Update spaCy pipeline
Browse files- .gitattributes +2 -0
- README.md +14 -58
- config.cfg +23 -146
- en_ner_sender_recipient-any-py3-none-any.whl +2 -2
- meta.json +19 -174
- ner/model +2 -2
- ner/moves +1 -1
- tok2vec/model +2 -2
- vocab/key2row +3 -1
- vocab/lookups.bin +2 -2
- vocab/strings.json +2 -2
- vocab/vectors +0 -0
.gitattributes
CHANGED
@@ -36,3 +36,5 @@ en_ner_sender_recipient-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
|
|
36 |
ner/model filter=lfs diff=lfs merge=lfs -text
|
37 |
vocab/strings.json filter=lfs diff=lfs merge=lfs -text
|
38 |
tok2vec/model filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
36 |
ner/model filter=lfs diff=lfs merge=lfs -text
|
37 |
vocab/strings.json filter=lfs diff=lfs merge=lfs -text
|
38 |
tok2vec/model filter=lfs diff=lfs merge=lfs -text
|
39 |
+
vocab/vectors filter=lfs diff=lfs merge=lfs -text
|
40 |
+
vocab/key2row filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -13,57 +13,22 @@ model-index:
|
|
13 |
metrics:
|
14 |
- name: NER Precision
|
15 |
type: precision
|
16 |
-
value: 0.
|
17 |
- name: NER Recall
|
18 |
type: recall
|
19 |
-
value: 0.
|
20 |
- name: NER F Score
|
21 |
type: f_score
|
22 |
-
value: 0.
|
23 |
-
- task:
|
24 |
-
name: TAG
|
25 |
-
type: token-classification
|
26 |
-
metrics:
|
27 |
-
- name: TAG (XPOS) Accuracy
|
28 |
-
type: accuracy
|
29 |
-
value: 0.0
|
30 |
-
- task:
|
31 |
-
name: LEMMA
|
32 |
-
type: token-classification
|
33 |
-
metrics:
|
34 |
-
- name: Lemma Accuracy
|
35 |
-
type: accuracy
|
36 |
-
value: 0.0
|
37 |
-
- task:
|
38 |
-
name: UNLABELED_DEPENDENCIES
|
39 |
-
type: token-classification
|
40 |
-
metrics:
|
41 |
-
- name: Unlabeled Attachment Score (UAS)
|
42 |
-
type: f_score
|
43 |
-
value: 0.0
|
44 |
-
- task:
|
45 |
-
name: LABELED_DEPENDENCIES
|
46 |
-
type: token-classification
|
47 |
-
metrics:
|
48 |
-
- name: Labeled Attachment Score (LAS)
|
49 |
-
type: f_score
|
50 |
-
value: 0.0
|
51 |
-
- task:
|
52 |
-
name: SENTS
|
53 |
-
type: token-classification
|
54 |
-
metrics:
|
55 |
-
- name: Sentences F-Score
|
56 |
-
type: f_score
|
57 |
-
value: 0.0
|
58 |
---
|
59 |
| Feature | Description |
|
60 |
| --- | --- |
|
61 |
| **Name** | `en_ner_sender_recipient` |
|
62 |
-
| **Version** | `0.0.
