The workflow uses enhanced version that includes Portuguese texts. English data is taken from here:
https://www.kaggle.com/danofer/dbpedia-classes
The workflow show how to use BERT extension for Knime by Redfield to train models for text classification.
Required Python packages (need to be available in your TensorFlow 2 Python environment):
bert==2.2.0
bert-for-tf2==0.14.4
Keras-Preprocessing==1.1.2
numpy==1.19.1
pandas==0.23.4
pyarrow==0.11.1
tensorboard==2.2.2
tensorboard-plugin-wit==1.7.0
tensorflow==2.2.0
tensorflow-estimator==2.2.0
tensorflow-hub==0.8.0
tokenizers==0.7.0
tqdm==4.48.0
transformers==3.0.2
Used extensions & nodes
Created with KNIME Analytics Platform version 4.2.3
-
KNIME Base nodes
KNIME AG, Zurich, Switzerland
Version 4.2.3
-
KNIME Expressions
KNIME AG, Zurich, Switzerland
Version 4.2.2
-
KNIME JavaScript Views
KNIME AG, Zurich, Switzerland
Version 4.2.3
-
KNIME Javasnippet
KNIME AG, Zurich, Switzerland
Version 4.2.0
-
KNIME Math Expression (JEP)
KNIME AG, Zurich, Switzerland
Version 4.2.2
-
KNIME Plotly
KNIME AG, Zurich, Switzerland
Version 4.2.0
-
KNIME Quick Forms
KNIME AG, Zurich, Switzerland
Version 4.2.3
-
Redfield BERT Nodes
Redfield AB
Version 0.0.1
Legal
By downloading the workflow, you agree to our terms and conditions.
License (CC-BY-4.0)Discussion
Discussions are currently not available, please try again later.