pytorch - 标记器解码步骤中的标记到单词映射拥抱面？

Question

有没有办法知道从 token 到 tokenizer.decode() 中的原始单词的映射？功能？
例如:

from transformers.tokenization_roberta import RobertaTokenizer

tokenizer = RobertaTokenizer.from_pretrained('roberta-large', do_lower_case=True)

str = "This is a tokenization example"
tokenized = tokenizer.tokenize(str) 
## ['this', 'Ġis', 'Ġa', 'Ġtoken', 'ization', 'Ġexample']

encoded = tokenizer.encode_plus(str) 
## encoded['input_ids']=[0, 42, 16, 10, 19233, 1938, 1246, 2]

decoded = tokenizer.decode(encoded['input_ids']) 
## '<s> this is a tokenization example</s>'

目标是有一个函数来映射 decode 中的每个标记。处理正确的输入词，因为这里将是: desired_output = [[1],[2],[3],[4,5],[6]]如 this对应 id 42 , 而 token和 ization对应于 ID [19244,1938]位于索引 4,5的 input_ids大批。

Answer 1

据我所知，他们没有内置的方法，但你可以自己创建一个:

from transformers.tokenization_roberta import RobertaTokenizer

tokenizer = RobertaTokenizer.from_pretrained('roberta-large', do_lower_case=True)

example = "This is a tokenization example"

print({x : tokenizer.encode(x, add_special_tokens=False, add_prefix_space=True) for x in example.split()})

输出:

{'This': [42], 'is': [16], 'a': [10], 'tokenization': [19233, 1938], 'example': [1246]}

要准确获得所需的输出，您必须使用列表理解:

#start index because the number of special tokens is fixed for each model (but be aware of single sentence input and pairwise sentence input)
idx = 1

enc =[tokenizer.encode(x, add_special_tokens=False, add_prefix_space=True) for x in example.split()]

desired_output = []

for token in enc:
    tokenoutput = []
    for ids in token:
      tokenoutput.append(idx)
      idx +=1
    desired_output.append(tokenoutput)

print(desired_output)

输出:

[[1], [2], [3], [4, 5], [6]]