KoichiYasuoka commited on
Commit
b2eb9a9
1 Parent(s): bfdde8a

model improved

Browse files

Files changed (4) hide show
  1. README.md +1 -1
  2. config.json +101 -91
  3. pytorch_model.bin +2 -2
  4. supar.model +2 -2
README.md CHANGED
@@ -19,7 +19,7 @@ widget:
19
 
20
  ## Model Description
21
 
22
- This is a BERT model pre-trained on Japanese Wikipedia texts for POS-tagging and dependency-parsing, derived from [bert-base-japanese-char-extended](https://huggingface.co/KoichiYasuoka/bert-base-japanese-char-extended). Every long-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
23
 
24
  ## How to Use
25
 
19
 
20
  ## Model Description
21
 
22
+ This is a BERT model pre-trained on Japanese Wikipedia texts for POS-tagging and dependency-parsing, derived from [bert-base-japanese-char-extended](https://huggingface.co/KoichiYasuoka/bert-base-japanese-char-extended). Every long-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
23
 
24
  ## How to Use
25
 
config.json CHANGED
@@ -13,51 +13,56 @@
13
  "1": "ADP",
14
  "2": "ADV",
15
  "3": "AUX",
16
- "4": "B-ADJ",
17
- "5": "B-ADP",
18
- "6": "B-ADV",
19
- "7": "B-AUX",
20
- "8": "B-CCONJ",
21
- "9": "B-DET",
22
- "10": "B-INTJ",
23
- "11": "B-NOUN",
24
- "12": "B-NUM",
25
- "13": "B-PART",
26
- "14": "B-PRON",
27
- "15": "B-PROPN",
28
- "16": "B-PUNCT",
29
- "17": "B-SCONJ",
30
- "18": "B-SYM",
31
- "19": "B-VERB",
32
- "20": "B-X",
33
- "21": "CCONJ",
34
- "22": "I-ADJ",
35
- "23": "I-ADP",
36
- "24": "I-ADV",
37
- "25": "I-AUX",
38
- "26": "I-CCONJ",
39
- "27": "I-DET",
40
- "28": "I-INTJ",
41
- "29": "I-NOUN",
42
- "30": "I-NUM",
43
- "31": "I-PART",
44
- "32": "I-PRON",
45
- "33": "I-PROPN",
46
- "34": "I-PUNCT",
47
- "35": "I-SCONJ",
48
- "36": "I-SYM",
49
- "37": "I-VERB",
50
- "38": "I-X",
51
- "39": "NOUN",
52
- "40": "NUM",
53
- "41": "PART",
54
- "42": "PRON",
55
- "43": "PROPN",
56
- "44": "PUNCT",
57
- "45": "SCONJ",
58
- "46": "SYM",
59
- "47": "VERB",
60
- "48": "X"
 
 
 
 
 
61
  },
62
  "initializer_range": 0.02,
63
  "intermediate_size": 3072,
@@ -66,51 +71,56 @@
66
  "ADP": 1,
67
  "ADV": 2,
68
  "AUX": 3,
69
- "B-ADJ": 4,
70
- "B-ADP": 5,
71
- "B-ADV": 6,
72
- "B-AUX": 7,
73
- "B-CCONJ": 8,
74
- "B-DET": 9,
75
- "B-INTJ": 10,
76
- "B-NOUN": 11,
77
- "B-NUM": 12,
78
- "B-PART": 13,
79
- "B-PRON": 14,
80
- "B-PROPN": 15,
81
- "B-PUNCT": 16,
82
- "B-SCONJ": 17,
83
- "B-SYM": 18,
84
- "B-VERB": 19,
85
- "B-X": 20,
86
- "CCONJ": 21,
87
- "I-ADJ": 22,
88
- "I-ADP": 23,
89
- "I-ADV": 24,
90
- "I-AUX": 25,
91
- "I-CCONJ": 26,
92
- "I-DET": 27,
93
- "I-INTJ": 28,
94
- "I-NOUN": 29,
95
- "I-NUM": 30,
96
- "I-PART": 31,
97
- "I-PRON": 32,
98
- "I-PROPN": 33,
99
- "I-PUNCT": 34,
100
- "I-SCONJ": 35,
101
- "I-SYM": 36,
102
- "I-VERB": 37,
103
- "I-X": 38,
104
- "NOUN": 39,
105
- "NUM": 40,
106
- "PART": 41,
107
- "PRON": 42,
108
- "PROPN": 43,
109
- "PUNCT": 44,
110
- "SCONJ": 45,
111
- "SYM": 46,
112
- "VERB": 47,
113
- "X": 48
 
 
 
 
 
