Commit
•
e1dfa8e
1
Parent(s):
0f0b59f
initial release
Browse files- README.md +47 -0
- config.json +721 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spm.model +3 -0
- supar.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
README.md
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- "ja"
|
| 4 |
+
tags:
|
| 5 |
+
- "japanese"
|
| 6 |
+
- "token-classification"
|
| 7 |
+
- "pos"
|
| 8 |
+
- "dependency-parsing"
|
| 9 |
+
datasets:
|
| 10 |
+
- "universal_dependencies"
|
| 11 |
+
license: "cc-by-sa-4.0"
|
| 12 |
+
pipeline_tag: "token-classification"
|
| 13 |
+
widget:
|
| 14 |
+
- text: "国境の長いトンネルを抜けると雪国であった。"
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# deberta-base-japanese-wikipedia-luw-upos
|
| 18 |
+
|
| 19 |
+
## Model Description
|
| 20 |
+
|
| 21 |
+
This is a DeBERTa(V2) model pre-trained on Japanese Wikipedia and 青空文庫 texts for POS-tagging and dependency-parsing, derived from [deberta-base-japanese-wikipedia](https://huggingface.co/KoichiYasuoka/deberta-base-japanese-wikipedia). Every long-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech).
|
| 22 |
+
|
| 23 |
+
## How to Use
|
| 24 |
+
|
| 25 |
+
```py
|
| 26 |
+
import torch
|
| 27 |
+
from transformers import AutoTokenizer,AutoModelForTokenClassification
|
| 28 |
+
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-base-japanese-wikipedia-luw-upos")
|
| 29 |
+
model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/deberta-base-japanese-wikipedia-luw-upos")
|
| 30 |
+
s="国境の長いトンネルを抜けると雪国であった。"
|
| 31 |
+
t=tokenizer.tokenize(s)
|
| 32 |
+
p=[model.config.id2label[q] for q in torch.argmax(model(tokenizer.encode(s,return_tensors="pt"))["logits"],dim=2)[0].tolist()[1:-1]]
|
| 33 |
+
print(list(zip(t,p)))
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
or
|
| 37 |
+
|
| 38 |
+
```py
|
| 39 |
+
import esupar
|
| 40 |
+
nlp=esupar.load("KoichiYasuoka/deberta-base-japanese-wikipedia-luw-upos")
|
| 41 |
+
print(nlp("国境の長いトンネルを抜けると雪国であった。"))
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
## See Also
|
| 45 |
+
|
| 46 |
+
[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models
|
| 47 |
+
|
config.json
ADDED
|
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "ADJ",
|
| 13 |
+
"1": "ADJ+AUX",
|
| 14 |
+
"2": "ADP",
|
| 15 |
+
"3": "ADV",
|
| 16 |
+
"4": "AUX",
|
| 17 |
+
"5": "AUX+VERB",
|
| 18 |
+
"6": "B-ADJ",
|
| 19 |
+
"7": "B-ADJ+ADJ",
|
| 20 |
+
"8": "B-ADJ+AUX+AUX",
|
| 21 |
+
"9": "B-ADJ+VERB",
|
| 22 |
+
"10": "B-ADP",
|
| 23 |
+
"11": "B-ADP+NOUN",
|
| 24 |
+
"12": "B-ADV",
|
| 25 |
+
"13": "B-ADV+ADP",
|
| 26 |
+
"14": "B-ADV+ADP+VERB",
|
| 27 |
+
"15": "B-AUX",
|
| 28 |
+
"16": "B-AUX+AUX+AUX",
|
| 29 |
+
"17": "B-AUX+AUX+PART",
|
| 30 |
+
"18": "B-AUX+SCONJ",
|
| 31 |
+
"19": "B-AUX+VERB",
|
| 32 |
+
"20": "B-CCONJ",
|
| 33 |
+
"21": "B-DET",
|
| 34 |
+
"22": "B-INTJ",
|
| 35 |
+