|
63 |
| **spaCy** | `>=3.4.3,<3.5.0` |
|
64 |
-
| **Default Pipeline** | `tok2vec`, `
|
65 |
-
| **Components** | `tok2vec`, `
|
66 |
-
| **Vectors** |
|
67 |
| **Sources** | n/a |
|
68 |
| **License** | n/a |
|
69 |
| **Author** | [n/a]() |
|
@@ -72,13 +37,11 @@ model-index:
|
|
72 |
|
73 |
<details>
|
74 |
|
75 |
-
<summary>View label scheme (
|
76 |
|
77 |
| Component | Labels |
|
78 |
| --- | --- |
|
79 |
-
| **`
|
80 |
-
| **`parser`** | `ROOT`, `acl`, `acomp`, `advcl`, `advmod`, `agent`, `amod`, `appos`, `attr`, `aux`, `auxpass`, `case`, `cc`, `ccomp`, `compound`, `conj`, `csubj`, `csubjpass`, `dative`, `dep`, `det`, `dobj`, `expl`, `intj`, `mark`, `meta`, `neg`, `nmod`, `npadvmod`, `nsubj`, `nsubjpass`, `nummod`, `oprd`, `parataxis`, `pcomp`, `pobj`, `poss`, `preconj`, `predet`, `prep`, `prt`, `punct`, `quantmod`, `relcl`, `xcomp` |
|
81 |
-
| **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `RECIPIENT`, `SENDER`, `TIME`, `WORK_OF_ART` |
|
82 |
|
83 |
</details>
|
84 |
|
@@ -86,15 +49,8 @@ model-index:
|
|
86 |
|
87 |
| Type | Score |
|
88 |
| --- | --- |
|
89 |
-
| `
|
90 |
-
| `
|
91 |
-
| `
|
92 |
-
| `
|
93 |
-
| `
|
94 |
-
| `SENTS_R` | 0.00 |
|
95 |
-
| `SENTS_F` | 0.00 |
|
96 |
-
| `LEMMA_ACC` | 0.00 |
|
97 |
-
| `ENTS_F` | 0.00 |
|
98 |
-
| `ENTS_P` | 0.00 |
|
99 |
-
| `ENTS_R` | 0.00 |
|
100 |
-
| `NER_LOSS` | 6283.03 |
|
|
|
13 |
metrics:
|
14 |
- name: NER Precision
|
15 |
type: precision
|
16 |
+
value: 0.3507720105
|
17 |
- name: NER Recall
|
18 |
type: recall
|
19 |
+
value: 0.1265969114
|
20 |
- name: NER F Score
|
21 |
type: f_score
|
22 |
+
value: 0.1860475247
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
---
|
24 |
| Feature | Description |
|
25 |
| --- | --- |
|
26 |
| **Name** | `en_ner_sender_recipient` |
|
27 |
+
| **Version** | `0.0.2` |
|
28 |
| **spaCy** | `>=3.4.3,<3.5.0` |
|
29 |
+
| **Default Pipeline** | `tok2vec`, `ner` |
|
30 |
+
| **Components** | `tok2vec`, `ner` |
|
31 |
+
| **Vectors** | 514157 keys, 20000 unique vectors (300 dimensions) |
|
32 |
| **Sources** | n/a |
|
33 |
| **License** | n/a |
|
34 |
| **Author** | [n/a]() |
|
|
|
37 |
|
38 |
<details>
|
39 |
|
40 |
+
<summary>View label scheme (2 labels for 1 components)</summary>
|
41 |
|
42 |
| Component | Labels |
|
43 |
| --- | --- |
|
44 |
+
| **`ner`** | `RECIPIENT`, `SENDER` |
|
|
|
|
|
45 |
|
46 |
</details>
|
47 |
|
|
|
49 |
|
50 |
| Type | Score |
|
51 |
| --- | --- |
|
52 |
+
| `ENTS_F` | 18.60 |
|
53 |
+
| `ENTS_P` | 35.08 |
|
54 |
+
| `ENTS_R` | 12.66 |
|
55 |
+
| `TOK2VEC_LOSS` | 385.52 |
|
56 |
+
| `NER_LOSS` | 4421.31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.cfg
CHANGED
@@ -10,28 +10,16 @@ seed = 0
|
|
10 |
|
11 |
[nlp]
|
12 |
lang = "en"
|
13 |
-
pipeline = ["tok2vec","
|
14 |
-
|
|
|
15 |
before_creation = null
|
16 |
after_creation = null
|
17 |
after_pipeline_creation = null
