BERT Embedder

Node accepts non-fine-tuned BERT model (magenta output port) or fine-tuned BERT mode (grey output port) and utilizes it for calculation of the embeddings of the texts. Embeddings are the vector representation of the texts that can be used for visualization, clustering, classification, etc.

Options

Settings

Sentence column

The column with texts that will be vectorized.

Max sequence length

The maximum length of a sequence after tokenization, limit is 512.

Advanced

Batch size

The size of a chunk of the input data to process.

Python

Python

Select one of Python execution environment options:

• use default Python environment for Deep Learning
• use Conda environment

Views

This node has no views

Workflows

• No workflows found

Links

• No links available

Developers