File size: 2,926 Bytes
033909d
 
c9cb3b8
 
 
 
 
 
 
033909d
c9cb3b8
4129883
c9cb3b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
---
license: cc-by-nc-sa-4.0
datasets:
- wikipedia
- cc100
language:
- ja
library_name: transformers
pipeline_tag: fill-mask
---

Japanese BERT-base (Vaporetto + WordPiece)
===

## How to load the tokenizer
Please download the dictionary file for Vaporetto + WordPiece from [our GitHub repository](https://github.com/hitachi-nlp/compare-ja-tokenizer/blob/public/data/dict/vaporetto_wordpiece.json).
Then you can load the tokenizer by specifying the path of the dictionary file to `dict_path`.

```python
from typing import Optional

from tokenizers import Tokenizer, NormalizedString, PreTokenizedString
from tokenizers.processors import BertProcessing
from tokenizers.pre_tokenizers import PreTokenizer
from transformers import PreTrainedTokenizerFast

import vaporetto
import textspan

class VaporettoPreTokenizer:
    def __init__(self, unidic_path: str):
        with open(unidic_path, 'rb') as fp:
            model = fp.read()
        self.tokenizer = vaporetto.Vaporetto(model, predict_tags=False)
    
    def tokenize(self, sequence: str) -> list[str]:
        tokens = self.tokenizer.tokenize(sequence)
        return [token.surface() for token in tokens]
    
    def custom_split(self, i: int, normalized_string: NormalizedString) -> list[NormalizedString]:
        text = str(normalized_string)
        tokens = self.tokenize(text)
        tokens_spans = textspan.get_original_spans(tokens, text)
        return [normalized_string[st:ed] for cahr_spans in tokens_spans for st,ed in cahr_spans]
    
    def pre_tokenize(self, pretok: PreTokenizedString):
        pretok.split(self.custom_split)

# load a pre-tokenizer
pre_tokenizer = VaporettoPreTokenizer("/path/to/bccwj-suw+unidic+tag.model.zst")

# load a tokenizer
dict_path = /path/to/vaporetto_wordpiece.json
tokenizer = Tokenizer.from_file(dict_path)
tokenizer.post_processor = BertProcessing(
    cls=("[CLS]", tokenizer.token_to_id('[CLS]')),
    sep=("[SEP]", tokenizer.token_to_id('[SEP]'))
)

# convert to PreTrainedTokenizerFast
tokenizer = PreTrainedTokenizerFast(
    tokenizer_object=tokenizer,
    unk_token='[UNK]',
    cls_token='[CLS]',
    sep_token='[SEP]',
    pad_token='[PAD]',
    mask_token='[MASK]'
)

# set a pre-tokenizer
tokenizer._tokenizer.pre_tokenizer = PreTokenizer.custom(pre_tokenizer)
```

```python
# Test
test_str = "γ“γ‚“γ«γ‘γ―γ€‚η§γ―ε½’ζ…‹η΄ θ§£ζžε™¨γ«γ€γ„γ¦η ”η©Άγ‚’γ—γ¦γ„γΎγ™γ€‚"
tokenizer.convert_ids_to_tokens(tokenizer(test_str).input_ids)
# -> ['[CLS]','こ','##γ‚“','##に','##け','##は','。','私','は','ε½’ζ…‹','η΄ ','解析','器','に','぀い','て','η ”η©Ά','γ‚’','し','て','い','ます','。','[SEP]']
```

## How to load the model
```python
from transformers import AutoModelForMaskedLM
model = AutoModelForMaskedLM.from_pretrained("hitachi-nlp/bert-base_vaporetto-wordpiece")
```


**See [our repository](https://github.com/hitachi-nlp/compare-ja-tokenizer) for more details!**