Upload 15 files
Browse files- .gitattributes +3 -0
- id_dep_web_sm/config.cfg +169 -0
- id_dep_web_sm/meta.json +106 -0
- id_dep_web_sm/parser/cfg +13 -0
- id_dep_web_sm/parser/model +3 -0
- id_dep_web_sm/parser/moves +1 -0
- id_dep_web_sm/tagger/cfg +24 -0
- id_dep_web_sm/tagger/model +3 -0
- id_dep_web_sm/tok2vec/cfg +3 -0
- id_dep_web_sm/tok2vec/model +3 -0
- id_dep_web_sm/tokenizer +0 -0
- id_dep_web_sm/vocab/key2row +1 -0
- id_dep_web_sm/vocab/lookups.bin +3 -0
- id_dep_web_sm/vocab/strings.json +0 -0
- id_dep_web_sm/vocab/vectors +0 -0
- id_dep_web_sm/vocab/vectors.cfg +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
id_dep_web_sm/parser/model filter=lfs diff=lfs merge=lfs -text
|
37 |
+
id_dep_web_sm/tagger/model filter=lfs diff=lfs merge=lfs -text
|
38 |
+
id_dep_web_sm/tok2vec/model filter=lfs diff=lfs merge=lfs -text
|
id_dep_web_sm/config.cfg
ADDED
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[paths]
|
2 |
+
train = null
|
3 |
+
dev = null
|
4 |
+
vectors = null
|
5 |
+
init_tok2vec = null
|
6 |
+
|
7 |
+
[system]
|
8 |
+
seed = 0
|
9 |
+
gpu_allocator = null
|
10 |
+
|
11 |
+
[nlp]
|
12 |
+
lang = "id"
|
13 |
+
pipeline = ["tok2vec","parser","tagger"]
|
14 |
+
disabled = []
|
15 |
+
before_creation = null
|
16 |
+
after_creation = null
|
17 |
+
after_pipeline_creation = null
|
18 |
+
batch_size = 1000
|
19 |
+
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
20 |
+
vectors = {"@vectors":"spacy.Vectors.v1"}
|
21 |
+
|
22 |
+
[components]
|
23 |
+
|
24 |
+
[components.parser]
|
25 |
+
factory = "parser"
|
26 |
+
learn_tokens = false
|
27 |
+
min_action_freq = 30
|
28 |
+
moves = null
|
29 |
+
scorer = {"@scorers":"spacy.parser_scorer.v1"}
|
30 |
+
update_with_oracle_cut_size = 100
|
31 |
+
|
32 |
+
[components.parser.model]
|
33 |
+
@architectures = "spacy.TransitionBasedParser.v2"
|
34 |
+
state_type = "parser"
|
35 |
+
extra_state_tokens = false
|
36 |
+
hidden_width = 64
|
37 |
+
maxout_pieces = 2
|
38 |
+
use_upper = true
|
39 |
+
nO = null
|
40 |
+
|
41 |
+
[components.parser.model.tok2vec]
|
42 |
+
@architectures = "spacy.HashEmbedCNN.v2"
|
43 |
+
pretrained_vectors = null
|
44 |
+
width = 96
|
45 |
+
depth = 4
|
46 |
+
embed_size = 2000
|
47 |
+
window_size = 1
|
48 |
+
maxout_pieces = 3
|
49 |
+
subword_features = true
|
50 |
+
|
51 |
+
[components.tagger]
|
52 |
+
factory = "tagger"
|
53 |
+
label_smoothing = 0.0
|
54 |
+
neg_prefix = "!"
