bert-embedding 安装及使用入门
安装
pip install bert-embedding
#如果要使用GPU
pip install mxnet-cu92 Note:
1. 安装过程中如果遇到WinError 5的权限问题，需要添加--user参数，即pip install --user mxnet-cu92
2. 若要支持cuda10.0需使用命令 pip install mxnet-cu100安装
3. 验证： 进入python 交互编辑器，输入命令from bert-embedding import BertEmbedding。如没有报错，则表示安装成功。
使用
from bert_embedding import BertEmbedding
bert_abstract = """We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.
Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers.
As a result, the pre-trained BERT representations can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications.
BERT is conceptually simple and empirically powerful.
It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE benchmark to 80.4% (7.6% absolute improvement), MultiNLI accuracy to 86.7 (5.6% absolute improvement) and the SQuAD v1.1 question answering Test F1 to 93.2 (1.5% absolute improvement), outperforming human performance by 2.0%."""
sentences = bert_abstract.split('\n')
bert_embedding = BertEmbedding()
result = bert_embedding(sentences)执行结果为如下图所示的包含元组（tokens, tokens embedding）的列表。
first_sentence = result[0]
first_sentence[0]
# ['we', 'introduce', 'a', 'new', 'language', 'representation', 'model', 'called', 'bert', ',', 'which', 'stands', 'for', 'bidirectional', 'encoder', 'representations', 'from', 'transformers']
len(first_sentence[0])
# 18
len(first_sentence[1])
# 18
first_token_in_first_sentence = first_sentence[1]
first_token_in_first_sentence[1]
# array([ 0.4805648 , 0.18369392, -0.28554988, ..., -0.01961522,
# 1.0207764 , -0.67167974], dtype=float32)
first_token_in_first_sentence[1].shape
# (768,) 
可用的预训练BERT模型
| book_corpus_wiki_en_uncased | book_corpus_wiki_en_cased | wiki_multilingual | wiki_multilingual_cased | wiki_cn | |
|---|---|---|---|---|---|
| bert_12_768_12 | ✓ | ✓ | ✓ | ✓ | ✓ |
| bert_24_1024_16 | x | ✓ | x | x | x |
from bert_embedding import BertEmbedding
bert_embedding = BertEmbedding(model='bert_24_1024_16', dataset_name='book_corpus_wiki_en_cased')下载了 1.35G的bert_24_1024_16_book_corpus_wiki_en_cased-4e685a96.params。
处理OOV（未识别词）有三种方法：avg (默认), sum, and last。
这里用的是sum来处理的OOV，即bert_embedding(sentences,'sum')。执行结果如下所示：
参考文献：
https://gluon-nlp.mxnet.io/model_zoo/bert/index.html
https://github.com/imgarylai/bert-embedding