Skip to content

cnn_encoder

allennlp.modules.seq2vec_encoders.cnn_encoder

[SOURCE]


CnnEncoder

@Seq2VecEncoder.register("cnn")
class CnnEncoder(Seq2VecEncoder):
 | def __init__(
 |     self,
 |     embedding_dim: int,
 |     num_filters: int,
 |     ngram_filter_sizes: Tuple[int, ...] = (2, 3, 4, 5),
 |     conv_layer_activation: Activation = None,
 |     output_dim: Optional[int] = None
 | ) -> None

A CnnEncoder is a combination of multiple convolution layers and max pooling layers. As a Seq2VecEncoder, the input to this module is of shape (batch_size, num_tokens, input_dim), and the output is of shape (batch_size, output_dim).

The CNN has one convolution layer for each ngram filter size. Each convolution operation gives out a vector of size num_filters. The number of times a convolution layer will be used is num_tokens - ngram_size + 1. The corresponding maxpooling layer aggregates all these outputs from the convolution layer and outputs the max.

This operation is repeated for every ngram size passed, and consequently the dimensionality of the output after maxpooling is len(ngram_filter_sizes) * num_filters. This then gets (optionally) projected down to a lower dimensional output, specified by output_dim.

We then use a fully connected layer to project in back to the desired output_dim. For more details, refer to "A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification", Zhang and Wallace 2016, particularly Figure 1.

Registered as a Seq2VecEncoder with name "cnn".

Parameters

  • embedding_dim : int
    This is the input dimension to the encoder. We need this because we can't do shape inference in pytorch, and we need to know what size filters to construct in the CNN.
  • num_filters : int
    This is the output dim for each convolutional layer, which is the number of "filters" learned by that layer.
  • ngram_filter_sizes : Tuple[int], optional (default = (2, 3, 4, 5))
    This specifies both the number of convolutional layers we will create and their sizes. The default of (2, 3, 4, 5) will have four convolutional layers, corresponding to encoding ngrams of size 2 to 5 with some number of filters.
  • conv_layer_activation : Activation, optional (default = torch.nn.ReLU)
    Activation to use after the convolution layers.
  • output_dim : Optional[int], optional (default = None)
    After doing convolutions and pooling, we'll project the collected features into a vector of this size. If this value is None, we will just return the result of the max pooling, giving an output of shape len(ngram_filter_sizes) * num_filters.

get_input_dim

class CnnEncoder(Seq2VecEncoder):
 | ...
 | def get_input_dim(self) -> int

get_output_dim

class CnnEncoder(Seq2VecEncoder):
 | ...
 | def get_output_dim(self) -> int

forward

class CnnEncoder(Seq2VecEncoder):
 | ...
 | def forward(self, tokens: torch.Tensor, mask: torch.BoolTensor)