"23": "B-NOUN",
|
| 36 |
+
"24": "B-NOUN+ADJ",
|
| 37 |
+
"25": "B-NOUN+ADP",
|
| 38 |
+
"26": "B-NUM",
|
| 39 |
+
"27": "B-PART",
|
| 40 |
+
"28": "B-PRON",
|
| 41 |
+
"29": "B-PROPN",
|
| 42 |
+
"30": "B-PUNCT",
|
| 43 |
+
"31": "B-SCONJ",
|
| 44 |
+
"32": "B-SYM",
|
| 45 |
+
"33": "B-VERB",
|
| 46 |
+
"34": "B-VERB+AUX",
|
| 47 |
+
"35": "B-VERB+AUX+AUX",
|
| 48 |
+
"36": "B-VERB+AUX+NOUN",
|
| 49 |
+
"37": "B-VERB+AUX+PART",
|
| 50 |
+
"38": "B-VERB+AUX+SCONJ",
|
| 51 |
+
"39": "B-X",
|
| 52 |
+
"40": "CCONJ",
|
| 53 |
+
"41": "DET",
|
| 54 |
+
"42": "I-ADJ",
|
| 55 |
+
"43": "I-ADJ+ADJ",
|
| 56 |
+
"44": "I-ADJ+AUX+AUX",
|
| 57 |
+
"45": "I-ADJ+VERB",
|
| 58 |
+
"46": "I-ADP",
|
| 59 |
+
"47": "I-ADP+NOUN",
|
| 60 |
+
"48": "I-ADV",
|
| 61 |
+
"49": "I-ADV+ADP",
|
| 62 |
+
"50": "I-ADV+ADP+VERB",
|
| 63 |
+
"51": "I-AUX",
|
| 64 |
+
"52": "I-AUX+AUX+AUX",
|
| 65 |
+
"53": "I-AUX+AUX+PART",
|
| 66 |
+
"54": "I-AUX+SCONJ",
|
| 67 |
+
"55": "I-AUX+VERB",
|
| 68 |
+
"56": "I-CCONJ",
|
| 69 |
+
"57": "I-DET",
|
| 70 |
+
"58": "I-INTJ",
|
| 71 |
+
"59": "I-NOUN",
|
| 72 |
+
"60": "I-NOUN+ADJ",
|
| 73 |
+
"61": "I-NOUN+ADP",
|
| 74 |
+
"62": "I-NUM",
|
| 75 |
+
"63": "I-PART",
|
| 76 |
+
"64": "I-PRON",
|
| 77 |
+
"65": "I-PROPN",
|
| 78 |
+
"66": "I-PUNCT",
|
| 79 |
+
"67": "I-SCONJ",
|
| 80 |
+
"68": "I-SYM",
|
| 81 |
+
"69": "I-VERB",
|
| 82 |
+
"70": "I-VERB+AUX",
|
| 83 |
+
"71": "I-VERB+AUX+AUX",
|
| 84 |
+
"72": "I-VERB+AUX+NOUN",
|
| 85 |
+
"73": "I-VERB+AUX+PART",
|
| 86 |
+
"74": "I-VERB+AUX+SCONJ",
|
| 87 |
+
"75": "I-X",
|
| 88 |
+
"76": "INTJ",
|
| 89 |
+
"77": "NOUN",
|
| 90 |
+
"78": "NOUN+ADP",
|
| 91 |
+
"79": "NOUN+AUX",
|
| 92 |
+
"80": "NUM",
|
| 93 |
+
"81": "PART",
|
| 94 |
+
"82": "PRON",
|
| 95 |
+
"83": "PRON+ADP",
|
| 96 |
+
"84": "PROPN",
|
| 97 |
+
"85": "PUNCT",
|
| 98 |
+
"86": "SCONJ",
|
| 99 |
+
"87": "SYM",
|
| 100 |
+
"88": "VERB",
|
| 101 |
+
"89": "VERB+AUX",
|
| 102 |
+
"90": "X"
|
| 103 |
+
},
|
| 104 |
+
"initializer_range": 0.02,
|
| 105 |
+
"intermediate_size": 3072,
|
| 106 |
+
"label2id": {
|
| 107 |
+
"ADJ": 0,
|
| 108 |
+
"ADJ+AUX": 1,
|
| 109 |
+
"ADP": 2,
|
| 110 |
+
"ADV": 3,
|
| 111 |
+
"AUX": 4,
|
| 112 |
+
"AUX+VERB": 5,
|
| 113 |
+
"B-ADJ": 6,
|
| 114 |
+
"B-ADJ+ADJ": 7,
|
| 115 |
+
"B-ADJ+AUX+AUX": 8,
|
| 116 |
+
"B-ADJ+VERB": 9,
|
| 117 |
+
"B-ADP": 10,
|
| 118 |
+
"B-ADP+NOUN": 11,
|
| 119 |
+
"B-ADV": 12,
|
| 120 |
+
"B-ADV+ADP": 13,
|
| 121 |
+
"B-ADV+ADP+VERB": 14,
|
| 122 |
+
"B-AUX": 15,
|
| 123 |
+
"B-AUX+AUX+AUX": 16,
|
| 124 |
+
"B-AUX+AUX+PART": 17,
|
| 125 |
+
"B-AUX+SCONJ": 18,
|
| 126 |
+
"B-AUX+VERB": 19,
|
| 127 |
+
"B-CCONJ": 20,
|
| 128 |
+
"B-DET": 21,
|
| 129 |
+
"B-INTJ": 22,
|
| 130 |
+
"B-NOUN": 23,
|
| 131 |
+
"B-NOUN+ADJ": 24,
|
| 132 |
+
"B-NOUN+ADP": 25,
|
| 133 |
+
"B-NUM": 26,
|
| 134 |
+
"B-PART": 27,
|
| 135 |
+
"B-PRON": 28,
|
