模型:
bert-large-uncased
BERT是一个在英语语料库上进行自监督训练的transformers模型。这意味着它仅使用原始文本进行预训练,而不会以任何方式对其进行标记(这就是为什么它可以使用大量公开可用的数据),它通过自动过程从这些文本中生成输入和标签。更确切地说,它通过以下两个目标进行预训练:
通过这种方式,该模型学习到了英语语言的内部表示,这可以用于提取对下游任务有用的特征:例如,如果您有一个带标签的句子数据集,可以使用由BERT模型生成的特征作为输入训练标准分类器。
此模型具有以下配置:
您可以直接使用原始模型进行掩码语言建模或下一个句子预测,但它主要用于在下游任务上进行微调。查看你感兴趣的任务的精调版本,请参阅 model hub 。
请注意,此模型主要旨在对使用整个句子(可能是掩码的)进行决策的任务进行微调,例如序列分类、标记分类或问题回答。对于文本生成等任务,您应该查看像GPT2这样的模型。
您可以使用管道直接使用此模型进行掩码语言建模:
>>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='bert-large-uncased') >>> unmasker("Hello I'm a [MASK] model.") [{'sequence': "[CLS] hello i'm a fashion model. [SEP]", 'score': 0.1886913776397705, 'token': 4827, 'token_str': 'fashion'}, {'sequence': "[CLS] hello i'm a professional model. [SEP]", 'score': 0.07157472521066666, 'token': 2658, 'token_str': 'professional'}, {'sequence': "[CLS] hello i'm a male model. [SEP]", 'score': 0.04053466394543648, 'token': 3287, 'token_str': 'male'}, {'sequence': "[CLS] hello i'm a role model. [SEP]", 'score': 0.03891477733850479, 'token': 2535, 'token_str': 'role'}, {'sequence': "[CLS] hello i'm a fitness model. [SEP]", 'score': 0.03038121573626995, 'token': 10516, 'token_str': 'fitness'}]
以下是如何在PyTorch中使用此模型获取给定文本的特征:
from transformers import BertTokenizer, BertModel tokenizer = BertTokenizer.from_pretrained('bert-large-uncased') model = BertModel.from_pretrained("bert-large-uncased") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input)
以及在TensorFlow中:
from transformers import BertTokenizer, TFBertModel tokenizer = BertTokenizer.from_pretrained('bert-large-uncased') model = TFBertModel.from_pretrained("bert-large-uncased") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='tf') output = model(encoded_input)
即使用于该模型的训练数据可能被认为是相对中立的,但此模型可能会有偏见的预测:
>>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='bert-large-uncased') >>> unmasker("The man worked as a [MASK].") [{'sequence': '[CLS] the man worked as a bartender. [SEP]', 'score': 0.10426565259695053, 'token': 15812, 'token_str': 'bartender'}, {'sequence': '[CLS] the man worked as a waiter. [SEP]', 'score': 0.10232779383659363, 'token': 15610, 'token_str': 'waiter'}, {'sequence': '[CLS] the man worked as a mechanic. [SEP]', 'score': 0.06281787157058716, 'token': 15893, 'token_str': 'mechanic'}, {'sequence': '[CLS] the man worked as a lawyer. [SEP]', 'score': 0.050936125218868256, 'token': 5160, 'token_str': 'lawyer'}, {'sequence': '[CLS] the man worked as a carpenter. [SEP]', 'score': 0.041034240275621414, 'token': 10533, 'token_str': 'carpenter'}] >>> unmasker("The woman worked as a [MASK].") [{'sequence': '[CLS] the woman worked as a waitress. [SEP]', 'score': 0.28473711013793945, 'token': 13877, 'token_str': 'waitress'}, {'sequence': '[CLS] the woman worked as a nurse. [SEP]', 'score': 0.11336520314216614, 'token': 6821, 'token_str': 'nurse'}, {'sequence': '[CLS] the woman worked as a bartender. [SEP]', 'score': 0.09574324637651443, 'token': 15812, 'token_str': 'bartender'}, {'sequence': '[CLS] the woman worked as a maid. [SEP]', 'score': 0.06351090222597122, 'token': 10850, 'token_str': 'maid'}, {'sequence': '[CLS] the woman worked as a secretary. [SEP]', 'score': 0.048970773816108704, 'token': 3187, 'token_str': 'secretary'}]
此偏差也会影响该模型的所有经过微调的版本。
BERT模型在 BookCorpus 上进行了预训练,该数据集包含11,038本未公开的图书和 English Wikipedia (不包括列表、表和标题)。
文本使用WordPiece和词汇量为30,000进行小写化和标记化。模型的输入格式如下:
[CLS] Sentence A [SEP] Sentence B [SEP]
在50%的情况下,句子A和句子B对应于原始语料库中的两个连续句子;在其他情况下,它是语料库中的另一个随机句子。请注意,这里认为的一个句子是一个连续的文本段落,通常比一个句子长。唯一的限制是带有这两个“句子”的结果总长度小于512个令牌。
每个句子的掩码过程的详细信息如下:
该模型在4个云TPU(16个TPU芯片总共)上进行了一百万个步骤的预训练,批量大小为256。90%的步骤的序列长度限制为128个标记,而剩余的10%为512个。使用的优化器是学习率为1e-4的Adam, β 1 = 0.9 \beta_{1} = 0.9 β 1 = 0 . 9 , β 2 = 0.999 \beta_{2} = 0.999 β 2 = 0 . 9 9 9 ,权重衰减为0.01,学习率预热步骤为10,000步,学习率线性衰减。
在经过微调的下游任务上,该模型实现了以下结果:
Model | SQUAD 1.1 F1/EM | Multi NLI Accuracy |
---|---|---|
BERT-Large, Uncased (Original) | 91.0/84.3 | 86.05 |
@article{DBLP:journals/corr/abs-1810-04805, author = {Jacob Devlin and Ming{-}Wei Chang and Kenton Lee and Kristina Toutanova}, title = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language Understanding}, journal = {CoRR}, volume = {abs/1810.04805}, year = {2018}, url = {http://arxiv.org/abs/1810.04805}, archivePrefix = {arXiv}, eprint = {1810.04805}, timestamp = {Tue, 30 Oct 2018 20:39:56 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1810-04805.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }