如何在推理后将标记化的词转换回原始词？

Question

我正在为已经训练好的 NER 模型编写推理脚本，但我在将编码标记（它们的 ID）转换为原始单词时遇到了问题。

# example input
df = pd.DataFrame({'_id': [1], 'body': ['Amazon and Tesla are currently the best picks out there!']})

# calling method that handles inference:
ner_model = NER()
ner_model.recognize_from_df(df, 'body')

# here is only part of larger NER class that handles the inference:
def recognize_from_df(self, df: pd.DataFrame, input_col: str):
    predictions = []
    df = df[['_id', input_col]].copy()
    dataset = Dataset.from_pandas(df)
    # tokenization, padding, truncation:
    encoded_dataset = dataset.map(lambda examples: self.bert_tokenizer(examples[input_col], 
                                      padding='max_length', truncation=True, max_length=512), batched=True)
    encoded_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask'], device=device)
    dataloader = torch.utils.data.DataLoader(encoded_dataset, batch_size=32)
    encoded_dataset_ids = encoded_dataset['_id']

    for batch in dataloader:
        output = self.model(**batch)
        # decoding predictions and tokens
        for i in range(batch['input_ids'].shape[0]):
            tags = [self.unique_labels[label_id] for label_id in output[i]]
            tokens = [t for t in self.bert_tokenizer.convert_ids_to_tokens(batch['input_ids'][i]) if t != '[PAD]']
        ...

结果接近我需要的：

# tokens:
['[CLS]', 'am', '##az', '##on', 'and', 'te', '##sla', 'are', 'currently', 'the', 'best', 'picks', 'out', 'there', ...]
# tags:
['X', 'B-COMPANY', 'X', 'X', 'O', 'B-COMPANY', 'X', 'O', 'O', 'O', 'O', 'O', 'O', 'O', ...]

如何把'am', '##az', '##on'和'B-COMPANY', 'X', 'X'合二为一token/tag？我知道有个方法叫convert_tokens_to_string在 Tokenizer 中，但它 returns 只是一个大字符串，很难映射到标签。

此致

Answer 1

如果您只想“合并”公司名称，则可以在线性时间内使用纯 Python。

为简洁起见，跳过句子标记 [CLS] 的开头：

tokens = tokens[1:]
tags = tags[1:]

下面的函数将合并公司令牌并适当增加指针：

def merge_company(tokens, tags):
    generated_tokens = []
    i = 0
    while i < len(tags):
        if tags[i] == "B-COMPANY":
            company_token = [tokens[i]]
            for j in range(i + 1, len(tags)):
                i += 1
                if tags[j] != "X":
                    break
                else:
                    company_token.append(tokens[j][2:])
            generated_tokens.append("".join(company_token))
        else:
            generated_tokens.append(tokens[i])
            i += 1

    return generated_tokens

用法非常简单，请注意 tags 也需要删除它们的 X：

tokens = merge_company(tokens, tags)
tags = [tag for tag in tags if tag != "X"]

这会给你：

['amazon', 'and', 'tesla', 'are', 'currently', 'the', 'best', 'picks', 'out', 'there']
['B-COMPANY', 'O', 'B-COMPANY', 'O', 'O', 'O', 'O', 'O', 'O', 'O']

如何在推理后将标记化的词转换回原始词？

How to convert tokenized words back to the original ones after inference?

python

pytorch

huggingface-transformers

huggingface-tokenizers

huggingface-datasets