| 136 |
+
"B-PROPN": 29,
|
| 137 |
+
"B-PUNCT": 30,
|
| 138 |
+
"B-SCONJ": 31,
|
| 139 |
+
"B-SYM": 32,
|
| 140 |
+
"B-VERB": 33,
|
| 141 |
+
"B-VERB+AUX": 34,
|
| 142 |
+
"B-VERB+AUX+AUX": 35,
|
| 143 |
+
"B-VERB+AUX+NOUN": 36,
|
| 144 |
+
"B-VERB+AUX+PART": 37,
|
| 145 |
+
"B-VERB+AUX+SCONJ": 38,
|
| 146 |
+
"B-X": 39,
|
| 147 |
+
"CCONJ": 40,
|
| 148 |
+
"DET": 41,
|
| 149 |
+
"I-ADJ": 42,
|
| 150 |
+
"I-ADJ+ADJ": 43,
|
| 151 |
+
"I-ADJ+AUX+AUX": 44,
|
| 152 |
+
"I-ADJ+VERB": 45,
|
| 153 |
+
"I-ADP": 46,
|
| 154 |
+
"I-ADP+NOUN": 47,
|
| 155 |
+
"I-ADV": 48,
|
| 156 |
+
"I-ADV+ADP": 49,
|
| 157 |
+
"I-ADV+ADP+VERB": 50,
|
| 158 |
+
"I-AUX": 51,
|
| 159 |
+
"I-AUX+AUX+AUX": 52,
|
| 160 |
+
"I-AUX+AUX+PART": 53,
|
| 161 |
+
"I-AUX+SCONJ": 54,
|
| 162 |
+
"I-AUX+VERB": 55,
|
| 163 |
+
"I-CCONJ": 56,
|
| 164 |
+
"I-DET": 57,
|
| 165 |
+
"I-INTJ": 58,
|
| 166 |
+
"I-NOUN": 59,
|
| 167 |
+
"I-NOUN+ADJ": 60,
|
| 168 |
+
"I-NOUN+ADP": 61,
|
| 169 |
+
"I-NUM": 62,
|
| 170 |
+
"I-PART": 63,
|
| 171 |
+
"I-PRON": 64,
|
| 172 |
+
"I-PROPN": 65,
|
| 173 |
+
"I-PUNCT": 66,
|
| 174 |
+
"I-SCONJ": 67,
|
| 175 |
+
"I-SYM": 68,
|
| 176 |
+
"I-VERB": 69,
|
| 177 |
+
"I-VERB+AUX": 70,
|
| 178 |
+
"I-VERB+AUX+AUX": 71,
|
| 179 |
+
"I-VERB+AUX+NOUN": 72,
|
| 180 |
+
"I-VERB+AUX+PART": 73,
|
| 181 |
+
"I-VERB+AUX+SCONJ": 74,
|
| 182 |
+
"I-X": 75,
|
| 183 |
+
"INTJ": 76,
|
| 184 |
+
"NOUN": 77,
|
| 185 |
+
"NOUN+ADP": 78,
|
| 186 |
+
"NOUN+AUX": 79,
|
| 187 |
+
"NUM": 80,
|
| 188 |
+
"PART": 81,
|
| 189 |
+
"PRON": 82,
|
| 190 |
+
"PRON+ADP": 83,
|
| 191 |
+
"PROPN": 84,
|
| 192 |
+
"PUNCT": 85,
|
| 193 |
+
"SCONJ": 86,
|
| 194 |
+
"SYM": 87,
|
| 195 |
+
"VERB": 88,
|
| 196 |
+
"VERB+AUX": 89,
|
| 197 |
+
"X": 90
|
| 198 |
+
},
|
| 199 |
+
"layer_norm_eps": 1e-07,
|
| 200 |
+
"max_position_embeddings": 512,
|
| 201 |
+
"max_relative_positions": -1,
|
| 202 |
+
"model_type": "deberta-v2",
|
| 203 |
+
"num_attention_heads": 12,
|
| 204 |
+
"num_hidden_layers": 12,
|
| 205 |
+
"pad_token_id": 1,
|
| 206 |
+
"pooler_dropout": 0,
|
| 207 |
+
"pooler_hidden_act": "gelu",
|
| 208 |
+
"pooler_hidden_size": 768,
|
| 209 |
+
"pos_att_type": null,
|
| 210 |
+
"position_biased_input": true,
|
| 211 |
+
"relative_attention": false,
|
| 212 |
+
"task_specific_params": {
|
| 213 |
+
"upos_multiword": {
|
| 214 |
+
"ADJ+ADJ": {
|
| 215 |
+
"\u5c11\u306a\u304f\u306a\u3044": [
|
| 216 |
+
"\u5c11\u306a\u304f",
|
| 217 |
+
"\u306a\u3044"
|
| 218 |
+
]
|
| 219 |
+
},
|
| 220 |
+
"ADJ+AUX": {
|
| 221 |
+
"\u679c\u6562\u306a": [
|
| 222 |
+
"\u679c\u6562",
|
| 223 |
+
"\u306a"
|
| 224 |
+
]
|
| 225 |
+
},
|
| 226 |
+
"ADJ+AUX+AUX": {
|
| 227 |
+
"\u591a\u304b\u3063\u305f\u3089\u3057\u304f": [
|
| 228 |
+
"\u591a\u304b\u3063",
|
| 229 |
+
"\u305f",
|
| 230 |
+
"\u3089\u3057\u304f"
|
| 231 |
+
]
|
| 232 |
+
},
|
| 233 |
+
"ADJ+VERB": {
|
| 234 |
+
