Text CNN

The eds.text_cnn component is a simple 1D convolutional network to contextualize word embeddings (as computed by the embedding component passed as argument).

Parameters

PARAMETER	DESCRIPTION
nlp	The pipeline object TYPE: PipelineProtocol
name	The name of the component TYPE: str
embedding	Embedding module to apply to the input TYPE: TorchComponent[WordEmbeddingBatchOutput, BatchInput]
output_size	Size of the output embeddings Defaults to the input_size TYPE: Optional[int]
out_channels	Number of channels TYPE: int
kernel_sizes	Window size of each kernel TYPE: Sequence[int]
activation	Activation function to use TYPE: str
residual	Whether to use residual connections TYPE: bool
normalize	Whether to normalize before or after the residual connection TYPE: NormalizationPlacement

---