KoichiYasuoka commited on
Commit
7b8a887
1 Parent(s): 3ec6bd7

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 +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ widget:
18
 
19
  ## Model Description
20
 
21
- This is a RoBERTa model pre-trained on 青空文庫 texts for POS-tagging and dependency-parsing, derived from [roberta-large-japanese-aozora-char](https://huggingface.co/KoichiYasuoka/roberta-large-japanese-aozora-char). Every long-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
22
 
23
  ## How to Use
24
 
 
18
 
19
  ## Model Description
20
 
21
+ This is a RoBERTa model pre-trained on 青空文庫 texts for POS-tagging and dependency-parsing, derived from [roberta-large-japanese-aozora-char](https://huggingface.co/KoichiYasuoka/roberta-large-japanese-aozora-char). Every long-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
22
 
23
  ## How to Use
24
 
config.json CHANGED
@@ -14,51 +14,56 @@
14
  "1": "ADP",
15
  "2": "ADV",
16
  "3": "AUX",
17
- "4": "B-ADJ",
18
- "5": "B-ADP",
19
- "6": "B-ADV",
20
- "7": "B-AUX",
21
- "8": "B-CCONJ",
22
- "9": "B-DET",
23
- "10": "B-INTJ",
24
- "11": "B-NOUN",
25
- "12": "B-NUM",
26
- "13": "B-PART",
27
- "14": "B-PRON",
28
- "15": "B-PROPN",
29
- "16": "B-PUNCT",
30
- "17": "B-SCONJ",
31
- "18": "B-SYM",
32
- "19": "B-VERB",
33
- "20": "B-X",
34
- "21": "CCONJ",
35
- "22": "I-ADJ",
36
- "23": "I-ADP",
37
- "24": "I-ADV",
38
- "25": "I-AUX",
39
- "26": "I-CCONJ",
40
- "27": "I-DET",
41
- "28": "I-INTJ",
42
- "29": "I-NOUN",
43
- "30": "I-NUM",
44
- "31": "I-PART",
45
- "32": "I-PRON",
46
- "33": "I-PROPN",
47
- "34": "I-PUNCT",
48
- "35": "I-SCONJ",
49
- "36": "I-SYM",
50
- "37": "I-VERB",
51
- "38": "I-X",
52
- "39": "NOUN",
53
- "40": "NUM",
54
- "41": "PART",
55
- "42": "PRON",
56
- "43": "PROPN",
57
- "44": "PUNCT",
58
- "45": "SCONJ",
59
- "46": "SYM",
60
- "47": "VERB",
61
- "48": "X"
 
 
 
 
 
62
  },
63
  "initializer_range": 0.02,
64
  "intermediate_size": 4096,
@@ -67,51 +72,56 @@
67
  "ADP": 1,
68
  "ADV": 2,
69
  "AUX": 3,
70
- "B-ADJ": 4,
71
- "B-ADP": 5,
72
- "B-ADV": 6,
73
- "B-AUX": 7,
74
- "B-CCONJ": 8,
75
- "B-DET": 9,
76
- "B-INTJ": 10,
77
- "B-NOUN": 11,
78
- "B-NUM": 12,
79
- "B-PART": 13,
80
- "B-PRON": 14,
81
- "B-PROPN": 15,
82
- "B-PUNCT": 16,
83
- "B-SCONJ": 17,
84
- "B-SYM": 18,
85
- "B-VERB": 19,
86
- "B-X": 20,
87
- "CCONJ": 21,
88
- "I-ADJ": 22,
89
- "I-ADP": 23,
90
- "I-ADV": 24,
91
- "I-AUX": 25,
92
- "I-CCONJ": 26,
93
- "I-DET": 27,
94
- "I-INTJ": 28,
95
- "I-NOUN": 29,
96
- "I-NUM": 30,
97
- "I-PART": 31,
98
- "I-PRON": 32,
99
- "I-PROPN": 33,
100
- "I-PUNCT": 34,
101
- "I-SCONJ": 35,
102
- "I-SYM": 36,
103
- "I-VERB": 37,
104
- "I-X": 38,
105
- "NOUN": 39,
106
- "NUM": 40,
107
- "PART": 41,
108
- "PRON": 42,
109
- "PROPN": 43,
110
- "PUNCT": 44,
111
- "SCONJ": 45,
112
- "SYM": 46,
113
- "VERB": 47,
114
- "X": 48
 
 
 
 
 
115
  },
116
  "layer_norm_eps": 1e-12,
117
  "max_position_embeddings": 512,
@@ -122,7 +132,7 @@
122
  "position_embedding_type": "absolute",
123
  "tokenizer_class": "BertTokenizerFast",
124
  "torch_dtype": "float32",
125
- "transformers_version": "4.19.2",
126
  "type_vocab_size": 2,
127
  "use_cache": true,
128
  "vocab_size": 9415
 
