hub_sparse_text_embedding_column
Module to construct dense representations from sparse text features.
Description
The input to this feature column is a batch of multiple strings with arbitrary size, assuming the input is a SparseTensor.
Usage
hub_sparse_text_embedding_column(
key,
module_spec,
combiner,
default_value, trainable = FALSE
)
Arguments
Arguments | Description |
---|---|
key | A string or feature_column identifying the text feature. |
module_spec | A string handle or a _ModuleSpec identifying the module. |
combiner | a string specifying reducing op for embeddings in the same Example. Currently, ‘mean’, ‘sqrtn’, ‘sum’ are supported. Using combiner = NULL is undefined. |
default_value | default value for Examples where the text feature is empty. Note, it’s recommended to have default_value consistent OOV tokens, in case there was special handling of OOV in the text module. If NULL , the text feature is assumed be non-empty for each Example. |
trainable | Whether or not the Module is trainable. FALSE by default, meaning the pre-trained weights are frozen. This is different from the ordinary tf.feature_column.embedding_column() , but that one is intended for training from scratch. |
Details
This type of feature column is typically suited for modules that operate on pre-tokenized text to produce token level embeddings which are combined with the combiner into a text embedding. The combiner always treats the tokens as a bag of words rather than a sequence. The output (i.e., transformed input layer) is a DenseTensor, with shape [batch_size, num_embedding_dim].