|
55 |
+
overwrite = false
|
56 |
+
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
|
57 |
+
|
58 |
+
[components.tagger.model]
|
59 |
+
@architectures = "spacy.Tagger.v2"
|
60 |
+
nO = null
|
61 |
+
normalize = false
|
62 |
+
|
63 |
+
[components.tagger.model.tok2vec]
|
64 |
+
@architectures = "spacy.HashEmbedCNN.v2"
|
65 |
+
pretrained_vectors = null
|
66 |
+
width = 96
|
67 |
+
depth = 4
|
68 |
+
embed_size = 2000
|
69 |
+
window_size = 1
|
70 |
+
maxout_pieces = 3
|
71 |
+
subword_features = true
|
72 |
+
|
73 |
+
[components.tok2vec]
|
74 |
+
factory = "tok2vec"
|
75 |
+
|
76 |
+
[components.tok2vec.model]
|
77 |
+
@architectures = "spacy.HashEmbedCNN.v2"
|
78 |
+
pretrained_vectors = null
|
79 |
+
width = 96
|
80 |
+
depth = 4
|
81 |
+
embed_size = 2000
|
82 |
+
window_size = 1
|
83 |
+
maxout_pieces = 3
|
84 |
+
subword_features = true
|
85 |
+
|
86 |
+
[corpora]
|
87 |
+
|
88 |
+
[corpora.dev]
|
89 |
+
@readers = "spacy.Corpus.v1"
|
90 |
+
path = ${paths.dev}
|
91 |
+
gold_preproc = false
|
92 |
+
max_length = 0
|
93 |
+
limit = 0
|
94 |
+
augmenter = null
|
95 |
+
|
96 |
+
[corpora.train]
|
97 |
+
@readers = "spacy.Corpus.v1"
|
98 |
+
path = ${paths.train}
|
99 |
+
gold_preproc = false
|
100 |
+
max_length = 0
|
101 |
+
limit = 0
|
102 |
+
augmenter = null
|
103 |
+
|
104 |
+
[training]
|
105 |
+
seed = ${system.seed}
|
106 |
+
gpu_allocator = ${system.gpu_allocator}
|
107 |
+
dropout = 0.1
|
108 |
+
accumulate_gradient = 1
|
109 |
+
patience = 1600
|
110 |
+
max_epochs = 0
|
111 |
+
max_steps = 20000
|
112 |
+
eval_frequency = 200
|
113 |
+
frozen_components = []
|
114 |
+
annotating_components = []
|
115 |
+
dev_corpus = "corpora.dev"
|
116 |
+
train_corpus = "corpora.train"
|
117 |
+
before_to_disk = null
|
118 |
+
before_update = null
|
119 |
+
|
120 |
+
[training.batcher]
|
121 |
+
@batchers = "spacy.batch_by_words.v1"
|
122 |
+
discard_oversize = false
|
123 |
+
tolerance = 0.2
|
124 |
+
get_length = null
|
125 |
+
|
126 |
+
[training.batcher.size]
|
127 |
+
@schedules = "compounding.v1"
|
128 |
+
start = 100
|
129 |
+
stop = 1000
|
130 |
+
compound = 1.001
|
131 |
+
t = 0.0
|
132 |
+
|
133 |
+
[training.logger]
|
134 |
+
@loggers = "spacy.ConsoleLogger.v1"
|
135 |
+
progress_bar = false
|
136 |
+
|
137 |
+
[training.optimizer]
|
138 |
+
@optimizers = "Adam.v1"
|
139 |
+
beta1 = 0.9
|
140 |
+
beta2 = 0.999
|
141 |
+
L2_is_weight_decay = true
|
142 |
+
L2 = 0.01
|
143 |
+
grad_clip = 1.0
|
144 |
+
use_averages = false
|
145 |
+
eps = 0.00000001
|
146 |
+
learn_rate = 0.001
|
147 |
+
|
148 |
+
[training.score_weights]
|
149 |
+
dep_uas = 0.25