14
  "1": "ADP",
15
  "2": "ADV",
16
  "3": "AUX",
17
+ "4": "AUX|Polarity=Neg",
18
+ "5": "B-ADJ",
19
+ "6": "B-ADP",
20
+ "7": "B-ADV",
21
+ "8": "B-AUX",
22
+ "9": "B-AUX|Polarity=Neg",
23
+ "10": "B-CCONJ",
24
+ "11": "B-DET",
25
+ "12": "B-INTJ",
26
+ "13": "B-NOUN",
27
+ "14": "B-NOUN|Polarity=Neg",
28
+ "15": "B-NUM",
29
+ "16": "B-PART",
30
+ "17": "B-PRON",
31
+ "18": "B-PROPN",
32
+ "19": "B-PUNCT",
33
+ "20": "B-SCONJ",
34
+ "21": "B-SYM",
35
+ "22": "B-VERB",
36
+ "23": "B-X",
37
+ "24": "CCONJ",
38
+ "25": "I-ADJ",
39
+ "26": "I-ADP",
40
+ "27": "I-ADV",
41
+ "28": "I-AUX",
42
+ "29": "I-AUX|Polarity=Neg",
43
+ "30": "I-CCONJ",
44
+ "31": "I-DET",
45
+ "32": "I-INTJ",
46
+ "33": "I-NOUN",
47
+ "34": "I-NOUN|Polarity=Neg",
48
+ "35": "I-NUM",
49
+ "36": "I-PART",
50
+ "37": "I-PRON",
51
+ "38": "I-PROPN",
52
+ "39": "I-PUNCT",
53
+ "40": "I-SCONJ",
54
+ "41": "I-SYM",
55
+ "42": "I-VERB",
56
+ "43": "I-X",
57
+ "44": "NOUN",
58
+ "45": "NUM",
59
+ "46": "PART",
60
+ "47": "PRON",
61
+ "48": "PROPN",
62
+ "49": "PUNCT",
63
+ "50": "SCONJ",
64
+ "51": "SYM",
65
+ "52": "VERB",
66
+ "53": "X"
67
  },
68
  "initializer_range": 0.02,
69
  "intermediate_size": 4096,
 
72
  "ADP": 1,
73
  "ADV": 2,
74
  "AUX": 3,
75
+ "AUX|Polarity=Neg": 4,
76
+ "B-ADJ": 5,
77
+ "B-ADP": 6,
78
+ "B-ADV": 7,
79
+ "B-AUX": 8,
80
+ "B-AUX|Polarity=Neg": 9,
81
+ "B-CCONJ": 10,
82
+ "B-DET": 11,
83
+ "B-INTJ": 12,
84
+ "B-NOUN": 13,
85
+ "B-NOUN|Polarity=Neg": 14,
86
+ "B-NUM": 15,
87
+ "B-PART": 16,
88
+ "B-PRON": 17,
89
+ "B-PROPN": 18,
90
+ "B-PUNCT": 19,
91
+ "B-SCONJ": 20,
92
+ "B-SYM": 21,
93
+ "B-VERB": 22,
94
+ "B-X": 23,
95
+ "CCONJ": 24,
96
+ "I-ADJ": 25,
97
+ "I-ADP": 26,
98
+ "I-ADV": 27,
99
+ "I-AUX": 28,
100
+ "I-AUX|Polarity=Neg": 29,
101
+ "I-CCONJ": 30,
102
+ "I-DET": 31,
103
+ "I-INTJ": 32,
104
+ "I-NOUN": 33,
105
+ "I-NOUN|Polarity=Neg": 34,
106
+ "I-NUM": 35,
107
+ "I-PART": 36,
108
+ "I-PRON": 37,
109
+ "I-PROPN": 38,
110
+ "I-PUNCT": 39,
111
+ "I-SCONJ": 40,
112
+ "I-SYM": 41,
113
+ "I-VERB": 42,
114
+ "I-X": 43,
115
+ "NOUN": 44,
116
+ "NUM": 45,
117
+ "PART": 46,
118
+ "PRON": 47,
119
+ "PROPN": 48,
120
+ "PUNCT": 49,
121
+ "SCONJ": 50,
122
+ "SYM": 51,
123
+ "VERB": 52,
124
+ "X": 53
125
  },
126
  "layer_norm_eps": 1e-12,
127
  "max_position_embeddings": 512,
 
132
  "position_embedding_type": "absolute",
133
  "tokenizer_class": "BertTokenizerFast",
134
  "torch_dtype": "float32",
135
+ "transformers_version": "4.19.4",
136
  "type_vocab_size": 2,
137
  "use_cache": true,
138
  "vocab_size": 9415
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72a82baa53d0f94a7ae47b5933238aa15c369913006dc75dedec8e75c55bb7c8
3
- size 1250252273
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:911288f97fd8d0fa06db921b0bdece8f8e0e1cbdfb2df65a272dd52f4ec60c9a
3
+ size 1250272753
supar.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:836d88dbb4f11fd2abfe580f94809b656a335f544a17ca15ba4ef6107577240d
3
  size 1302635621
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:150e7c1aeb6e7592b846af918df900394817f1e17d5eebd6e3b5792aa68fc14a
3
  size 1302635621