"\u306a\u304f\u306a\u308b": [
|
| 235 |
+
"\u306a\u304f",
|
| 236 |
+
"\u306a\u308b"
|
| 237 |
+
],
|
| 238 |
+
"\u5c11\u306a\u304f\u306a\u3063": [
|
| 239 |
+
"\u5c11\u306a\u304f",
|
| 240 |
+
"\u306a\u3063"
|
| 241 |
+
]
|
| 242 |
+
},
|
| 243 |
+
"ADP+NOUN": {
|
| 244 |
+
"\u306f\u3057\u3083\u304d\u3057\u3083\u304d\u30ec\u30bf\u30b9": [
|
| 245 |
+
"\u306f",
|
| 246 |
+
"\u3057\u3083\u304d\u3057\u3083\u304d\u30ec\u30bf\u30b9"
|
| 247 |
+
]
|
| 248 |
+
},
|
| 249 |
+
"ADV+ADP": {
|
| 250 |
+
"\u3082\u3061\u3063\u3068": [
|
| 251 |
+
"\u3082\u3061\u3063",
|
| 252 |
+
"\u3068"
|
| 253 |
+
]
|
| 254 |
+
},
|
| 255 |
+
"ADV+ADP+VERB": {
|
| 256 |
+
"\u3082\u3057\u304b\u3057": [
|
| 257 |
+
"\u3082\u3057",
|
| 258 |
+
"\u304b",
|
| 259 |
+
"\u3057"
|
| 260 |
+
]
|
| 261 |
+
},
|
| 262 |
+
"AUX+AUX+AUX": {
|
| 263 |
+
"\u3060\u3063\u305f\u3089\u3057\u3044": [
|
| 264 |
+
"\u3060\u3063",
|
| 265 |
+
"\u305f",
|
| 266 |
+
"\u3089\u3057\u3044"
|
| 267 |
+
],
|
| 268 |
+
"\u3060\u3063\u305f\u3089\u3057\u304f": [
|
| 269 |
+
"\u3060\u3063",
|
| 270 |
+
"\u305f",
|
| 271 |
+
"\u3089\u3057\u304f"
|
| 272 |
+
]
|
| 273 |
+
},
|
| 274 |
+
"AUX+AUX+PART": {
|
| 275 |
+
"\u3066\u3044\u305f\u3060\u3051": [
|
| 276 |
+
"\u3066\u3044",
|
| 277 |
+
"\u305f",
|
| 278 |
+
"\u3060\u3051"
|
| 279 |
+
]
|
| 280 |
+
},
|
| 281 |
+
"AUX+SCONJ": {
|
| 282 |
+
"\u3060\u3051\u3069": [
|
| 283 |
+
"\u3060",
|
| 284 |
+
"\u3051\u3069"
|
| 285 |
+
],
|
| 286 |
+
"\u306e\u3060\u3051\u3069": [
|
| 287 |
+
"\u306e\u3060",
|
| 288 |
+
"\u3051\u3069"
|
| 289 |
+
],
|
| 290 |
+
"\u3093\u3060\u3051\u3069": [
|
| 291 |
+
"\u3093\u3060",
|
| 292 |
+
"\u3051\u3069"
|
| 293 |
+
]
|
| 294 |
+
},
|
| 295 |
+
"AUX+VERB": {
|
| 296 |
+
"\u306a\u304f\u306a\u3063": [
|
| 297 |
+
"\u306a\u304f",
|
| 298 |
+
"\u306a\u3063"
|
| 299 |
+
],
|
| 300 |
+
"\u306a\u304f\u306a\u308a": [
|
| 301 |
+
"\u306a\u304f",
|
| 302 |
+
"\u306a\u308a"
|
| 303 |
+
],
|
| 304 |
+
"\u306a\u304f\u306a\u308b": [
|
| 305 |
+
"\u306a\u304f",
|
| 306 |
+
"\u306a\u308b"
|
| 307 |
+
]
|
| 308 |
+
},
|
| 309 |
+
"NOUN+ADJ": {
|
| 310 |
+
"\u60aa\u540d\u9ad8\u3044": [
|
| 311 |
+
"\u60aa\u540d",
|
| 312 |
+
"\u9ad8\u3044"
|
| 313 |
+
]
|
| 314 |
+
},
|
| 315 |
+
"NOUN+ADP": {
|
| 316 |
+
"\u3072\u3068\u308a\u3067": [
|
| 317 |
+
"\u3072\u3068\u308a",
|
| 318 |
+
"\u3067"
|
| 319 |
+
],
|
| 320 |
+
"\u4ee3\u8d70\u904b\u8ee2\u304c": [
|
| 321 |
+
"\u4ee3\u8d70\u904b\u8ee2",
|
| 322 |
+
"\u304c"
|
| 323 |
+
],
|
| 324 |
+
"\u4f7f\u7528\u958b\u59cb\u307e\u3067": [
|
| 325 |
+
"\u4f7f\u7528\u958b\u59cb",
|
| 326 |
+
"\u307e\u3067"
|
| 327 |
+
],
|
| 328 |
+
"\u516c\u8ee2\u304c": [
|
| 329 |
+
"\u516c\u8ee2",
|
| 330 |
+
"\u304c"
|
| 331 |
+
],
|
| 332 |
+
"\u5171\u98df\u3044\u3082": [
|
| 333 |
+
"\u5171\u98df\u3044",
|
| 334 |
+
"\u3082"
|
| 335 |
+
],
|
| 336 |
+
"\u9152\u6c17\u5e2f\u3073\u904b\u8ee2\u304c": [
