如何将另一个预训练的 BERT 模型与 ktrain 文本分类器一起使用？

Question

我们如何为 ktrain 库中的文本分类器使用不同的预训练模型？使用时：

model = text.text_classifier('bert', (x_train, y_train) , preproc=preproc)

This uses the multilangual pretrained model

不过，我也想试试单语模型。即荷兰语：''wietsedv/bert-base-dutch-cased'，它也用于其他 k-train 实现，for example.

但是，当尝试在文本分类器中使用此命令时它不起作用：

model = text.text_classifier('bert', (x_train, y_train) ,
> preproc=preproc, bert_model='wietsedv/bert-base-dutch-cased')

或

model = text.text_classifier('wietsedv/bert-base-dutch-cased', (x_train, y_train), preproc=preproc)

有人知道怎么做吗？谢谢！

Answer 1

ktrain中有两个文本分类API。第一个是 text_classifier API，可用于 select 数量的变压器和 non-transformers 模型。第二个是 Transformer API，它可以与任何 transformers 型号一起使用，包括您列出的型号。

后者在this tutorial notebook and this medium article中有详细解释。

例如，您可以在下面的示例中将 MODEL_NAME 替换为您想要的任何模型：

示例：

# load text data
categories = ['alt.atheism', 'soc.religion.christian','comp.graphics', 'sci.med']
from sklearn.datasets import fetch_20newsgroups
train_b = fetch_20newsgroups(subset='train', categories=categories, shuffle=True)
test_b = fetch_20newsgroups(subset='test',categories=categories, shuffle=True)
(x_train, y_train) = (train_b.data, train_b.target)
(x_test, y_test) = (test_b.data, test_b.target)

# build, train, and validate model (Transformer is wrapper around transformers library)
import ktrain
from ktrain import text
MODEL_NAME = 'distilbert-base-uncased'  # replace this with model of choice
t = text.Transformer(MODEL_NAME, maxlen=500, class_names=train_b.target_names)
trn = t.preprocess_train(x_train, y_train)
val = t.preprocess_test(x_test, y_test)
model = t.get_classifier()
learner = ktrain.get_learner(model, train_data=trn, val_data=val, batch_size=6)
learner.fit_onecycle(5e-5, 4)
learner.validate(class_names=t.get_classes()) # class_names must be string values

# Output from learner.validate()
#                        precision    recall  f1-score   support
#
#           alt.atheism       0.92      0.93      0.93       319
#         comp.graphics       0.97      0.97      0.97       389
#               sci.med       0.97      0.95      0.96       396
#soc.religion.christian       0.96      0.96      0.96       398
#
#              accuracy                           0.96      1502
#             macro avg       0.95      0.96      0.95      1502
#          weighted avg       0.96      0.96      0.96      1502

如何将另一个预训练的 BERT 模型与 ktrain 文本分类器一起使用？

How to use another pretrained BERT model with the ktrain text classifier?

python

bert-language-model

ktrain