|
18 |
-
batch_size = 256
|
19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
20 |
|
21 |
[components]
|
22 |
|
23 |
-
[components.attribute_ruler]
|
24 |
-
factory = "attribute_ruler"
|
25 |
-
scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
|
26 |
-
validate = false
|
27 |
-
|
28 |
-
[components.lemmatizer]
|
29 |
-
factory = "lemmatizer"
|
30 |
-
mode = "rule"
|
31 |
-
model = null
|
32 |
-
overwrite = false
|
33 |
-
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
|
34 |
-
|
35 |
[components.ner]
|
36 |
factory = "ner"
|
37 |
incorrect_spans_key = null
|
@@ -49,86 +37,9 @@ use_upper = true
|
|
49 |
nO = null
|
50 |
|
51 |
[components.ner.model.tok2vec]
|
52 |
-
@architectures = "spacy.Tok2Vec.v2"
|
53 |
-
|
54 |
-
[components.ner.model.tok2vec.embed]
|
55 |
-
@architectures = "spacy.MultiHashEmbed.v2"
|
56 |
-
width = 96
|
57 |
-
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
|
58 |
-
rows = [5000,1000,2500,2500,50]
|
59 |
-
include_static_vectors = false
|
60 |
-
|
61 |
-
[components.ner.model.tok2vec.encode]
|
62 |
-
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
63 |
-
width = 96
|
64 |
-
depth = 4
|
65 |
-
window_size = 1
|
66 |
-
maxout_pieces = 3
|
67 |
-
|
68 |
-
[components.parser]
|
69 |
-
factory = "parser"
|
70 |
-
learn_tokens = false
|
71 |
-
min_action_freq = 30
|
72 |
-
moves = null
|
73 |
-
scorer = {"@scorers":"spacy.parser_scorer.v1"}
|
74 |
-
update_with_oracle_cut_size = 100
|
75 |
-
|
76 |
-
[components.parser.model]
|
77 |
-
@architectures = "spacy.TransitionBasedParser.v2"
|
78 |
-
state_type = "parser"
|
79 |
-
extra_state_tokens = false
|
80 |
-
hidden_width = 64
|
81 |
-
maxout_pieces = 2
|
82 |
-
use_upper = true
|
83 |
-
nO = null
|
84 |
-
|
85 |
-
[components.parser.model.tok2vec]
|
86 |
-
@architectures = "spacy.Tok2VecListener.v1"
|
87 |
-
width = 96
|
88 |
-
upstream = "tok2vec"
|
89 |
-
|
90 |
-
[components.senter]
|
91 |
-
factory = "senter"
|
92 |
-
overwrite = false
|
93 |
-
scorer = {"@scorers":"spacy.senter_scorer.v1"}
|
94 |
-
|
95 |
-
[components.senter.model]
|
96 |
-
@architectures = "spacy.Tagger.v2"
|
97 |
-
nO = null
|
98 |
-
normalize = false
|
99 |
-
|
100 |
-
[components.senter.model.tok2vec]
|
101 |
-
@architectures = "spacy.Tok2Vec.v2"
|
102 |
-
|
103 |
-
[components.senter.model.tok2vec.embed]
|
104 |
-
@architectures = "spacy.MultiHashEmbed.v2"
|
105 |
-
width = 16
|
106 |
-
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
|
107 |
-
rows = [1000,500,500,500,50]
|
108 |
-
include_static_vectors = false
|
109 |
-
|
110 |
-
[components.senter.model.tok2vec.encode]
|
111 |
-
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
112 |
-
width = 16
|
113 |
-
depth = 2
|
114 |
-
window_size = 1
|
115 |
-
maxout_pieces = 2
|
116 |
-
|
117 |
-
[components.tagger]
|
118 |
-
factory = "tagger"
|
119 |
-
neg_prefix = "!"