|
| 337 |
+
"\u9152\u6c17\u5e2f\u3073\u904b\u8ee2",
|
| 338 |
+
"\u304c"
|
| 339 |
+
]
|
| 340 |
+
},
|
| 341 |
+
"NOUN+AUX": {
|
| 342 |
+
"\u3072\u3068\u308a\u3067": [
|
| 343 |
+
"\u3072\u3068\u308a",
|
| 344 |
+
"\u3067"
|
| 345 |
+
],
|
| 346 |
+
"\u601d\u3044\u3060": [
|
| 347 |
+
"\u601d\u3044",
|
| 348 |
+
"\u3060"
|
| 349 |
+
]
|
| 350 |
+
},
|
| 351 |
+
"PRON+ADP": {
|
| 352 |
+
"\u306a\u3093\u304b": [
|
| 353 |
+
"\u306a\u3093",
|
| 354 |
+
"\u304b"
|
| 355 |
+
]
|
| 356 |
+
},
|
| 357 |
+
"VERB+AUX": {
|
| 358 |
+
"\u3044\u308f\u308c": [
|
| 359 |
+
"\u3044\u308f",
|
| 360 |
+
"\u308c"
|
| 361 |
+
],
|
| 362 |
+
"\u3044\u308f\u308c\u308b": [
|
| 363 |
+
"\u3044\u308f",
|
| 364 |
+
"\u308c\u308b"
|
| 365 |
+
],
|
| 366 |
+
"\u304a\u3053\u306a\u308f\u308c": [
|
| 367 |
+
"\u304a\u3053\u306a\u308f",
|
| 368 |
+
"\u308c"
|
| 369 |
+
],
|
| 370 |
+
"\u304b\u307e\u308f\u305a": [
|
| 371 |
+
"\u304b\u307e\u308f",
|
| 372 |
+
"\u305a"
|
| 373 |
+
],
|
| 374 |
+
"\u3055\u3089\u308f\u308c": [
|
| 375 |
+
"\u3055\u3089\u308f",
|
| 376 |
+
"\u308c"
|
| 377 |
+
],
|
| 378 |
+
"\u3057\u3053\u307e\u305b": [
|
| 379 |
+
"\u3057\u3053\u307e",
|
| 380 |
+
"\u305b"
|
| 381 |
+
],
|
| 382 |
+
"\u3059\u3079\u304d": [
|
| 383 |
+
"\u3059",
|
| 384 |
+
"\u3079\u304d"
|
| 385 |
+
],
|
| 386 |
+
"\u306a\u3055\u308c": [
|
| 387 |
+
"\u306a\u3055",
|
| 388 |
+
"\u308c"
|
| 389 |
+
],
|
| 390 |
+
"\u306a\u3055\u308c\u308b": [
|
| 391 |
+
"\u306a\u3055",
|
| 392 |
+
"\u308c\u308b"
|
| 393 |
+
],
|
| 394 |
+
"\u306a\u3058\u307e\u305b": [
|
| 395 |
+
"\u306a\u3058\u307e",
|
| 396 |
+
"\u305b"
|
| 397 |
+
],
|
| 398 |
+
"\u306a\u3089\u305a": [
|
| 399 |
+
"\u306a\u3089",
|
| 400 |
+
"\u305a"
|
| 401 |
+
],
|
| 402 |
+
"\u307f\u306a\u3055\u308c": [
|
| 403 |
+
"\u307f\u306a\u3055",
|
| 404 |
+
"\u308c"
|
| 405 |
+
],
|
| 406 |
+
"\u30c1\u30a7\u30c3\u30af\u3059\u3079\u304f": [
|
| 407 |
+
"\u30c1\u30a7\u30c3\u30af\u3059",
|
| 408 |
+
"\u3079\u304f"
|
| 409 |
+
],
|
| 410 |
+
"\u30e4\u30e9\u30ec": [
|
| 411 |
+
"\u30e4\u30e9",
|
| 412 |
+
"\u30ec"
|
| 413 |
+
],
|
| 414 |
+
"\u4e0b\u3055\u308c\u308b": [
|
| 415 |
+
"\u4e0b\u3055",
|
| 416 |
+
"\u308c\u308b"
|
| 417 |
+
],
|
| 418 |
+
"\u4ecb\u5165\u3059\u3079\u3057": [
|
| 419 |
+
"\u4ecb\u5165\u3059",
|
| 420 |
+
"\u3079\u3057"
|
| 421 |
+
],
|
| 422 |
+
"\u4ed5\u821e\u308f\u308c": [
|
| 423 |
+
"\u4ed5\u821e\u308f",
|
| 424 |
+
"\u308c"
|
| 425 |
+
],
|
| 426 |
+
"\u4f11\u307e\u305b": [
|
| 427 |
+
"\u4f11\u307e",
|
| 428 |
+
"\u305b"
|
| 429 |
+
],
|
| 430 |
+
"\u4f34\u308f\u308c": [
|
| 431 |
+
"\u4f34\u308f",
|
| 432 |
+
"\u308c"
|
| 433 |
+
],
|
| 434 |
+
"\u5145\u5f53\u3059\u3079\u304f": [
|
| 435 |
+
"\u5145\u5f53\u3059",
|
| 436 |
+
"\u3079\u304f"
|
| 437 |
+
],
|
| 438 |
+
"\u5165\u3063\u3061\u3083\u3044": [
|
| 439 |
+
"\u5165\u3063",
|
| 440 |
+