|
150 |
+
dep_las = 0.25
|
151 |
+
dep_las_per_type = null
|
152 |
+
sents_p = null
|
153 |
+
sents_r = null
|
154 |
+
sents_f = 0.0
|
155 |
+
tag_acc = 0.5
|
156 |
+
|
157 |
+
[pretraining]
|
158 |
+
|
159 |
+
[initialize]
|
160 |
+
vectors = ${paths.vectors}
|
161 |
+
init_tok2vec = ${paths.init_tok2vec}
|
162 |
+
vocab_data = null
|
163 |
+
lookups = null
|
164 |
+
before_init = null
|
165 |
+
after_init = null
|
166 |
+
|
167 |
+
[initialize.components]
|
168 |
+
|
169 |
+
[initialize.tokenizer]
|
id_dep_web_sm/meta.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"lang":"id",
|
3 |
+
"name":"pipeline",
|
4 |
+
"version":"0.0.0",
|
5 |
+
"spacy_version":">=3.8.3,<3.9.0",
|
6 |
+
"description":"",
|
7 |
+
"author":"",
|
8 |
+
"email":"",
|
9 |
+
"url":"",
|
10 |
+
"license":"",
|
11 |
+
"spacy_git_version":"be0fa81",
|
12 |
+
"vectors":{
|
13 |
+
"width":0,
|
14 |
+
"vectors":0,
|
15 |
+
"keys":0,
|
16 |
+
"name":null,
|
17 |
+
"mode":"default"
|
18 |
+
},
|
19 |
+
"labels":{
|
20 |
+
"tok2vec":[
|
21 |
+
|
22 |
+
],
|
23 |
+
"parser":[
|
24 |
+
"ROOT",
|
25 |
+
"acl",
|
26 |
+
"acl:relcl",
|
27 |
+
"advcl",
|
28 |
+
"advmod",
|
29 |
+
"advmod:emph",
|
30 |
+
"amod",
|
31 |
+
"appos",
|
32 |
+
"aux",
|
33 |
+
"case",
|
34 |
+
"case:adv",
|
35 |
+
"cc",
|
36 |
+
"cc:preconj",
|
37 |
+
"ccomp",
|
38 |
+
"clf",
|
39 |
+
"compound",
|
40 |
+
"compound:a",
|
41 |
+
"conj",
|
42 |
+
"cop",
|
43 |
+
"csubj",
|
44 |
+
"csubj:pass",
|
45 |
+
"dep",
|
46 |
+
"det",
|
47 |
+
"discourse",
|
48 |
+
"fixed",
|
49 |
+
"flat",
|
50 |
+
"flat:foreign",
|
51 |
+
"flat:name",
|
52 |
+
"goeswith",
|
53 |
+
"iobj",
|
54 |
+
"list",
|
55 |
+
"mark",
|
56 |
+
"nmod",
|
57 |
+
"nmod:lmod",
|
58 |
+
"nmod:poss",
|
59 |
+
"nmod:tmod",
|
60 |
+
"nsubj",
|
61 |
+
"nsubj:pass",
|
62 |
+
"nummod",
|
63 |
+
"obj",
|
64 |
+
"obl",
|
65 |
+
"obl:agent",
|
66 |
+
"obl:tmod",
|
67 |
+
"orphan",
|
68 |
+
"parataxis",
|
69 |
+
"punct",
|
70 |
+
"vocative",
|
71 |
+
"xcomp"
|
72 |
+
],
|
73 |
+
"tagger":[
|
74 |
+
"PROPN",
|
75 |
+
"AUX",
|
76 |
+
"DET",
|
77 |
+
"NOUN",
|
78 |
+
"PRON",
|
79 |
+
"VERB",
|
80 |
+
"ADP",
|
81 |
+
"PUNCT",
|
82 |
+
"ADV",
|
83 |
+
"CCONJ",
|
84 |
+
"SCONJ",
|
85 |
+
"NUM",
|
86 |
+
"ADJ",
|
87 |
+
"PART",
|
88 |
+
"SYM",
|
89 |
+
"INTJ",
|
90 |
+
"X"
|
91 |
+
]
|
92 |
+
},
|
93 |
+
"pipeline":[
|
94 |
+
"tok2vec",
|
95 |
+
"parser",
|
96 |
+
"tagger"
|
97 |
+
],
|
98 |
+
"components":[
|
99 |
+
"tok2vec",
|
100 |
+
"parser",
|
101 |
+
"tagger"
|
102 |
+
],
|
103 |
+
"disabled":[
|
104 |
+
|
105 |
+
]
|
106 |
+
}
|
id_dep_web_sm/parser/cfg