|
120 |
-
overwrite = false
|
121 |
-
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
|
122 |
-
|
123 |
-
[components.tagger.model]
|
124 |
-
@architectures = "spacy.Tagger.v2"
|
125 |
-
nO = null
|
126 |
-
normalize = false
|
127 |
-
|
128 |
-
[components.tagger.model.tok2vec]
|
129 |
@architectures = "spacy.Tok2VecListener.v1"
|
130 |
-
width =
|
131 |
-
upstream = "
|
132 |
|
133 |
[components.tok2vec]
|
134 |
factory = "tok2vec"
|
@@ -138,10 +49,10 @@ factory = "tok2vec"
|
|
138 |
|
139 |
[components.tok2vec.model.embed]
|
140 |
@architectures = "spacy.MultiHashEmbed.v2"
|
141 |
-
width =
|
142 |
-
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"
|
143 |
-
rows = [5000,1000,2500,2500
|
144 |
-
include_static_vectors =
|
145 |
|
146 |
[components.tok2vec.model.encode]
|
147 |
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
@@ -155,33 +66,33 @@ maxout_pieces = 3
|
|
155 |
[corpora.dev]
|
156 |
@readers = "spacy.Corpus.v1"
|
157 |
path = ${paths.dev}
|
158 |
-
gold_preproc = false
|
159 |
max_length = 0
|
|
|
160 |
limit = 0
|
161 |
augmenter = null
|
162 |
|
163 |
[corpora.train]
|
164 |
@readers = "spacy.Corpus.v1"
|
165 |
path = ${paths.train}
|
166 |
-
gold_preproc = false
|
167 |
max_length = 0
|
|
|
168 |
limit = 0
|
169 |
augmenter = null
|
170 |
|
171 |
[training]
|
172 |
-
train_corpus = "corpora.train"
|
173 |
dev_corpus = "corpora.dev"
|
174 |
-
|
175 |
-
|
|
|
176 |
dropout = 0.1
|
177 |
accumulate_gradient = 1
|
178 |
patience = 50
|
179 |
max_epochs = 5
|
180 |
-
max_steps =
|
181 |
eval_frequency = 10
|
182 |
-
frozen_components = [
|
183 |
-
before_to_disk = null
|
184 |
annotating_components = []
|
|
|
185 |
|
186 |
[training.batcher]
|
187 |
@batchers = "spacy.batch_by_words.v1"
|
@@ -207,60 +118,26 @@ beta2 = 0.999
|
|
207 |
L2_is_weight_decay = true
|
208 |
L2 = 0.01
|
209 |
grad_clip = 1.0
|
210 |
-
use_averages =
|
211 |
eps = 0.00000001
|
212 |
learn_rate = 0.001
|
213 |
|
214 |
[training.score_weights]
|
215 |
-
|
216 |
-
dep_uas = 0.0
|
217 |
-
dep_las = 0.16
|
218 |
-
dep_las_per_type = null
|
219 |
-
sents_p = null
|
220 |
-
sents_r = null
|
221 |
-
sents_f = 0.02
|
222 |
-
lemma_acc = 0.5
|
223 |
-
ents_f = 0.16
|
224 |
ents_p = 0.0
|
225 |
ents_r = 0.0
|
226 |
ents_per_type = null
|
227 |
-
speed = 0.0
|
228 |
|
229 |
[pretraining]
|
230 |
|
231 |
[initialize]
|
232 |
-
|
233 |
-
vectors = null
|
234 |
init_tok2vec = ${paths.init_tok2vec}
|
235 |
-
|
236 |
lookups = null
|
237 |
-
|
238 |
-
|
239 |
-
@callbacks = "spacy.copy_from_base_model.v1"
|
240 |
-
tokenizer = "en_core_web_sm"
|
241 |
-
vocab = "en_core_web_sm"
|
242 |
|
243 |
[initialize.components]
|
244 |
|
245 |
-
[initialize.components.ner]
|
246 |
-
|
247 |
-
[initialize.components.ner.labels]
|
248 |
-
@readers = "spacy.read_labels.v1"
|
249 |
-
path = "corpus/labels/ner.json"
|
250 |
-
require = false
|
251 |
-
|
252 |
-
[initialize.components.parser]
|
253 |
-
|
254 |
-
[initialize.components.parser.labels]
|
255 |
-
@readers = "spacy.read_labels.v1"
|
256 |
-
path = "corpus/labels/parser.json"
|
257 |
-
require = false
|
258 |
-
|
259 |
-
[initialize.components.tagger]
|
260 |
-
|
261 |
-
[initialize.components.tagger.labels]
|
262 |
-
@readers = "spacy.read_labels.v1"