"\u3061\u3083\u3044"
|
| 441 |
+
],
|
| 442 |
+
"\u52d5\u304b\u305b": [
|
| 443 |
+
"\u52d5\u304b",
|
| 444 |
+
"\u305b"
|
| 445 |
+
],
|
| 446 |
+
"\u533f\u308f\u308c": [
|
| 447 |
+
"\u533f\u308f",
|
| 448 |
+
"\u308c"
|
| 449 |
+
],
|
| 450 |
+
"\u542b\u307e\u305b": [
|
| 451 |
+
"\u542b\u307e",
|
| 452 |
+
"\u305b"
|
| 453 |
+
],
|
| 454 |
+
"\u548c\u307e\u305b": [
|
| 455 |
+
"\u548c\u307e",
|
| 456 |
+
"\u305b"
|
| 457 |
+
],
|
| 458 |
+
"\u554f\u308f\u305a": [
|
| 459 |
+
"\u554f\u308f",
|
| 460 |
+
"\u305a"
|
| 461 |
+
],
|
| 462 |
+
"\u554f\u308f\u308c": [
|
| 463 |
+
"\u554f\u308f",
|
| 464 |
+
"\u308c"
|
| 465 |
+
],
|
| 466 |
+
"\u554f\u308f\u308c\u308b": [
|
| 467 |
+
"\u554f\u308f",
|
| 468 |
+
"\u308c\u308b"
|
| 469 |
+
],
|
| 470 |
+
"\u596a\u308f\u308c": [
|
| 471 |
+
"\u596a\u308f",
|
| 472 |
+
"\u308c"
|
| 473 |
+
],
|
| 474 |
+
"\u596a\u308f\u308c\u308b": [
|
| 475 |
+
"\u596a\u308f",
|
| 476 |
+
"\u308c\u308b"
|
| 477 |
+
],
|
| 478 |
+
"\u5acc\u308f\u308c": [
|
| 479 |
+
"\u5acc\u308f",
|
| 480 |
+
"\u308c"
|
| 481 |
+
],
|
| 482 |
+
"\u601d\u3063\u3061\u3083\u3044": [
|
| 483 |
+
"\u601d\u3063",
|
| 484 |
+
"\u3061\u3083\u3044"
|
| 485 |
+
],
|
| 486 |
+
"\u601d\u3063\u3061\u3083\u3046": [
|
| 487 |
+
"\u601d\u3063",
|
| 488 |
+
"\u3061\u3083\u3046"
|
| 489 |
+
],
|
| 490 |
+
"\u60a9\u307e\u305b": [
|
| 491 |
+
"\u60a9\u307e",
|
| 492 |
+
"\u305b"
|
| 493 |
+
],
|
| 494 |
+
"\u60a9\u307e\u305b\u308b": [
|
| 495 |
+
"\u60a9\u307e",
|
| 496 |
+
"\u305b\u308b"
|
| 497 |
+
],
|
| 498 |
+
"\u6271\u308f\u308c": [
|
| 499 |
+
"\u6271\u308f",
|
| 500 |
+
"\u308c"
|
| 501 |
+
],
|
| 502 |
+
"\u6271\u308f\u308c\u308b": [
|
| 503 |
+
"\u6271\u308f",
|
| 504 |
+
"\u308c\u308b"
|
| 505 |
+
],
|
| 506 |
+
"\u6279\u5224\u3059\u3079\u304d": [
|
| 507 |
+
"\u6279\u5224\u3059",
|
| 508 |
+
"\u3079\u304d"
|
| 509 |
+
],
|
| 510 |
+
"\u6392\u9664\u3059\u3079\u304d": [
|
| 511 |
+
"\u6392\u9664\u3059",
|
| 512 |
+
"\u3079\u304d"
|
| 513 |
+
],
|
| 514 |
+
"\u6458\u767a\u3059\u3079\u304d": [
|
| 515 |
+
"\u6458\u767a\u3059",
|
| 516 |
+
"\u3079\u304d"
|
| 517 |
+
],
|
| 518 |
+
"\u6551\u308f\u308c\u308b": [
|
| 519 |
+
"\u6551\u308f",
|
| 520 |
+
"\u308c\u308b"
|
| 521 |
+
],
|
| 522 |
+
"\u66ae\u3089\u3059\u3079\u304d": [
|
| 523 |
+
"\u66ae\u3089\u3059",
|
| 524 |
+
"\u3079\u304d"
|
| 525 |
+
],
|
| 526 |
+
"\u679c\u305f\u3059\u3079\u304f": [
|
| 527 |
+
"\u679c\u305f\u3059",
|
| 528 |
+
"\u3079\u304f"
|
| 529 |
+
],
|
| 530 |
+
"\u69cb\u308f\u305a": [
|
| 531 |
+
"\u69cb\u308f",
|
| 532 |
+
"\u305a"
|
| 533 |
+
],
|
| 534 |
+
"\u6b4c\u308f\u308c": [
|
| 535 |
+
"\u6b4c\u308f",
|
| 536 |
+
"\u308c"
|
| 537 |
+
],
|
| 538 |
+
"\u6b6a\u307e\u305b\u308b": [
|
| 539 |
+
"\u6b6a\u307e",
|
| 540 |
+
"\u305b\u308b"
|
| 541 |
+
],
|
| 542 |
+
"\u6e08\u307e\u305b": [
|
| 543 |
+
"\u6e08\u307e",
|
| 544 |
+
"\u305b"
|
| 545 |