114
  },
115
  "layer_norm_eps": 1e-12,
116
  "max_position_embeddings": 512,
@@ -121,7 +131,7 @@
121
  "position_embedding_type": "absolute",
122
  "tokenizer_class": "BertTokenizer",
123
  "torch_dtype": "float32",
124
- "transformers_version": "4.19.2",
125
  "type_vocab_size": 2,
126
  "use_cache": true,
127
  "vocab_size": 6291
13
  "1": "ADP",
14
  "2": "ADV",
15
  "3": "AUX",
16
+ "4": "AUX|Polarity=Neg",
17
+ "5": "B-ADJ",
18
+ "6": "B-ADP",
19
+ "7": "B-ADV",
20
+ "8": "B-AUX",
21
+ "9": "B-AUX|Polarity=Neg",
22
+ "10": "B-CCONJ",
23
+ "11": "B-DET",
24
+ "12": "B-INTJ",
25
+ "13": "B-NOUN",
26
+ "14": "B-NOUN|Polarity=Neg",
27
+ "15": "B-NUM",
28
+ "16": "B-PART",
29
+ "17": "B-PRON",
30
+ "18": "B-PROPN",
31
+ "19": "B-PUNCT",
32
+ "20": "B-SCONJ",
33
+ "21": "B-SYM",
34
+ "22": "B-VERB",
35
+ "23": "B-X",
36
+ "24": "CCONJ",
37
+ "25": "I-ADJ",
38
+ "26": "I-ADP",
39
+ "27": "I-ADV",
40
+ "28": "I-AUX",
41
+ "29": "I-AUX|Polarity=Neg",
42
+ "30": "I-CCONJ",
43
+ "31": "I-DET",
44
+ "32": "I-INTJ",
45
+ "33": "I-NOUN",
46
+ "34": "I-NOUN|Polarity=Neg",
47
+ "35": "I-NUM",
48
+ "36": "I-PART",
49
+ "37": "I-PRON",
50
+ "38": "I-PROPN",
51
+ "39": "I-PUNCT",
52
+ "40": "I-SCONJ",
53
+ "41": "I-SYM",
54
+ "42": "I-VERB",
55
+ "43": "I-X",
56
+ "44": "NOUN",
57
+ "45": "NUM",
58
+ "46": "PART",
59
+ "47": "PRON",
60
+ "48": "PROPN",
61
+ "49": "PUNCT",
62
+ "50": "SCONJ",
63
+ "51": "SYM",
64
+ "52": "VERB",
65
+ "53": "X"
66
  },
67
  "initializer_range": 0.02,
68
  "intermediate_size": 3072,
71
  "ADP": 1,
72
  "ADV": 2,
73
  "AUX": 3,
74
+ "AUX|Polarity=Neg": 4,
75
+ "B-ADJ": 5,
76
+ "B-ADP": 6,
77
+ "B-ADV": 7,
78
+ "B-AUX": 8,
79
+ "B-AUX|Polarity=Neg": 9,
80
+ "B-CCONJ": 10,
81
+ "B-DET": 11,
82
+ "B-INTJ": 12,
83
+ "B-NOUN": 13,
84
+ "B-NOUN|Polarity=Neg": 14,
85
+ "B-NUM": 15,
86
+ "B-PART": 16,
87
+ "B-PRON": 17,
88
+ "B-PROPN": 18,
89
+ "B-PUNCT": 19,
90
+ "B-SCONJ": 20,
91
+ "B-SYM": 21,
92
+ "B-VERB": 22,
93
+ "B-X": 23,
94
+ "CCONJ": 24,
95
+ "I-ADJ": 25,
96
+ "I-ADP": 26,
97
+ "I-ADV": 27,
98
+ "I-AUX": 28,
99
+ "I-AUX|Polarity=Neg": 29,
100
+ "I-CCONJ": 30,
101
+ "I-DET": 31,
102
+ "I-INTJ": 32,
103
+ "I-NOUN": 33,
104
+ "I-NOUN|Polarity=Neg": 34,
105
+ "I-NUM": 35,
106
+ "I-PART": 36,
107
+ "I-PRON": 37,
108
+ "I-PROPN": 38,
109
+ "I-PUNCT": 39,
110
+ "I-SCONJ": 40,
111
+ "I-SYM": 41,
112
+ "I-VERB": 42,
113
+ "I-X": 43,
114
+ "NOUN": 44,
115
+ "NUM": 45,
116
+ "PART": 46,
117
+ "PRON": 47,
118
+ "PROPN": 48,
119
+ "PUNCT": 49,
120
+ "SCONJ": 50,
121
+ "SYM": 51,
122
+ "VERB": 52,
123
+ "X": 53
124
  },
125
  "layer_norm_eps": 1e-12,
126
  "max_position_embeddings": 512,
131
  "position_embedding_type": "absolute",
132
  "tokenizer_class": "BertTokenizer",
133
  "torch_dtype": "float32",
134
+ "transformers_version": "4.19.4",
135
  "type_vocab_size": 2,
136
  "use_cache": true,
137
  "vocab_size": 6291
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b8258f7c475fca7980396ebbade0cc300f773d94e4f109d2b482fe3344dab49
3
- size 361353229
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333b45f2bcbed40ea7833a98459c4ac31c4bb4dfddf1f9ec1031e36def33e538
3
+ size 361365489
supar.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57617003c4704ff1e4e5ce70a0c7cd20764ff0ef2ebdc8cde125fe355435ccf7
3
- size 411800936
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe62a966dd881e01896d547de7d7aa7cc28db4afbddf894732ea60b4126c0b23
3
+ size 411796901