omar-araboghli
commited on
Commit
•
fa499d2
1
Parent(s):
b971b20
Uploading model and model config
Browse files- best.th +3 -0
- config.json +61 -0
- vocabulary/labels.txt +17 -0
- vocabulary/non_padded_namespaces.txt +2 -0
- vocabulary/token_characters.txt +110 -0
best.th
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b78a3ac97d17cf647f3239351c192d846fdbf222513361bf5c73d79d3db893b
|
3 |
+
size 537505659
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dataset_reader": {
|
3 |
+
"type": "conll2003",
|
4 |
+
"coding_scheme": "BIOUL",
|
5 |
+
"tag_label": "ner",
|
6 |
+
"token_indexers": {
|
7 |
+
"bert": {
|
8 |
+
"type": "bert-pretrained",
|
9 |
+
"do_lowercase": "true",
|
10 |
+
"pretrained_model": "scibert_scivocab_uncased",
|
11 |
+
"use_starting_offsets": true
|
12 |
+
},
|
13 |
+
"token_characters": {
|
14 |
+
"type": "characters",
|
15 |
+
"min_padding_length": 3
|
16 |
+
}
|
17 |
+
}
|
18 |
+
},
|
19 |
+
"model": {
|
20 |
+
"type": "crf_tagger",
|
21 |
+
"calculate_span_f1": true,
|
22 |
+
"constrain_crf_decoding": true,
|
23 |
+
"dropout": 0.5,
|
24 |
+
"encoder": {
|
25 |
+
"type": "lstm",
|
26 |
+
"bidirectional": true,
|
27 |
+
"dropout": 0.5,
|
28 |
+
"hidden_size": 768,
|
29 |
+
"input_size": 896,
|
30 |
+
"num_layers": 2
|
31 |
+
},
|
32 |
+
"include_start_end_transitions": false,
|
33 |
+
"label_encoding": "BIOUL",
|
34 |
+
"text_field_embedder": {
|
35 |
+
"allow_unmatched_keys": true,
|
36 |
+
"embedder_to_indexer_map": {
|
37 |
+
"bert": ["bert", "bert-offsets"],
|
38 |
+
"token_characters": ["token_characters"]
|
39 |
+
},
|
40 |
+
"token_embedders": {
|
41 |
+
"bert": {
|
42 |
+
"type": "bert-pretrained",
|
43 |
+
"pretrained_model": "scibert_scivocab_uncased"
|
44 |
+
},
|
45 |
+
"token_characters": {
|
46 |
+
"type": "character_encoding",
|
47 |
+
"embedding": {
|
48 |
+
"embedding_dim": 16
|
49 |
+
},
|
50 |
+
"encoder": {
|
51 |
+
"type": "cnn",
|
52 |
+
"conv_layer_activation": "relu",
|
53 |
+
"embedding_dim": 16,
|
54 |
+
"ngram_filter_sizes": [3],
|
55 |
+
"num_filters": 128
|
56 |
+
}
|
57 |
+
}
|
58 |
+
}
|
59 |
+
}
|
60 |
+
}
|
61 |
+
}
|
vocabulary/labels.txt
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
O
|
2 |
+
I-Material
|
3 |
+
I-Data
|
4 |
+
B-Material
|
5 |
+
L-Material
|
6 |
+
I-Process
|
7 |
+
B-Data
|
8 |
+
L-Data
|
9 |
+
B-Process
|
10 |
+
L-Process
|
11 |
+
U-Process
|
12 |
+
I-Method
|
13 |
+
U-Material
|
14 |
+
U-Data
|
15 |
+
B-Method
|
16 |
+
L-Method
|
17 |
+
U-Method
|
vocabulary/non_padded_namespaces.txt
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
*labels
|
2 |
+
*tags
|
vocabulary/token_characters.txt
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
@@UNKNOWN@@
|
2 |
+
e
|
3 |
+
t
|
4 |
+
i
|
5 |
+
a
|
6 |
+
n
|
7 |
+
o
|
8 |
+
s
|
9 |
+
r
|
10 |
+
l
|
11 |
+
c
|
12 |
+
d
|
13 |
+
h
|
14 |
+
u
|
15 |
+
p
|
16 |
+
m
|
17 |
+
f
|
18 |
+
g
|
19 |
+
y
|
20 |
+
b
|
21 |
+
w
|
22 |
+
v
|
23 |
+
.
|
24 |
+
,
|
25 |
+
-
|
26 |
+
T
|
27 |
+
C
|
28 |
+
S
|
29 |
+
x
|
30 |
+
k
|
31 |
+
A
|
32 |
+
1
|
33 |
+
0
|
34 |
+
2
|
35 |
+
)
|
36 |
+
(
|
37 |
+
P
|
38 |
+
M
|
39 |
+
H
|
40 |
+
O
|
41 |
+
R
|
42 |
+
I
|
43 |
+
D
|
44 |
+
•
|
45 |
+
3
|
46 |
+
E
|
47 |
+
N
|
48 |
+
F
|
49 |
+
W
|
50 |
+
q
|
51 |
+
z
|
52 |
+
5
|
53 |
+
G
|
54 |
+
L
|
55 |
+
4
|
56 |
+
/
|
57 |
+
B
|
58 |
+
j
|
59 |
+
6
|
60 |
+
8
|
61 |
+
%
|
62 |
+
U
|
63 |
+
►
|
64 |
+
K
|
65 |
+
9
|
66 |
+
V
|
67 |
+
'
|
68 |
+
7
|
69 |
+
X
|
70 |
+
:
|
71 |
+
+
|
72 |
+
J
|
73 |
+
;
|
74 |
+
°
|
75 |
+
Z
|
76 |
+
Q
|
77 |
+
=
|
78 |
+
[
|
79 |
+
]
|
80 |
+
δ
|
81 |
+
∼
|
82 |
+
±
|
83 |
+
ν
|
84 |
+
"
|
85 |
+
>
|
86 |
+
~
|
87 |
+
β
|
88 |
+
Å
|
89 |
+
α
|
90 |
+
×
|
91 |
+
μ
|
92 |
+
≥
|
93 |
+
‰
|
94 |
+
ö
|
95 |
+
Y
|
96 |
+
∞
|
97 |
+
∈
|
98 |
+
é
|
99 |
+
≈
|
100 |
+
·
|
101 |
+
µ
|
102 |
+
≤
|
103 |
+
∨
|
104 |
+
→
|
105 |
+
≲
|
106 |
+
′
|
107 |
+
Ω
|
108 |
+
<
|
109 |
+
⩾
|
110 |
+
⊂
|