+
],
|
| 546 |
+
"\u72d9\u308f\u308c": [
|
| 547 |
+
"\u72d9\u308f",
|
| 548 |
+
"\u308c"
|
| 549 |
+
],
|
| 550 |
+
"\u751f\u304b\u3059\u3079\u304f": [
|
| 551 |
+
"\u751f\u304b\u3059",
|
| 552 |
+
"\u3079\u304f"
|
| 553 |
+
],
|
| 554 |
+
"\u77e5\u3089\u305b": [
|
| 555 |
+
"\u77e5\u3089",
|
| 556 |
+
"\u305b"
|
| 557 |
+
],
|
| 558 |
+
"\u77e5\u3089\u305b\u308b": [
|
| 559 |
+
"\u77e5\u3089",
|
| 560 |
+
"\u305b\u308b"
|
| 561 |
+
],
|
| 562 |
+
"\u7d42\u308f\u3063\u3061\u3083\u3046": [
|
| 563 |
+
"\u7d42\u308f\u3063",
|
| 564 |
+
"\u3061\u3083\u3046"
|
| 565 |
+
],
|
| 566 |
+
"\u7d71\u4e00\u3059\u3079\u304f": [
|
| 567 |
+
"\u7d71\u4e00\u3059",
|
| 568 |
+
"\u3079\u304f"
|
| 569 |
+
],
|
| 570 |
+
"\u884c\u3063\u3061\u3083\u3044": [
|
| 571 |
+
"\u884c\u3063",
|
| 572 |
+
"\u3061\u3083\u3044"
|
| 573 |
+
],
|
| 574 |
+
"\u884c\u308f\u305a": [
|
| 575 |
+
"\u884c\u308f",
|
| 576 |
+
"\u305a"
|
| 577 |
+
],
|
| 578 |
+
"\u884c\u308f\u308c": [
|
| 579 |
+
"\u884c\u308f",
|
| 580 |
+
"\u308c"
|
| 581 |
+
],
|
| 582 |
+
"\u884c\u308f\u308c\u308b": [
|
| 583 |
+
"\u884c\u308f",
|
| 584 |
+
"\u308c\u308b"
|
| 585 |
+
],
|
| 586 |
+
"\u88ab\u308f\u308c\u308b": [
|
| 587 |
+
"\u88ab\u308f",
|
| 588 |
+
"\u308c\u308b"
|
| 589 |
+
],
|
| 590 |
+
"\u8972\u308f\u308c": [
|
| 591 |
+
"\u8972\u308f",
|
| 592 |
+
"\u308c"
|
| 593 |
+
],
|
| 594 |
+
"\u8986\u308f\u308c": [
|
| 595 |
+
"\u8986\u308f",
|
| 596 |
+
"\u308c"
|
| 597 |
+
],
|
| 598 |
+
"\u898b\u306a\u3055\u308c": [
|
| 599 |
+
"\u898b\u306a\u3055",
|
| 600 |
+
"\u308c"
|
| 601 |
+
],
|
| 602 |
+
"\u898b\u821e\u308f\u308c": [
|
| 603 |
+
"\u898b\u821e\u308f",
|
| 604 |
+
"\u308c"
|
| 605 |
+
],
|
| 606 |
+
"\u89e3\u304d\u660e\u304b\u3059\u3079\u304d": [
|
| 607 |
+
"\u89e3\u304d\u660e\u304b\u3059",
|
| 608 |
+
"\u3079\u304d"
|
| 609 |
+
],
|
| 610 |
+
"\u8a60\u308f\u308c": [
|
| 611 |
+
"\u8a60\u308f",
|
| 612 |
+
"\u308c"
|
| 613 |
+
],
|
| 614 |
+
"\u8a98\u308f\u308c": [
|
| 615 |
+
"\u8a98\u308f",
|
| 616 |
+
"\u308c"
|
| 617 |
+
],
|
| 618 |
+
"\u8aac\u660e\u3059\u3079\u304d": [
|
| 619 |
+
"\u8aac\u660e\u3059",
|
| 620 |
+
"\u3079\u304d"
|
| 621 |
+
],
|
| 622 |
+
"\u8cb7\u3063\u3061\u3083\u3044": [
|
| 623 |
+
"\u8cb7\u3063",
|
| 624 |
+
"\u3061\u3083\u3044"
|
| 625 |
+
],
|
| 626 |
+
"\u8e0f\u307e\u305b": [
|
| 627 |
+
"\u8e0f\u307e",
|
| 628 |
+
"\u305b"
|
| 629 |
+
],
|
| 630 |
+
"\u8f9e\u8077\u3059\u3079\u304d": [
|
| 631 |
+
"\u8f9e\u8077\u3059",
|
| 632 |
+
"\u3079\u304d"
|
| 633 |
+
],
|
| 634 |
+
"\u990a\u308f\u308c\u308b": [
|
| 635 |
+
"\u990a\u308f",
|
| 636 |
+
"\u308c\u308b"
|
| 637 |
+
],
|
| 638 |
+
"\u9cf4\u3089\u3059\u3079\u304f": [
|
| 639 |
+
"\u9cf4\u3089\u3059",
|
| 640 |
+
"\u3079\u304f"
|
| 641 |
+
]
|
| 642 |
+
},
|
| 643 |
+
"VERB+AUX+AUX": {
|
| 644 |
+
"\u306a\u3063\u305f\u3089\u3057\u3044": [
|
| 645 |
+
"\u306a\u3063",
|