|
263 |
-
path = "corpus/labels/tagger.json"
|
264 |
-
require = false
|
265 |
-
|
266 |
[initialize.tokenizer]
|
|
|
10 |
|
11 |
[nlp]
|
12 |
lang = "en"
|
13 |
+
pipeline = ["tok2vec","ner"]
|
14 |
+
batch_size = 1000
|
15 |
+
disabled = []
|
16 |
before_creation = null
|
17 |
after_creation = null
|
18 |
after_pipeline_creation = null
|
|
|
19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
20 |
|
21 |
[components]
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
[components.ner]
|
24 |
factory = "ner"
|
25 |
incorrect_spans_key = null
|
|
|
37 |
nO = null
|
38 |
|
39 |
[components.ner.model.tok2vec]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
@architectures = "spacy.Tok2VecListener.v1"
|
41 |
+
width = ${components.tok2vec.model.encode.width}
|
42 |
+
upstream = "*"
|
43 |
|
44 |
[components.tok2vec]
|
45 |
factory = "tok2vec"
|
|
|
49 |
|
50 |
[components.tok2vec.model.embed]
|
51 |
@architectures = "spacy.MultiHashEmbed.v2"
|
52 |
+
width = ${components.tok2vec.model.encode.width}
|
53 |
+
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
|
54 |
+
rows = [5000,1000,2500,2500]
|
55 |
+
include_static_vectors = true
|
56 |
|
57 |
[components.tok2vec.model.encode]
|
58 |
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
|
|
66 |
[corpora.dev]
|
67 |
@readers = "spacy.Corpus.v1"
|
68 |
path = ${paths.dev}
|
|
|
69 |
max_length = 0
|
70 |
+
gold_preproc = false
|
71 |
limit = 0
|
72 |
augmenter = null
|
73 |
|
74 |
[corpora.train]
|
75 |
@readers = "spacy.Corpus.v1"
|
76 |
path = ${paths.train}
|
|
|
77 |
max_length = 0
|
78 |
+
gold_preproc = false
|
79 |
limit = 0
|
80 |
augmenter = null
|
81 |
|
82 |
[training]
|
|
|
83 |
dev_corpus = "corpora.dev"
|
84 |
+
train_corpus = "corpora.train"
|
85 |
+
seed = ${system.seed}
|
86 |
+
gpu_allocator = ${system.gpu_allocator}
|
87 |
dropout = 0.1
|
88 |
accumulate_gradient = 1
|
89 |
patience = 50
|
90 |
max_epochs = 5
|
91 |
+
max_steps = 20000
|
92 |
eval_frequency = 10
|
93 |
+
frozen_components = []
|
|
|
94 |
annotating_components = []
|
95 |
+
before_to_disk = null
|
96 |
|
97 |
[training.batcher]
|
98 |
@batchers = "spacy.batch_by_words.v1"
|
|
|
118 |
L2_is_weight_decay = true
|
119 |
L2 = 0.01
|
120 |
grad_clip = 1.0
|
121 |
+
use_averages = false
|
122 |
eps = 0.00000001
|
123 |
learn_rate = 0.001
|
124 |
|
125 |
[training.score_weights]
|
126 |
+
ents_f = 1.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
127 |
ents_p = 0.0
|
128 |
ents_r = 0.0
|
129 |
ents_per_type = null
|
|
|
130 |
|
131 |
[pretraining]
|
132 |
|
133 |
[initialize]
|
134 |
+
vectors = "en_core_web_md"
|
|
|
135 |
init_tok2vec = ${paths.init_tok2vec}
|
136 |
+
vocab_data = null
|
137 |
lookups = null
|
138 |
+
before_init = null
|
139 |
+
after_init = null
|
|
|
|
|
|
|
140 |
|
141 |
[initialize.components]
|
142 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
[initialize.tokenizer]
|
en_ner_sender_recipient-any-py3-none-any.whl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a95a8763493801e6c81c97433f4fb57bad661391dcbb62c35cc56e750978290b
|
3 |
+
size 38187757
|
meta.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"lang":"en",
|
3 |
"name":"ner_sender_recipient",
|
4 |
-
"version":"0.0.
