors/tokenizers/macintyre.rb +0 -77
- data/lib/treat/processors/tokenizers/multilingual.rb +0 -30
- data/lib/treat/registrable.rb +0 -28
- data/lib/treat/sugar.rb +0 -50
- data/lib/treat/viewable.rb +0 -29
- data/lib/treat/visitable.rb +0 -28
- data/test/profile.rb +0 -2
- data/test/tc_entity.rb +0 -117
- data/test/tc_extractors.rb +0 -73
- data/test/tc_formatters.rb +0 -41
- data/test/tc_inflectors.rb +0 -34
- data/test/tc_lexicalizers.rb +0 -32
- data/test/tc_processors.rb +0 -50
- data/test/tc_resources.rb +0 -22
- data/test/tc_treat.rb +0 -60
- data/test/tc_tree.rb +0 -60
- data/test/tests.rb +0 -20
- data/test/texts.rb +0 -19
- data/test/texts/english/half_cocked_basel.txt +0 -16
- data/test/texts/english/hose_and_dry.doc +0 -0
- data/test/texts/english/hungarys_troubles.abw +0 -70
- data/test/texts/english/long.html +0 -24
- data/test/texts/english/long.txt +0 -22
- data/test/texts/english/medium.txt +0 -5
- data/test/texts/english/republican_nomination.pdf +0 -0
- data/test/texts/english/saving_the_euro.odt +0 -0
- data/test/texts/english/short.txt +0 -3
- data/test/texts/english/zero_sum.html +0 -111
@@ -1,16 +1,16 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
1
|
+
class Treat::Languages::Chinese
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {
|
9
|
+
:tag => [:stanford]
|
10
|
+
}
|
11
|
+
Processors = {
|
12
|
+
:parsers => [:stanford]
|
13
|
+
}
|
14
|
+
Retrievers = {}
|
15
|
+
|
16
16
|
end
|
@@ -1,16 +1,16 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
1
|
+
class Treat::Languages::Dutch
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {}
|
9
|
+
Processors = {
|
10
|
+
:chunkers => [:txt],
|
11
|
+
:segmenters => [:punkt],
|
12
|
+
:tokenizers => [:perl, :tactful]
|
13
|
+
}
|
14
|
+
Retrievers = {}
|
15
|
+
|
16
16
|
end
|
@@ -1,64 +1,63 @@
|
|
1
|
-
|
2
|
-
module Languages
|
3
|
-
class English
|
4
|
-
|
5
|
-
RequiredDependencies = ['rbtagger', 'ruby-stemmer', 'tactful_tokenizer', 'nickel', 'wordnet']
|
6
|
-
OptionalDependencies = ['uea-stemmer', 'tokenizer', 'engtagger']
|
7
|
-
|
8
|
-
Extractors = {
|
9
|
-
:time => [:nickel],
|
10
|
-
:date => [:chronic, :ruby],
|
11
|
-
:topics => [:reuters],
|
12
|
-
:topic_words => [:lda],
|
13
|
-
:keywords => [:tf_idf, :topics_tf_idf],
|
14
|
-
:named_entity_tag => [:stanford],
|
15
|
-
:coreferences => [:stanford],
|
16
|
-
:roles => [:naive]
|
17
|
-
}
|
18
|
-
|
19
|
-
Processors = {
|
20
|
-
:chunkers => [:txt],
|
21
|
-
:parsers => [:stanford, :enju],
|
22
|
-
:segmenters => [:tactful, :punkt, :stanford],
|
23
|
-
:tokenizers => [:macintyre, :multilingual, :perl, :punkt, :tactful, :stanford]
|
24
|
-
}
|
25
|
-
|
26
|
-
Lexicalizers = {
|
27
|
-
:category => [:from_tag],
|
28
|
-
:linkages => [:naive],
|
29
|
-
:synsets => [:wordnet],
|
30
|
-
:tag => [:brill, :lingua, :stanford]
|
31
|
-
}
|
32
|
-
|
33
|
-
Inflectors = {
|
34
|
-
:conjugations => [:linguistics],
|
35
|
-
:declensions => [:english, :linguistics],