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"moves":null,
|
3 |
+
"update_with_oracle_cut_size":100,
|
4 |
+
"multitasks":[
|
5 |
+
|
6 |
+
],
|
7 |
+
"min_action_freq":30,
|
8 |
+
"learn_tokens":false,
|
9 |
+
"beam_width":1,
|
10 |
+
"beam_density":0.0,
|
11 |
+
"beam_update_prob":0.0,
|
12 |
+
"incorrect_spans_key":null
|
13 |
+
}
|
id_dep_web_sm/parser/model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d0d9591e65e456f4416183abafe94ceb8a38f3343c9f22ae755f30a82566f60
|
3 |
+
size 4060164
|
id_dep_web_sm/parser/moves
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
��moves�E{"0":{"nsubj":-2,"cop":-3,"det":-4,"ROOT":-5,"nsubj:pass":-6,"acl:relcl":-7,"case":-8,"obl":-9,"nmod":-10,"punct":-11,"appos":-12,"amod":-13,"compound":-14,"advmod":-15,"cc":-16,"mark":-17,"acl":-18,"obj":-19,"conj":-20,"nmod:poss":-21,"advcl":-22,"flat:name":-23,"nmod:tmod":-24,"nummod":-25,"aux":-26,"dep":-27,"xcomp":-28,"advmod:emph":-29,"ccomp":-30,"parataxis":-31,"obl:tmod":-32,"clf":-33,"flat":-34,"fixed":-35,"discourse":-36,"vocative":-37,"obl:agent":-38,"case:adv":-39,"nmod:lmod":-40,"compound:a":-41,"goeswith":-42,"orphan":-43,"csubj":-44,"iobj":-45,"list":-46,"csubj:pass":-47,"cc:preconj":-48,"flat:foreign":-49},"1":{"nsubj":-2,"cop":-3,"det":-4,"ROOT":-5,"nsubj:pass":-6,"acl:relcl":-7,"case":-8,"obl":-9,"nmod":-10,"punct":-11,"appos":-12,"amod":-13,"compound":-14,"advmod":-15,"cc":-16,"mark":-17,"acl":-18,"obj":-19,"conj":-20,"nmod:poss":-21,"advcl":-22,"flat:name":-23,"nmod:tmod":-24,"nummod":-25,"aux":-26,"dep":-27,"xcomp":-28,"advmod:emph":-29,"ccomp":-30,"parataxis":-31,"obl:tmod":-32,"clf":-33,"flat":-34,"fixed":-35,"discourse":-36,"vocative":-37,"obl:agent":-38,"case:adv":-39,"nmod:lmod":-40,"compound:a":-41,"goeswith":-42,"orphan":-43,"csubj":-44,"iobj":-45,"list":-46,"csubj:pass":-47,"cc:preconj":-48,"flat:foreign":-49},"2":{"dep":0,"nsubj":-2,"cop":-3,"det":-4,"ROOT":-5,"nsubj:pass":-6,"acl:relcl":-7,"case":-8,"obl":-9,"nmod":-10,"punct":-11,"appos":-12,"amod":-13,"compound":-14,"advmod":-15,"cc":-16,"mark":-17,"acl":-18,"obj":-19,"conj":-20,"nmod:poss":-21,"advcl":-22,"flat:name":-23,"nmod:tmod":-24,"nummod":-25,"aux":-26,"xcomp":-28,"advmod:emph":-29,"ccomp":-30,"parataxis":-31,"obl:tmod":-32,"clf":-33,"flat":-34,"fixed":-35,"discourse":-36,"vocative":-37,"obl:agent":-38,"case:adv":-39,"nmod:lmod":-40,"compound:a":-41,"goeswith":-42,"orphan":-43,"csubj":-44,"iobj":-45,"list":-46,"csubj:pass":-47,"cc:preconj":-48,"flat:foreign":-49},"3":{"dep":0,"nsubj":-2,"cop":-3,"det":-4,"ROOT":-5,"nsubj:pass":-6,"acl:relcl":-7,"case":-8,"obl":-9,"nmod":-10,"punct":