Specification of an entity tag present in the training data.
DIET (Dual Intent and Entity Transformer) is a multi-task architecture for intent classification and entity recognition.
The architecture is based on a transformer which is shared for both tasks.
A sequence of entity labels is predicted through a Conditional Random Field (CRF)
tagging layer on top of the transformer output sequence corresponding to the
input sequence of tokens. The transformer output for the
__CLS__ token and
intent labels are embedded into a single semantic vector space. We use the
dot-product loss to maximize the similarity with the target label and minimize
similarities with negative samples.
Declare instance variables with default values.
Prepares data for training.
Performs sanity checks on training data, extracts encodings for labels.
Train the embedding intent classifier on a data set.
Return the most likely label and its similarity to the input.
Persist this model into the passed directory.
Return the metadata necessary to load the model again.
Loads the trained model from the provided directory.