|
5 |
"description":"",
|
6 |
"author":"",
|
7 |
"email":"",
|
@@ -10,204 +10,49 @@
|
|
10 |
"spacy_version":">=3.4.3,<3.5.0",
|
11 |
"spacy_git_version":"63673a792",
|
12 |
"vectors":{
|
13 |
-
"width":
|
14 |
-
"vectors":
|
15 |
-
"keys":
|
16 |
-
"name":
|
17 |
},
|
18 |
"labels":{
|
19 |
"tok2vec":[
|
20 |
|
21 |
-
],
|
22 |
-
"tagger":[
|
23 |
-
"$",
|
24 |
-
"''",
|
25 |
-
",",
|
26 |
-
"-LRB-",
|
27 |
-
"-RRB-",
|
28 |
-
".",
|
29 |
-
":",
|
30 |
-
"ADD",
|
31 |
-
"AFX",
|
32 |
-
"CC",
|
33 |
-
"CD",
|
34 |
-
"DT",
|
35 |
-
"EX",
|
36 |
-
"FW",
|
37 |
-
"HYPH",
|
38 |
-
"IN",
|
39 |
-
"JJ",
|
40 |
-
"JJR",
|
41 |
-
"JJS",
|
42 |
-
"LS",
|
43 |
-
"MD",
|
44 |
-
"NFP",
|
45 |
-
"NN",
|
46 |
-
"NNP",
|
47 |
-
"NNPS",
|
48 |
-
"NNS",
|
49 |
-
"PDT",
|
50 |
-
"POS",
|
51 |
-
"PRP",
|
52 |
-
"PRP$",
|
53 |
-
"RB",
|
54 |
-
"RBR",
|
55 |
-
"RBS",
|
56 |
-
"RP",
|
57 |
-
"SYM",
|
58 |
-
"TO",
|
59 |
-
"UH",
|
60 |
-
"VB",
|
61 |
-
"VBD",
|
62 |
-
"VBG",
|
63 |
-
"VBN",
|
64 |
-
"VBP",
|
65 |
-
"VBZ",
|
66 |
-
"WDT",
|
67 |
-
"WP",
|
68 |
-
"WP$",
|
69 |
-
"WRB",
|
70 |
-
"XX",
|
71 |
-
"_SP",
|
72 |
-
"``"
|
73 |
-
],
|
74 |
-
"parser":[
|
75 |
-
"ROOT",
|
76 |
-
"acl",
|
77 |
-
"acomp",
|
78 |
-
"advcl",
|
79 |
-
"advmod",
|
80 |
-
"agent",
|
81 |
-
"amod",
|
82 |
-
"appos",
|
83 |
-
"attr",
|
84 |
-
"aux",
|
85 |
-
"auxpass",
|
86 |
-
"case",
|
87 |
-
"cc",
|
88 |
-
"ccomp",
|
89 |
-
"compound",
|
90 |
-
"conj",
|
91 |
-
"csubj",
|
92 |
-
"csubjpass",
|
93 |
-
"dative",
|
94 |
-
"dep",
|
95 |
-
"det",
|
96 |
-
"dobj",
|
97 |
-
"expl",
|
98 |
-
"intj",
|
99 |
-
"mark",
|
100 |
-
"meta",
|
101 |
-
"neg",
|
102 |
-
"nmod",
|
103 |
-
"npadvmod",
|
104 |
-
"nsubj",
|
105 |
-
"nsubjpass",
|
