在tokenizer.decode()
函数中是否有办法知道从令牌到原始单词的映射?
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>'
目标是拥有一个将decode
进程中的每个令牌映射到正确的输入单词的函数,因为在这里它是:
desired_output = [[1],[2],[3],[4,5],[6]]
因为this
对应于ID 42
,而token
和ization
对应于索引{{ [19244,1938]
数组中的1}}。
答案 0 :(得分:2)
据我所知,它们不是内置方法,但是您可以自己创建一个方法:
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,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]]