hub_sparse_text_embedding_column: Module to construct dense representations from sparse text...
In tfhub: Interface to 'TensorFlow' Hub

The input to this feature column is a batch of multiple strings with arbitrary size, assuming the input is a SparseTensor.

hub_sparse_text_embedding_column(
  key,
  module_spec,
  combiner,
  default_value,
  trainable = FALSE
)

`key`	A string or [feature_column](https://tensorflow.rstudio.com/tfestimators/articles/feature_columns.html) 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.

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].

tfhub documentation built on Dec. 19, 2021, 9:07 a.m.