106 |
-
"nummod",
|
107 |
-
"oprd",
|
108 |
-
"parataxis",
|
109 |
-
"pcomp",
|
110 |
-
"pobj",
|
111 |
-
"poss",
|
112 |
-
"preconj",
|
113 |
-
"predet",
|
114 |
-
"prep",
|
115 |
-
"prt",
|
116 |
-
"punct",
|
117 |
-
"quantmod",
|
118 |
-
"relcl",
|
119 |
-
"xcomp"
|
120 |
-
],
|
121 |
-
"attribute_ruler":[
|
122 |
-
|
123 |
-
],
|
124 |
-
"lemmatizer":[
|
125 |
-
|
126 |
],
|
127 |
"ner":[
|
128 |
-
"CARDINAL",
|
129 |
-
"DATE",
|
130 |
-
"EVENT",
|
131 |
-
"FAC",
|
132 |
-
"GPE",
|
133 |
-
"LANGUAGE",
|
134 |
-
"LAW",
|
135 |
-
"LOC",
|
136 |
-
"MONEY",
|
137 |
-
"NORP",
|
138 |
-
"ORDINAL",
|
139 |
-
"ORG",
|
140 |
-
"PERCENT",
|
141 |
-
"PERSON",
|
142 |
-
"PRODUCT",
|
143 |
-
"QUANTITY",
|
144 |
"RECIPIENT",
|
145 |
-
"SENDER"
|
146 |
-
"TIME",
|
147 |
-
"WORK_OF_ART"
|
148 |
]
|
149 |
},
|
150 |
"pipeline":[
|
151 |
"tok2vec",
|
152 |
-
"tagger",
|
153 |
-
"parser",
|
154 |
-
"attribute_ruler",
|
155 |
-
"lemmatizer",
|
156 |
"ner"
|
157 |
],
|
158 |
"components":[
|
159 |
"tok2vec",
|
160 |
-
"tagger",
|
161 |
-
"parser",
|
162 |
-
"senter",
|
163 |
-
"attribute_ruler",
|
164 |
-
"lemmatizer",
|
165 |
"ner"
|
166 |
],
|
167 |
"disabled":[
|
168 |
-
|
169 |
],
|
170 |
"performance":{
|
171 |
-
"
|
172 |
-
"
|
173 |
-
"
|
174 |
-
"dep_las_per_type":0.0,
|
175 |
-
"sents_p":0.0,
|
176 |
-
"sents_r":0.0,
|
177 |
-
"sents_f":0.0,
|
178 |
-
"lemma_acc":0.0,
|
179 |
-
"ents_f":0.0,
|
180 |
-
"ents_p":0.0,
|
181 |
-
"ents_r":0.0,
|
182 |
"ents_per_type":{
|
183 |
-
"RECIPIENT":{
|
184 |
-
"p":0.0,
|
185 |
-
"r":0.0,
|
186 |
-
"f":0.0
|
187 |
-
},
|
188 |
"SENDER":{
|
189 |
-
"p":0.
|
190 |
-
"r":0.
|
191 |
-
"f":0.
|
192 |
},
|
193 |
-
"
|
194 |
-
"p":0.
|
195 |
-
"r":0.
|
196 |
-
"f":0.
