word-embedding - 如何使用translators.BertTokenizer编码多个句子？

Question

我想通过使用transform.BertTokenizer编码多个句子来创建一个小批量。似乎只用一个句子就可以了。如何使它适用于几个句子？

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

# tokenize a single sentence seems working
tokenizer.encode('this is the first sentence')
>>> [2023, 2003, 1996, 2034, 6251]

# tokenize two sentences
tokenizer.encode(['this is the first sentence', 'another setence'])
>>> [100, 100] # expecting 7 tokens

Answer 1

使用tokenizer.batch_encode_plus(documentation)。它将生成一个字典，其中包含input_ids，token_type_ids和attention_mask作为每个输入句子的列表:

tokenizer.batch_encode_plus(['this is the first sentence', 'another setence'])

输出:

{'input_ids': [[101, 2023, 2003, 1996, 2034, 6251, 102], [101, 2178, 2275, 10127, 102]], 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1]]}

如果只想生成input_id，则必须将 return_token_type_ids和 return_attention_mask设置为False:

tokenizer.batch_encode_plus(['this is the first sentence', 'another setence'], return_token_type_ids=False, return_attention_mask=False)

输出:

{'input_ids': [[101, 2023, 2003, 1996, 2034, 6251, 102], [101, 2178, 2275, 10127, 102]]}