|
36
|
-
:stem => [:porter, :porter_c, :uea],
|
37
|
-
:ordinal_words => [:linguistics],
|
38
|
-
:cardinal_words => [:linguistics]
|
39
|
-
}
|
1
|
+
class Treat::Languages::English
|
40
2
|
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
3
|
+
RequiredDependencies = ['rbtagger', 'ruby-stemmer', 'tactful_tokenizer', 'nickel', 'rwordnet']
|
4
|
+
OptionalDependencies = ['uea-stemmer', 'engtagger', 'active_support', 'english']
|
5
|
+
|
6
|
+
Extractors = {
|
7
|
+
:time => [:chronic, :ruby, :nickel],
|
8
|
+
:topics => [:reuters],
|
9
|
+
:topic_words => [:lda],
|
10
|
+
:keywords => [:tf_idf],
|
11
|
+
:name_tag => [:stanford],
|
12
|
+
:coreferences => [:stanford],
|
13
|
+
:roles => [:naive]
|
14
|
+
}
|
15
|
+
|
16
|
+
Inflectors = {
|
17
|
+
:conjugators => [:linguistics],
|
18
|
+
:declensors => [:english, :linguistics, :active_support],
|
19
|
+
:stemmers => [:porter, :porter_c, :uea],
|
20
|
+
:ordinalizers => [:linguistics],
|
21
|
+
:cardinalizers => [:linguistics]
|
22
|
+
}
|
23
|
+
|
24
|
+
Lexicalizers = {
|
25
|
+
:categorizers => [:from_tag],
|
26
|
+
:taggers => [:lingua, :brill, :stanford],
|
27
|
+
:sensers => [:wordnet]
|
28
|
+
}
|
29
|
+
|
30
|
+
Processors = {
|
31
|
+
:chunkers => [:txt],
|
32
|
+
:parsers => [:stanford, :enju],
|
33
|
+
:segmenters => [:tactful, :punkt, :stanford],
|
34
|
+
:tokenizers => [:perl, :ptb, :stanford, :tactful, :punkt]
|
35
|
+
}
|
36
|
+
|
37
|
+
Retrievers = {
|
38
|
+
:searchers => [:ferret],
|
39
|
+
:indexers => [:ferret]
|
40
|
+
}
|
41
|
+
|
42
|
+
CommonWords = [
|
43
|
+
'the', 'of', 'and', 'a', 'to', 'in', 'is',
|
44
|
+
'you', 'that', 'it', 'he', 'was', 'for', 'on',
|
45
|
+
'are', 'as', 'with', 'his', 'they', 'I', 'at',
|
46
|
+
'be', 'this', 'have', 'from', 'or', 'one', 'had',
|
47
|
+
'by', 'word', 'but', 'not', 'what', 'all', 'were',
|
48
|
+
'we', 'when', 'your', 'can', 'said', 'there', 'use',
|
49
|
+
'an', 'each', 'which', 'she', 'do', 'how', 'their',
|
50
|
+
'if', 'will', 'up', 'other', 'about', 'out', 'many',
|
51
|
+
'then', 'them', 'these', 'so', 'some', 'her', 'would',
|
52
|
+
'make', 'like', 'him', 'into', 'time', 'has', 'look',
|
53
|
+
'two', 'more', 'write', 'go', 'see', 'number', 'no',
|
54
|
+
'way', 'could', 'people', 'my', 'than', 'first', 'been',
|
55
|
+
'call', 'who', 'its', 'now', 'find', 'long', 'down',
|
56
|
+
'day', 'did', 'get', 'come', 'made', 'may', 'part',
|
57
|
+
'say', 'also', 'new', 'much', 'should', 'still',
|
58
|
+
'such', 'before', 'after', 'other', 'then', 'over',
|
59
|
+
'under', 'therefore', 'nonetheless', 'thereafter',
|
60
|
+
'afterwards', 'here', 'huh', 'hah', "n't", "'t", 'here'
|
61
|
+
]
|
62
|
+
|
64
63
|
end
|
@@ -1,20 +1,20 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
1
|
+
class Treat::Languages::French
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {
|
9
|
+
:tag => [:stanford],
|
10
|
+
:category => [:from_tag]
|
11
|
+
}
|
