block_zoo.encoder_decoder package

Submodules

block_zoo.encoder_decoder.SLUDecoder module

class block_zoo.encoder_decoder.SLUDecoder.SLUDecoder(layer_conf)

Bases: block_zoo.BaseLayer.BaseLayer

Spoken Language Understanding Encoder

References

Liu, B., & Lane, I. (2016). Attention-based recurrent neural network models for joint intent detection and slot filling. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, (1), 685–689. https://doi.org/10.21437/Interspeech.2016-1352

Parameters:layer_conf (SLUEncoderConf) – configuration of a layer

Attention(hidden, encoder_outputs, encoder_maskings)

Parameters:

• hidden – 1,B,D
• encoder_outputs – B,T,D
• encoder_maskings – B,T # ByteTensor

forward(string, string_len, context, encoder_outputs)

process inputs

Parameters:

• string (Variable) – word ids, [batch_size, seq_len]
• string_len (ndarray) – [batch_size]
• context (Variable) – [batch_size, 1, input_dim]
• encoder_outputs (Variable) – [batch_size, max_seq_len, input_dim]

Returns:

decode scores with shape [batch_size, seq_len, decoder_vocab_size]

Return type:

Variable

class block_zoo.encoder_decoder.SLUDecoder.SLUDecoderConf(**kwargs)

Bases: block_zoo.BaseLayer.BaseConf

Configuration of Spoken Language Understanding Encoder

References

Liu, B., & Lane, I. (2016). Attention-based recurrent neural network models for joint intent detection and slot filling. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, (1), 685–689. https://doi.org/10.21437/Interspeech.2016-1352

Parameters:

• hidden_dim (int) – dimension of hidden state
• dropout (float) – dropout rate
• num_layers (int) – number of BiLSTM layers
• num_decoder_output (int) –

declare()

Define things like “input_ranks” and “num_of_inputs”, which are certain with regard to your layer

num_of_input is N(N>0) means this layer accepts N inputs;

num_of_input is -1 means this layer accepts any number of inputs;

The rank here is not the same as matrix rank:

For a scalar, its rank is 0;

For a vector, its rank is 1;

For a matrix, its rank is 2;

For a cube of numbers, its rank is 3.

… For instance, the rank of (batch size, sequence length, hidden_dim) is 3.

if num_of_input > 0:

len(input_ranks) should be equal to num_of_input

elif num_of_input == -1:

input_ranks should be a list with only one element and the rank of all the inputs should be equal to that element.

NOTE: when we build the model, if num_of_input is -1, we would replace it with the real number of inputs and replace input_ranks with a list of real input_ranks.

Returns:None

default()

Define the default hyper parameters here. You can define these hyper parameters in your configuration file as well.

Returns:None

inference()

Inference things like output_dim, which may relies on defined hyper parameter such as hidden dim and input_dim

Returns:None

verify()

Define some necessary varification for your layer when we define the model.

If you define your own layer and rewrite this funciton, please add “super(YourLayerConf, self).verify()” at the beginning

Returns:None

block_zoo.encoder_decoder.SLUEncoder module

class block_zoo.encoder_decoder.SLUEncoder.SLUEncoder(layer_conf)

Bases: block_zoo.BaseLayer.BaseLayer

Spoken Language Understanding Encoder

References

Liu, B., & Lane, I. (2016). Attention-based recurrent neural network models for joint intent detection and slot filling. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, (1), 685–689. https://doi.org/10.21437/Interspeech.2016-1352

Parameters:layer_conf (SLUEncoderConf) – configuration of a layer

forward(string, string_len)

process inputs

Parameters:

• string (Variable) – [batch_size, seq_len, dim]
• string_len (ndarray) – [batch_size]

Returns:

output of bi-lstm with shape [batch_size, seq_len, 2 * hidden_dim] ndarray: string_len with shape [batch_size] Variable: context with shape [batch_size, 1, 2 * hidden_dim]

Return type:

Variable

class block_zoo.encoder_decoder.SLUEncoder.SLUEncoderConf(**kwargs)

Bases: block_zoo.BaseLayer.BaseConf

Configuration of Spoken Language Understanding Encoder

References

Liu, B., & Lane, I. (2016). Attention-based recurrent neural network models for joint intent detection and slot filling. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, (1), 685–689. https://doi.org/10.21437/Interspeech.2016-1352

Parameters:

• hidden_dim (int) – dimension of hidden state
• dropout (float) – dropout rate
• num_layers (int) – number of BiLSTM layers

declare()

Define things like “input_ranks” and “num_of_inputs”, which are certain with regard to your layer

num_of_input is N(N>0) means this layer accepts N inputs;

num_of_input is -1 means this layer accepts any number of inputs;

The rank here is not the same as matrix rank:

For a scalar, its rank is 0;

For a vector, its rank is 1;

For a matrix, its rank is 2;

For a cube of numbers, its rank is 3.

… For instance, the rank of (batch size, sequence length, hidden_dim) is 3.

if num_of_input > 0:

len(input_ranks) should be equal to num_of_input

elif num_of_input == -1:

input_ranks should be a list with only one element and the rank of all the inputs should be equal to that element.

NOTE: when we build the model, if num_of_input is -1, we would replace it with the real number of inputs and replace input_ranks with a list of real input_ranks.

Returns:None

default()

Define the default hyper parameters here. You can define these hyper parameters in your configuration file as well.

Returns:None

inference()

Inference things like output_dim, which may relies on defined hyper parameter such as hidden dim and input_dim

Returns:None

verify()

Define some necessary varification for your layer when we define the model.

If you define your own layer and rewrite this funciton, please add “super(YourLayerConf, self).verify()” at the beginning

Returns:None

verify_before_inference()

Some conditions must be fulfilled, otherwise there would be errors when calling inference()

The difference between verify_before_inference() and verify() is that:

verify_before_inference() is called before inference() while verify() is called after inference().

Returns:None

Module contents