| 646 |
+
"\u305f",
|
| 647 |
+
"\u3089\u3057\u3044"
|
| 648 |
+
],
|
| 649 |
+
"\u601d\u3063\u305f\u3089\u3057\u304f": [
|
| 650 |
+
"\u601d\u3063",
|
| 651 |
+
"\u305f",
|
| 652 |
+
"\u3089\u3057\u304f"
|
| 653 |
+
],
|
| 654 |
+
"\u8cb7\u3063\u305f\u3089\u3057\u304f": [
|
| 655 |
+
"\u8cb7\u3063",
|
| 656 |
+
"\u305f",
|
| 657 |
+
"\u3089\u3057\u304f"
|
| 658 |
+
]
|
| 659 |
+
},
|
| 660 |
+
"VERB+AUX+NOUN": {
|
| 661 |
+
"\u5909\u66f4\u3057\u305f\u305f\u3081": [
|
| 662 |
+
"\u5909\u66f4\u3057",
|
| 663 |
+
"\u305f",
|
| 664 |
+
"\u305f\u3081"
|
| 665 |
+
],
|
| 666 |
+
"\u5931\u6557\u3057\u305f\u305f\u3081": [
|
| 667 |
+
"\u5931\u6557\u3057",
|
| 668 |
+
"\u305f",
|
| 669 |
+
"\u305f\u3081"
|
| 670 |
+
],
|
| 671 |
+
"\u5bfe\u7acb\u3057\u305f\u305f\u3081": [
|
| 672 |
+
"\u5bfe\u7acb\u3057",
|
| 673 |
+
"\u305f",
|
| 674 |
+
"\u305f\u3081"
|
| 675 |
+
],
|
| 676 |
+
"\u6f5c\u5165\u3057\u305f\u305f\u3081": [
|
| 677 |
+
"\u6f5c\u5165\u3057",
|
| 678 |
+
"\u305f",
|
| 679 |
+
"\u305f\u3081"
|
| 680 |
+
],
|
| 681 |
+
"\u8131\u8d70\u3057\u305f\u305f\u3081": [
|
| 682 |
+
"\u8131\u8d70\u3057",
|
| 683 |
+
"\u305f",
|
| 684 |
+
"\u305f\u3081"
|
| 685 |
+
],
|
| 686 |
+
"\u8868\u660e\u3057\u305f\u305f\u3081": [
|
| 687 |
+
"\u8868\u660e\u3057",
|
| 688 |
+
"\u305f",
|
| 689 |
+
"\u305f\u3081"
|
| 690 |
+
],
|
| 691 |
+
"\u8981\u8acb\u3057\u305f\u305f\u3081": [
|
| 692 |
+
"\u8981\u8acb\u3057",
|
| 693 |
+
"\u305f",
|
| 694 |
+
"\u305f\u3081"
|
| 695 |
+
]
|
| 696 |
+
},
|
| 697 |
+
"VERB+AUX+SCONJ": {
|
| 698 |
+
"\u592d\u6298\u3057\u305f\u305f\u3081\u306b": [
|
| 699 |
+
"\u592d\u6298\u3057",
|
| 700 |
+
"\u305f",
|
| 701 |
+
"\u305f\u3081\u306b"
|
| 702 |
+
],
|
| 703 |
+
"\u5fb4\u767a\u3057\u305f\u305f\u3081\u306b": [
|
| 704 |
+
"\u5fb4\u767a\u3057",
|
| 705 |
+
"\u305f",
|
| 706 |
+
"\u305f\u3081\u306b"
|
| 707 |
+
],
|
| 708 |
+
"\u62d2\u5426\u3057\u305f\u305f\u3081\u306b": [
|
| 709 |
+
"\u62d2\u5426\u3057",
|
| 710 |
+
"\u305f",
|
| 711 |
+
"\u305f\u3081\u306b"
|
| 712 |
+
]
|
| 713 |
+
}
|
| 714 |
+
}
|
| 715 |
+
},
|
| 716 |
+
"tokenizer_class": "DebertaV2TokenizerFast",
|
| 717 |
+
"torch_dtype": "float32",
|
| 718 |
+
"transformers_version": "4.19.4",
|
| 719 |
+
"type_vocab_size": 0,
|
| 720 |
+
"vocab_size": 32000
|
| 721 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d9dc283f344a5962ffc3d73145d7d13aa93061dcffa80c204ca9cda53170536
|
| 3 |
+
size 440451827
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01ba4719c80b6fe911b091a7c05124b64eeece964e09c058ef8f9805daca546b
|
| 3 |
+
size 1
|
supar.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1418fb8011870c9767cd696aae417a242fa43f12873d299f49a93550c091b56d
|
| 3 |
+
size 488951787
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": true, "keep_accents": true, "model_max_length": 512, "tokenizer_class": "DebertaV2TokenizerFast"}
|