|
197 |
-
},
|
198 |
-
"NORP":{
|
199 |
-
"p":0.0,
|
200 |
-
"r":0.0,
|
201 |
-
"f":0.0
|
202 |
-
},
|
203 |
-
"PERSON":{
|
204 |
-
"p":0.0,
|
205 |
-
"r":0.0,
|
206 |
-
"f":0.0
|
207 |
}
|
208 |
},
|
209 |
-
"
|
210 |
-
"ner_loss":
|
211 |
},
|
212 |
"requirements":[
|
213 |
|
|
|
1 |
{
|
2 |
"lang":"en",
|
3 |
"name":"ner_sender_recipient",
|
4 |
+
"version":"0.0.2",
|
5 |
"description":"",
|
6 |
"author":"",
|
7 |
"email":"",
|
|
|
10 |
"spacy_version":">=3.4.3,<3.5.0",
|
11 |
"spacy_git_version":"63673a792",
|
12 |
"vectors":{
|
13 |
+
"width":300,
|
14 |
+
"vectors":20000,
|
15 |
+
"keys":514157,
|
16 |
+
"name":"en_vectors"
|
17 |
},
|
18 |
"labels":{
|
19 |
"tok2vec":[
|
20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
],
|
22 |
"ner":[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"RECIPIENT",
|
24 |
+
"SENDER"
|
|
|
|
|
25 |
]
|
26 |
},
|
27 |
"pipeline":[
|
28 |
"tok2vec",
|
|
|
|
|
|
|
|
|
29 |
"ner"
|
30 |
],
|
31 |
"components":[
|
32 |
"tok2vec",
|
|
|
|
|
|
|
|
|
|
|
33 |
"ner"
|
34 |
],
|
35 |
"disabled":[
|
36 |
+
|
37 |
],
|
38 |
"performance":{
|
39 |
+
"ents_f":0.1860475247,
|
40 |
+
"ents_p":0.3507720105,
|
41 |
+
"ents_r":0.1265969114,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
"ents_per_type":{
|
|
|
|
|
|
|
|
|
|
|
43 |
"SENDER":{
|
44 |
+
"p":0.4055570488,
|
45 |
+
"r":0.194699829,
|
46 |
+
"f":0.2630936553
|
47 |
},
|
48 |
+
"RECIPIENT":{
|
49 |
+
"p":0.1096984033,
|
50 |
+
"r":0.0189222962,
|
51 |
+
"f":0.0322770081
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
}
|
53 |
},
|
54 |
+
"tok2vec_loss":3.855186481,
|
55 |
+
"ner_loss":44.2130982176
|
56 |
},
|
57 |
"requirements":[
|
58 |
|
ner/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:189a45e7d5d37055e7799b3db371a7cf9741c89f81d968bcc6e08ed311739000
|
3 |
+
size 128548
|
ner/moves
CHANGED
@@ -1 +1 @@
|
|
1 |
-
��moves
|
|
|
1 |
+
��movesټ{"0":{},"1":{"SENDER":719197,"RECIPIENT":449266},"2":{"SENDER":719197,"RECIPIENT":449266},"3":{"SENDER":719197,"RECIPIENT":449266},"4":{"SENDER":719197,"RECIPIENT":449266,"":1},"5":{"":1}}�cfg��neg_key�
|
tok2vec/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11003ef7119f40f6ef584d13cd6dc24bc311765500065005548ff53b21e6df96
|
3 |
+
size 6235418
|
vocab/key2row
CHANGED
@@ -1 +1,3 @@
|
|
1 |
-
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:389912f67e81a52fbabb7edf8e36a0c3700b0b20d6dc6ef71bd56eb91ba08a0a
|
3 |
+
size 6165224
|
vocab/lookups.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
|
3 |
+
size 1
|
vocab/strings.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91d19e8896925d0f3afce0c586d5ca5e796db05fbf8092fc4389c090752dc930
|
3 |
+
size 19785939
|
vocab/vectors
CHANGED
Binary files a/vocab/vectors and b/vocab/vectors differ
|
|