12
|
+
Processors = {
|
13
|
+
:chunkers => [:txt],
|
14
|
+
:parsers => [:stanford],
|
15
|
+
:segmenters => [:punkt],
|
16
|
+
:tokenizers => [:perl, :tactful]
|
17
|
+
}
|
18
|
+
Retrievers = {}
|
19
|
+
|
20
20
|
end
|
@@ -1,20 +1,20 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
end
|
1
|
+
class Treat::Languages::German
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {
|
9
|
+
:tag => [:stanford],
|
10
|
+
:category => [:from_tag]
|
11
|
+
}
|
12
|
+
Processors = {
|
13
|
+
:chunkers => [:txt],
|
14
|
+
:parsers => [:stanford],
|
15
|
+
:segmenters => [:punkt],
|
16
|
+
:tokenizers => [:perl, :tactful]
|
17
|
+
}
|
18
|
+
Retrievers = {}
|
19
|
+
|
20
|
+
end
|
@@ -1,16 +1,16 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
1
|
+
class Treat::Languages::Greek
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {}
|
9
|
+
Processors = {
|
10
|
+
:chunkers => [:txt],
|
11
|
+
:segmenters => [:punkt],
|
12
|
+
:tokenizers => [:tactful]
|
13
|
+
}
|
14
|
+
Retrievers = {}
|
15
|
+
|
16
16
|
end
|
@@ -1,17 +1,17 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
1
|
+
class Treat::Languages::Italian
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {}
|
9
|
+
Processors = {
|
10
|
+
:chunkers => [:txt],
|
11
|
+
:parsers => [:stanford],
|
12
|
+
:segmenters => [:punkt],
|
13
|
+
:tokenizers => [:perl, :tactful]
|
14
|
+
}
|
15
|
+
Retrievers = {}
|
16
|
+
|
17
17
|
end
|
@@ -1,16 +1,16 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
1
|
+
class Treat::Languages::Polish
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {}
|
9
|
+
Processors = {
|
10
|
+
:chunkers => [:txt],
|
11
|
+
:segmenters => [:punkt],
|
12
|
+
:tokenizers => [:perl, :tactful]
|
13
|
+
}
|
14
|
+
Retrievers = {}
|
15
|
+
|
16
16
|
end
|
@@ -1,16 +1,16 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
1
|
+
class Treat::Languages::Portuguese
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {}
|
9
|
+
Processors = {
|
10
|
+
:chunkers => [:txt],
|
11
|
+
:segmenters => [:punkt],
|
12
|
+
:tokenizers => [:perl, :tactful]
|
13
|
+
}
|
14
|
+
Retrievers = {}
|
15
|
+
|
16
16
|
end
|
@@ -1,16 +1,16 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
1
|
+
class Treat::Languages::Russian
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {}
|
9
|
+
Processors = {
|
10
|
+
:chunkers => [:txt],
|
11
|
+
:segmenters => [:punkt],
|
12
|
+
:tokenizers => [:perl, :tactful]
|
13
|
+
}
|
14
|
+
Retrievers = {}
|
15
|
+
|
16
16
|
end
|
@@ -1,16 +1,16 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
end
|
1
|
+
class Treat::Languages::Spanish
|
2
|
+
|
3
|
+
RequiredDependencies = []
|
4
|
+
OptionalDependencies = []
|
5
|
+
|
6
|
+
Extractors = {}
|
7
|
+
Inflectors = {}
|
8
|
+
Lexicalizers = {}
|
9
|
+
Processors = {
|
10
|
+
:chunkers => [:txt],
|
11
|
+
:segmenters => [:punkt],
|
12
|
+
:tokenizers => [:perl, :tactful]
|
13
|
+
}
|
14
|
+
Retrievers = {}
|
15
|
+
|
16
|
+
end
|