-11,"appos":-12,"amod":-13,"compound":-14,"advmod":-15,"cc":-16,"mark":-17,"acl":-18,"obj":-19,"conj":-20,"nmod:poss":-21,"advcl":-22,"flat:name":-23,"nmod:tmod":-24,"nummod":-25,"aux":-26,"xcomp":-28,"advmod:emph":-29,"ccomp":-30,"parataxis":-31,"obl:tmod":-32,"clf":-33,"flat":-34,"fixed":-35,"discourse":-36,"vocative":-37,"obl:agent":-38,"case:adv":-39,"nmod:lmod":-40,"compound:a":-41,"goeswith":-42,"orphan":-43,"csubj":-44,"iobj":-45,"list":-46,"csubj:pass":-47,"cc:preconj":-48,"flat:foreign":-49},"4":{"ROOT":0,"nsubj":-2,"cop":-3,"det":-4,"nsubj:pass":-6,"acl:relcl":-7,"case":-8,"obl":-9,"nmod":-10,"punct":-11,"appos":-12,"amod":-13,"compound":-14,"advmod":-15,"cc":-16,"mark":-17,"acl":-18,"obj":-19,"conj":-20,"nmod:poss":-21,"advcl":-22,"flat:name":-23,"nmod:tmod":-24,"nummod":-25,"aux":-26,"dep":-27,"xcomp":-28,"advmod:emph":-29,"ccomp":-30,"parataxis":-31,"obl:tmod":-32,"clf":-33,"flat":-34,"fixed":-35,"discourse":-36,"vocative":-37,"obl:agent":-38,"case:adv":-39,"nmod:lmod":-40,"compound:a":-41,"goeswith":-42,"orphan":-43,"csubj":-44,"iobj":-45,"list":-46,"csubj:pass":-47,"cc:preconj":-48,"flat:foreign":-49}}�cfg��neg_key�
|
id_dep_web_sm/tagger/cfg
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"label_smoothing":0.0,
|
3 |
+
"labels":[
|
4 |
+
"PROPN",
|
5 |
+
"AUX",
|
6 |
+
"DET",
|
7 |
+
"NOUN",
|
8 |
+
"PRON",
|
9 |
+
"VERB",
|
10 |
+
"ADP",
|
11 |
+
"PUNCT",
|
12 |
+
"ADV",
|
13 |
+
"CCONJ",
|
14 |
+
"SCONJ",
|
15 |
+
"NUM",
|
16 |
+
"ADJ",
|
17 |
+
"PART",
|
18 |
+
"SYM",
|
19 |
+
"INTJ",
|
20 |
+
"X"
|
21 |
+
],
|
22 |
+
"neg_prefix":"!",
|
23 |
+
"overwrite":false
|
24 |
+
}
|
id_dep_web_sm/tagger/model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:574edacde8d90c2a76babadc1257b0fd347155ad0a3079f90cd1509d9b388b68
|
3 |
+
size 3712437
|
id_dep_web_sm/tok2vec/cfg
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
|
3 |
+
}
|
id_dep_web_sm/tok2vec/model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8459bda201c5daf60072489266a53b70f5c3a0b6bdfd3fab5d622a443b8754b
|
3 |
+
size 3705091
|
id_dep_web_sm/tokenizer
ADDED
The diff for this file is too large to render.
See raw diff
|
|
id_dep_web_sm/vocab/key2row
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
�
|
id_dep_web_sm/vocab/lookups.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
|
3 |
+
size 1
|
id_dep_web_sm/vocab/strings.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
id_dep_web_sm/vocab/vectors
ADDED
Binary file (128 Bytes). View file
|
|
id_dep_web_sm/vocab/vectors.cfg
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"mode":"default"
|
3 |
+
}
|